Tools for developers and makersOpen source

200 match your filters — 200 of them answered our check today.

Watching this group for 20 days · how we check

This week194 new arrivals5 stopped answering

An open-source runtime for building and running production AI agent systems, for developers who don't want to hand-roll retrieval, memory, and execution logic.

Open sourceSelf-hosted
What to know
How it works
Handles retrieval, memory, model routing, and verification instead of hardcoded pipelines
What's different
Self-hostable, open-source, with governed execution including planning, verification, and replay
Best for
Developers building production AI systems in Python or Go

Watched for 4 days · last checked today

Details →

Skeg

Live

A Rust-built, open-source vector database optimized to pack far more vectors per GB of RAM without losing recall, for teams running many-tenant deployments where memory is the bottleneck.

Open source
What to know
How it works
Multi-tenant architecture purpose-built for RAM efficiency at high tenant density.
What's different
Prioritizes memory efficiency over other tradeoffs; written in Rust.
Best for
High-density, many-tenant vector search deployments.

Watched for 2 days · last checked 2d ago

Details →

An open-source, cheaper Ahrefs alternative for keyword/backlink/site-audit research, connectable via MCP so an AI agent can run SEO work directly instead of a $100+/month subscription tool.

Open source
What to know
How it works
Provides keyword research, competitor research, backlinks, and site audits, connectable via MCP so an AI agent can work directly on SEO strategy and content.
What's different
Open source alternative to Ahrefs.
Pricing
Starting at $10/month instead of a $100+/month subscription.

Watched for 8 days · last checked 2d ago

Details →

Open-source malware scanner and runtime guard for AI agents

Domain registered 4 months ago

FreeWorks offlineOpen source
What to know
How it works
Vets AI agent skills and MCP servers for malicious behavior before install, scans what's already installed, and blocks hijack attempts at runtime, using 768 open ATR rules.
What's different
Scanned 96,096 published skills and found 751 malicious; rules already merged into Microsoft, Cisco, MISP, and OWASP tooling.
Pricing
Free, MIT licensed, fully on-device.

Watched for 8 days · last checked 2d ago

Details →

A free, open-source macOS menu bar app that tracks your ChatGPT Codex usage limits in real time for developers.

Domain registered 9 days ago

FreeOpen source
What to know
How it works
Lives in the macOS menu bar and shows current Codex usage at a glance.
Pricing
Free and open-source.

Watched for 7 days · last checked today

Details →

An open-source spec for tracking, versioning and securing AI prompts and models across a team's workflows.

Open source
What to know
How it works
An open-source spec to track, version, and secure AI prompts, models, and parameters, bringing supply chain security to agentic code.

Watched for 8 days · last checked 2d ago

Details →

A free, open-source Chrome DevTools extension for testing APIs — capture, inspect, edit, and replay HTTP requests without an external proxy, plus a quick header and secrets audit.

FreeOpen source
What to know
How it works
A Chrome DevTools extension that captures, inspects, edits, and replays HTTP/HTTPS requests without an external proxy, plus a Quick Security Check that audits headers and flags secrets or PII.
What's different
Works without needing to route traffic through an external proxy, unlike typical API testing setups.
Pricing
Free and open-source.
Best for
Developers testing API security directly inside Chrome DevTools.

Watched for 10 days · last checked today

Details →

A free, open-source macOS menu-bar app that keeps your Mac awake during downloads, renders or AI agent runs, with smart triggers and closed-display mode.

FreeOpen source
What to know
How it works
A native macOS menu-bar app that keeps your Mac awake during downloads, renders, or AI agent runs using smart triggers, timed sessions, and a closed-display mode.
Pricing
Free and open source.
Best for
Mac users running long downloads, renders, or agent tasks that need the machine to stay awake.

Watched for 12 days · last checked today

Details →

A directory where indie makers list product launches to get ongoing visibility after launch day, rather than the one-day spike typical of most launch boards.

FreeOpen sourceNo subscription
What to know
How it works
Founders launch products to get discovered, earn upvotes, and build momentum, moving through leaderboards, searchable maker profiles, archives, and a Hall of Fame with recurring promotion after launch day.
What's different
Focused on launches that stay visible after release day rather than the single 24-hour spike typical of most launch boards.
Best for
Indie hackers and solo founders launching their first product, or small teams launching a new tool or SaaS.

Watched for 18 days · last checked today

Details →

An Apache-2.0, offline-first toolkit that renders in-browser previews of Office, PDF, CAD and other files without a server-side conversion step. For developers embedding document viewers in self-hosted apps.

Domain registered 1 month ago

Works offlineOpen sourceSelf-hosted
What to know
How it works
A browser-native toolkit that renders read-only previews of Office, PDF/OFD, CAD, archive, email, diagram, 3D, media and data files (206 extensions across 24 pipelines) without a mandatory server-side conversion step.
What's different
Apache-2.0 licensed and offline-first; components can be self-hosted and used across Vanilla JS, React, Vue, Svelte and jQuery.
Best for
Developers embedding document/file preview into private or internal web apps.
Watch out
Read-only fidelity varies by file format.

Watched for 13 days · last checked 2d ago

Details →

An open-source Python library that compresses LLM prompts and context to cut token costs while preserving instructions.

Open source
What to know
How it works
Compresses prompts, RAG document contexts, and multi-turn chat logs in one line of code.
Pricing
Open-source Python package.
Best for
Developers who want to cut LLM token costs 40-70% without losing instruction fidelity.

Watched for 11 days · last checked today

Details →

AEGIS

Live

A self-hosted, MIT-licensed framework for running your own local-LLM AI agents over your tasks, money, knowledge and homelab data, built for developers who want to fork and customize it rather than use a hosted SaaS.

Domain registered 4 years ago

Open sourceSelf-hosted
What to know
How it works
A self-hosted platform where named agents run durable Temporal workflows over your own data (tasks, money, knowledge, homelab alerts), asking for a decision only when they truly need one.
What's different
Local-LLM-first and MIT-licensed, designed to be forked and customized rather than used as a hosted SaaS.
Pricing
Open source (MIT-licensed).
Best for
Developers who want to self-host and customize their own AI agent framework over personal data.

Watched for 13 days · last checked 2d ago

Details →

An open-source deception (honeypot) platform for security teams; the listing gives little detail beyond that positioning.

Domain registered 1 month ago

FreeOpen source
What to know
How it works
An open-source deception (honeypot) platform for security teams.
Best for
Security teams and developers who want an open-source deception/honeypot tool.

Watched for 14 days · last checked 2d ago

Details →

An open-source, self-hosted memory layer that links related facts across Claude, ChatGPT, Cursor and Codex via MCP. Built for developers comfortable self-hosting on Cloudflare, not a plug-and-play tool.

Open sourceSelf-hosted
What to know
How it works
A memory layer that remembers projects, people, decisions and preferences across Claude, ChatGPT, Cursor, Codex and any MCP client, automatically linking related memories and following those connections during recall.
What's different
Open source and self-hosted in your own Cloudflare account, and distinguishes settled decisions from drafts/stale context.
Best for
Developers comfortable self-hosting on Cloudflare who want a shared memory layer across multiple AI tools.

Watched for 15 days · last checked today

Details →

An open-source Discord extension that translates messages using your own translation API key, built privacy-first and developer-friendly. Really for technically comfortable users willing to set up their own API key.

Data stays with youOpen source
What to know
How it works
A Discord extension that translates messages using your own translation API key.
What's different
Open source and privacy-first — translation runs through your own API key rather than a shared third-party service.
Best for
Technically comfortable Discord users willing to set up their own translation API key.
Watch out
Requires bringing and configuring your own API key to work.

Watched for 14 days · last checked 2d ago

Details →

Scans your site the way AI crawlers like GPTBot and ClaudeBot actually see it, scores 32 checks, then an AI assistant walks you through fixes, including on WordPress.

Open source
What to know
How it works
Scans a website the way AI crawlers like GPTBot and ClaudeBot actually see it (they don't run JS), running 32 checks and producing a 0-100 score in about 5 seconds; an AI assistant then walks non-developers through fixes, including on WordPress.
What's different
Open source with a CLI, and built specifically around what AI crawlers see rather than standard SEO checks.
Best for
Site owners, including non-developers on WordPress, worried their site is invisible to AI crawlers despite ranking well on Google.

Watched for 17 days · last checked today

Details →

Measures how well AI writes code against your library's current API instead of guessing AI-friendliness.

Open source

Watched for 1 day · last checked 1d ago

Details →

Pandia

Live

Native desktop app for opening and editing multi-gigabyte JSON files instantly, for developers who hit size limits in browser-based JSON viewers.

FreeWorks offlineData stays with youOpen source
What to know
How it works
Opens huge files with no upload, shows JSON as Tree, Code, Grid, Graph, or Compare views, generates types for 9 languages.
What's different
Handles multi-gigabyte files offline where most JSON tools choke or require upload.
Pricing
Free
Watch out
Desktop-only (macOS, Windows, Linux).

Watched for 5 days · last checked today

Details →

Repurposes the Caps Lock key as a physical sleep-prevention switch so long-running builds, agents, or SSH sessions survive a closed MacBook lid.

FreeNo sign-upOpen source
What to know
How it works
Turns Caps Lock into a physical switch that keeps your MacBook awake; light shows active state.
Pricing
Free and open source.
Watch out
Requires Caps Lock not already assigned to something else.

Watched for 2 days · last checked 2d ago

Details →

An open-source toolkit for building AI features — chat, RAG, speech, vision — that runs entirely in the browser with no servers and no data leaving the device. Built for developers.

Domain registered 7 months ago

Works offlineData stays with youOpen source
What to know
How it works
An open-source toolkit for running AI entirely in the browser: LLM chat across 76 models, RAG and vector search, Whisper and Kokoro speech, and vision, with no server or API key required. Runs on WebGPU with a WebAssembly fallback.
What's different
Data never leaves the device, and it ships a zero-dependency core plus a shadcn UI registry of 107 components and 36 installable blocks for building on top of it.
Pricing
Open source (MIT license).
Best for
Developers building browser-based AI features without standing up servers or managing API keys.

Watched for 12 days · last checked 1d ago

Details →

Lets developers monitor their OpenAI Codex usage from the macOS menu bar instead of checking a web dashboard, using only their existing CLI session.

Data stays with youOpen source

Watched for 1 day · last checked 1d ago

Details →

Local firewall binary that sits between AI agents and the network to block secret leaks, prompt injection, SSRF, and MCP tool poisoning, for developers running autonomous agents, producing a signed offline-verifiable receipt instead of blind trust.

No sign-upWorks offlineOpen source
What to know
How it works
A single Go binary scans every outbound request from an agent and writes a signed receipt you verify offline against a published key when it blocks something.
Pricing
Apache 2.0, install via brew.
Best for
Developers whose AI agents have shell access, secrets, and an open line to the internet.

Watched for 7 days · last checked 1d ago

Details →

An open-source, self-hostable runtime for running AI agents across 24 LLM providers, with an MCP plugin marketplace and sandboxed code execution — built for developers.

Open sourceSelf-hosted
What to know
How it works
An open-source, self-hostable runtime for running AI agents, with a 5-tier memory system, support for 24 LLM providers, an MCP plugin marketplace, and sandboxed code execution; installs with one command.
What's different
MIT-licensed and self-hostable with a plugin marketplace, rather than a closed hosted agent platform.
Pricing
Open source, MIT license.
Best for
Developers who want to run and customize AI agents across multiple LLM providers on their own infrastructure.

Watched for 13 days · last checked 7d ago

Details →

Tool that reads your local git history to build a verifiable credential of what you've actually built, without exposing NDA-protected code.

FreeOpen source
What to know
How it works
Reads git history locally, generates a profile of your work, then you defend it live in Q&A
What's different
Never shares actual code, only derived claims you approve first
Pricing
CLI is free and open source
Best for
Developers and recruiters wanting proof of work beyond a resume

Watched for 5 days · last checked today

Details →

ADE

Live

Syncs your existing coding-agent subscriptions across web, desktop, terminal and mobile so you can start a session on one device and continue on another.

FreeOpen source
What to know
How it works
Chats sync across all surfaces; runs on web, desktop, terminal, and mobile.
Pricing
Free forever, open source.
Best for
Developers who already pay for multiple coding-agent subscriptions and switch devices often.

Watched for 2 days · last checked 2d ago

Details →

Lets developers add customizable vector maps to their projects instead of paying for commercial map APIs with sign-ups and rate limits.

FreeNo sign-upOpen source
What to know
How it works
Vector tile server built on OpenStreetMap and MapLibre with 3D terrain and hillshading.
Pricing
free, no API keys, no request limits

Watched for 1 day · last checked 1d ago

Details →

An open-source React component library of prebuilt UI pieces for developers building web app frontends, rather than a full app framework.

Open source
What to know
How it works
An open-source library of prebuilt React components and interaction building blocks for product frontends.
Best for
Developers building web app frontends who want ready-made React components instead of building from scratch.

Watched for 14 days · last checked today

Details →

Sim

Live

An open-source workspace for building and connecting AI agent workflows to 1,000+ integrations and LLMs; a developer/maker tool rather than a no-code product.

Open source
What to know
How it works
An open-source workspace for building agentic workflows, connecting AI agents to 1,000+ integrations and LLMs.
What's different
Open source.
Best for
Developers building custom AI agent workflows across many integrations.

Watched for 17 days · last checked today

Details →

Caw

Live

Web-based terminal multiplexer for monitoring and controlling multiple AI coding agent sessions, including on mobile.

Domain registered 13 days ago

Open source
What to know
How it works
A web terminal multiplexer for monitoring and interacting with multiple AI agent sessions (OpenCode, Claude Code, Codex, Copilot, etc.), including a Kanban board, file browser, push notifications, and on-demand git worktrees.
What's different
Open source and built to work well on mobile.

Watched for 4 days · last checked today

Details →

Open-source AI motion graphics editor that generates editable animation files instead of rendered video.

Domain registered 4 days ago

Open source
What to know
How it works
Generates editable motion-graphics files, instead of rendered video, that you can refine visually or in code.
What's different
Open-source and structured so animations are versionable and reusable across developers, designers, and AI agents.

Watched for 4 days · last checked today

Details →

Restarts a fresh Codex worker and critic each cycle to build, test, and fix code against a saved rubric.

Domain registered 5 days ago

Open source
What to know
How it works
Starts a fresh Codex worker and critic every cycle against a saved GUIDELINES.md rubric; failures become concrete fix notes for the next cycle.
What's different
Open source and zero-dependency Node.js, runs local, sandboxed, and cancellable from a dashboard.

Watched for 4 days · last checked today

Details →

Free open-source firewall that sits between AI agents and your systems to block risky actions like deleting production data.

Domain registered 24 years ago

FreeOpen source
What to know
How it works
Intercepts agent actions before execution and blocks high-risk ones
Pricing
Free, open source
Best for
Developers running AI agents with system access they want to constrain

Watched for 4 days · last checked today

Details →

cngx

Live

A CLI that actually runs your test suite before letting an AI coding agent's merge-ready claim through, catching agents that say tests passed when they didn't.

Open source
What to know
How it works
A CLI that reads an AI coding agent's claim that tests passed, actually runs your real checks (pytest, npm test, go test, etc.), and blocks the merge if the agent's story doesn't match the command output.
What's different
The verdict comes from real command output, not a regex match on the agent's claimed text.
Best for
Developers using AI coding agents who want a guardrail against merge-ready claims that were never actually tested.

Watched for 16 days · last checked today

Details →

Lets makers turn plain screenshots into polished product videos in-browser instead of using a full video editor.

FreeOpen sourceCan export my data
What to know
How it works
Client-native WASM video generation with animated templates and auto-generated gradient backgrounds.
Pricing
free, open-source, watermark-free export

Watched for 1 day · last checked 1d ago

Details →

Lets people encrypt files with PGP without a GnuPG install instead of using command-line-only tools.

Works offlineOpen sourceNo tracking
What to know
What's different
compatible with GPG, Kleopatra, and Thunderbird
Pricing
free, MIT license

Watched for 1 day · last checked 1d ago

Details →

Lets Chrome users open saved bookmarks with a keyboard shortcut instead of digging through bookmark menus.

FreeWorks offlineOpen source
What to know
How it works
Type a short code to open a page or a whole folder as a tab group; on-device AI adds tags and semantic search by default.
Pricing
free, open source

Watched for 1 day · last checked 1d ago

Details →

Lets people using multiple AI chatbots reuse the same project context instead of rewriting it each time they switch platforms.

FreeData stays with youOpen source
What to know
Pricing
free, open-source

Watched for 1 day · last checked 1d ago

Details →

Open-source SDK that lets AI agents build, evaluate, and optimize other agents cheaply.

Domain registered 10 days ago

Open source
What to know
How it works
An SDK that lets AI agents build, evaluate, and optimize other agents, supporting 1,000+ models, reusable skills, and automatic data generation.
What's different
Open source.
Pricing
About $0.02 to build a complete RAG application with one prompt.

Watched for 4 days · last checked today

Details →

Chimlo

Live

Free open-source macOS app that shows Codex and Claude Code agent status in the MacBook notch so you don't have to hunt through terminals.

FreeOpen source
What to know
How it works
Notch UI shows working/waiting/finished/failed agent states, lets you answer prompts inline
Pricing
Free, open source
Best for
Developers running multiple coding-agent sessions at once

Watched for 4 days · last checked today

Details →

An open-source platform for orchestrating LLM-based security research pipelines across vulnerability discovery and code analysis.

Domain registered 8 months ago

Open source
What to know
How it works
chains LLMs and custom agents into reusable security research workflows
Pricing
open source

Watched for 5 days · last checked today

Details →

Open-source memory storage for AI agents where every fact has provenance and deletion is cryptographically provable and auditable.

Open source
What to know
How it works
forget() destroys the data's key and issues a signed deletion certificate
What's different
reconciles GDPR deletion requirements with EU AI Act record-keeping
Pricing
open source (Apache-2.0), runs on plain Postgres

Watched for 5 days · last checked today

Details →

A personal AI assistant that runs fully on your own machine via local models, chatting through Telegram with Gmail/Calendar access.

Open sourceNo subscription
What to know
How it works
local models handle chat, memory and web search; cloud used only as a fallback
What's different
requires human approval for actions and runs in a Docker sandbox
Pricing
no subscription, open source (Apache 2.0)
Best for
Windows users wanting a private, local AI assistant

Watched for 5 days · last checked today

Details →

Open-source tool that clones any public website into clean, componentized Next.js or Vite code deterministically.

Domain registered 28 days ago

FreeOpen source
What to know
How it works
point it at a URL, get faithful componentized code in minutes
What's different
fully deterministic so fast, cheap, consistent
Pricing
free
Best for
developers rebuilding or copying web UIs

Watched for 6 days · last checked today

Details →

A stealth browser engine that lets scraping and automation scripts avoid bot detection, for developers running Playwright or Puppeteer agents.

Open source
What to know
How it works
Drop-in Chromium that reads as ordinary Chrome to detection systems
What's different
keeps existing Playwright/Puppeteer code unchanged, open BSD-3 engine
Best for
developers building scrapers or web-acting AI agents

Watched for 6 days · last checked today

Details →

Drive your coding agent from your phone via the same live tmux session as your computer, with git diffs, site preview, and thumb approvals.

Domain registered 30 days ago

Open sourceSelf-hosted
What to know
How it works
mirrors your tmux session to your phone, zero install
What's different
agents like Claude Code push when they need you; approve with a thumb
Pricing
open-source (AGPL)

Watched for 6 days · last checked today

Details →

Managed cloud that deploys open-source AI agents in one click, each in its own isolated VM with snapshots and bring-your-own-model.

Domain registered 30 days ago

Open source
What to know
How it works
one-click deploy; each agent runs in a kernel-isolated VM
What's different
automatic/manual snapshots make agents recoverable
Best for
developers running open-source AI agents

Watched for 6 days · last checked today

Details →

A free open-source cat mascot for apps that stays visually consistent across new poses and scenes, for builders who don't want a generic AI-generated look.

FreeOpen source
What to know
How it works
Pins each new generation to fixed reference images and a locked style prompt to keep the mascot consistent.
Pricing
Free for commercial use.
Best for
Developers adding a consistent character to onboarding flows or chatbots.

Watched for 7 days · last checked 1d ago

Details →

Reame

Live

A self-hosted LLM inference server that runs on cheap CPU hardware, for developers who want local AI inference without a GPU.

Open sourceSelf-hosted
What to know
How it works
CPU-first inference on llama.cpp with an OpenAI-compatible API
What's different
caches prompts and past generations so repeat requests cost less
Pricing
MIT licensed, works on a €5 VPS or free-tier ARM box
Best for
developers running narrow, repetitive AI workloads on cheap hardware

Watched for 6 days · last checked today

Details →

Pylva

Live

Tracks the real infrastructure cost of each customer for AI agent builders, so they can set margin caps per customer.

Open source
What to know
How it works
SDK-only telemetry tracks LLM and non-LLM usage per customer
What's different
open source, reactive rules like per-customer cost caps
Pricing
open source
Best for
builders of AI agent products billing by usage

Watched for 6 days · last checked today

Details →

im-bot

Live

A messaging platform where AI agents are added like contacts and join group chats with humans, for teams who want multi-agent collaboration inside a shared chat thread instead of separate agent tools.

Open source
What to know
How it works
Add agents by invite code; persistent per-room agent sessions with full context; connect any LLM via an open-source connector.
What's different
In-chat model switching, file sharing, 8-language support built in.

Watched for 2 days · last checked 1d ago

Details →

bpad

Live

An open-source encrypted note-taking PWA that encrypts notes client-side before sync, for people who want their notes unreadable to the server even in the cloud.

Works offlineData stays with youOpen source
What to know
How it works
Notes encrypted in-browser with Argon2id + AES-256-GCM before leaving the device; only ciphertext reaches the server.
What's different
Works offline across devices while staying private.

Watched for 2 days · last checked 1d ago

Details →

A local, single-file memory store for coding agents over MCP that cites its sources and abstains rather than hallucinating when it lacks evidence.

Open source
What to know
How it works
One Rust binary, one SQLite file, zero network, talks to agents over MCP.
Pricing
Open source, AGPL-3.0.
Watch out
Abstains instead of answering when there's no evidence.

Watched for 2 days · last checked 1d ago

Details →

Sanwo

Live

An open-source SDK that unifies multiple payment providers (Paystack, Flutterwave, Razorpay, Monnify, Interswitch) behind one API, instead of integrating each provider separately across web, mobile, and no-code platforms.

FreeOpen source
What to know
How it works
Native SDKs for React, Vue, Svelte, React Native, Flutter, iOS, Android, plus no-code plugins for Shopify, WordPress, Webflow, Wix, Squarespace.
Pricing
Free forever, Apache-2.0 licensed.

Watched for 2 days · last checked 1d ago

Details →

An open-source DDI platform unifying DNS, DHCP, and IP address management behind a FastAPI control plane and React UI.

Open source
What to know
How it works
Runs its own BIND9, PowerDNS, and Kea service containers managed through a FastAPI backend and React front end.

Watched for 7 days · last checked 1d ago

Details →

Open-source terminal supervisor that manages planning and worker AI agents for Codex, Claude Code, and Ollama sessions.

Open source
What to know
How it works
An open-source terminal supervisor where a planning agent proposes versioned plans you approve, then isolated worker agents implement the work while it handles scheduling, review, and recovery.

Watched for 4 days · last checked today

Details →

Open-source governance layer that keeps long-running AI coding agents on track with verified state and auditable handoffs.

Open source
What to know
How it works
Verifies a long-running AI agent's state and pushes one valid next action, using a graph-backed backlog with independent worker and QA roles and auditable bypasses.
What's different
Open-source governance layer aimed at preventing agents from drifting during long-running work.

Watched for 4 days · last checked today

Details →

An open-source platform for simulating multi-agent scenarios like markets, city governance, or logistics.

Open source
What to know
How it works
Define goals, resources, rules and tools, load a scenario pack, configure your LLM, and let multiple agents compete inside one simulated world.
What's different
Open-source; every observation, decision, action, and consequence is visible and replayable.

Watched for 6 days · last checked today

Details →

Gives developers open-source infrastructure for AI-native financial operations instead of building it from scratch.

Open source

Watched for 1 day · last checked 1d ago

Details →

An open-source framework for running inference and evaluation on generative world-model AI (video, 3D/4D, embodied agents) via CLI/TUI/Studio interfaces — research infrastructure for AI developers, not an end-user app.

Open source
What to know
How it works
An open-source framework that unifies inference and evaluation for generative world-model AI, supporting video generation, interactive worlds, 3D/4D representations and embodied models through TUI, CLI and Studio interfaces, with a growing collection of integrated models and 58 benchmarks.
What's different
Unifies inference and evaluation for world models under one workflow instead of requiring separate tooling per model type.
Pricing
Open-source.
Best for
AI researchers and developers working on world models who need a common infrastructure for running and benchmarking them.

Watched for 16 days · last checked today

Details →

An open-source discovery platform for random generators to find something fun or useful in seconds.

Domain registered 2 years ago

Open source
What to know
How it works
An open-source discovery platform of random generators for finding something fun, useful, or unexpected in seconds.

Watched for 5 days · last checked today

Details →

A free, open-source MCP server that lets AI agents safely read and write your Things 3 tasks, plus adds Kanban, matrix and time-blocking views Things 3 lacks.

FreeNo sign-upWorks offlineOpen source
What to know
How it works
reads are read-only, writes go only through Things' official URL scheme so agents can't corrupt data
Pricing
free, open source (MIT), no cloud or account
Best for
Things 3 users on macOS who want AI task management without risking their data

Watched for 5 days · last checked today

Details →

A self-hosted development environment for running coding agents (Claude Code, Codex, Cursor, etc.) from desktop or phone.

Domain registered 1 month ago

No sign-upOpen sourceSelf-hosted
What to know
How it works
start a task on desktop, get pushed for input, review diffs and ship from mobile
Pricing
MIT license, self-hosted, no vendor cloud or account
Best for
developers who want to manage agent sessions across devices

Watched for 5 days · last checked today

Details →

A free open-source Windows dashboard that shows your Codex usage quota, reset timers, and token counts at a glance.

FreeOpen sourceNo subscription
What to know
How it works
Displays weekly quota, reset time, reset-credit cards, and lifetime token usage for Codex
Pricing
Free and open-source

Watched for 4 days · last checked today

Details →

An open-source Next.js starter kit with auth, Stripe billing, and Mailtrap email already wired up, for developers bootstrapping a SaaS.

Open source
What to know
How it works
Pre-built scaffolding for auth, multi-tenancy, Stripe billing, and transactional email via Mailtrap
Best for
Developers and indie hackers starting a new SaaS project
Watch out
Blank-slate scaffolding, not a finished product

Watched for 5 days · last checked today

Details →

A local gateway that lets every AI coding client share one set of MCP server connections instead of configuring each tool separately, cutting how many tools your agent has to load.

FreeNo sign-upWorks offlineOpen source
What to know
How it works
A local-first, open-source gateway. You set up and authenticate each MCP server once, and every connected AI client — Claude, Cursor, VS Code, Codex — shares that same connection instead of you configuring it per tool.
What's different
Claims up to 91% less tool-token overhead by giving an agent a handful of meta-tools instead of loading hundreds of individual tool definitions; API keys stay in the OS keychain.
Pricing
Free, open source, no sign-up.
Best for
Developers running multiple AI coding clients against the same set of MCP servers who don't want to re-authenticate each one separately.
Watch out
The '91% overhead cut' figure is the product's own claim; we haven't independently benchmarked it.

Watched for 20 days · last checked today

Details →

A local terminal dashboard that manages multiple Claude Code agent sessions in one view, with worktree isolation and diff review, instead of juggling separate windows.

Works offlineOpen source
What to know
How it works
Runs locally and open source; install with a single npx command, with all sessions shown on one live terminal wall.
Best for
Developers running several Claude Code agents at once.

Watched for 7 days · last checked 1d ago

Details →

A self-hostable tool that turns your open browser tabs into a searchable, chat-queryable knowledge base by vectorizing their content.

Open sourceSelf-hosted
What to know
How it works
Captures open-tab content, vectorizes it with FAISS, and answers natural-language questions across everything you have open.
Best for
Developers who want to search across many open tabs without a hosted service.

Watched for 7 days · last checked 1d ago

Details →

An open-source visual table editor with a Python DSL that exports to HTML, PDF, and Excel, for developers automating dashboards and reports without hand-writing layout code.

Open sourceCan export my data
What to know
How it works
A live preview grid stays bidirectionally synced with Python code via an AST; design visually or write code and both update.
Best for
Developers automating BI dashboards, KPI cards, Gantt charts, or heatmaps.

Watched for 7 days · last checked 1d ago

Details →

Reviews pull requests and maps code dependencies so developers can understand large codebases before refactoring, without indexing delay.

Domain registered 1 month ago

Open sourceSelf-hosted
What to know
How it works
Builds a dependency graph and semantic index, cites source in answers
What's different
instant PR reviews with no indexing step, open source and self-hostable
Pricing
open source
Best for
developers working in large or unfamiliar codebases

Watched for 6 days · last checked today

Details →

Self-hosted, cookieless, open-source analytics with a live visitor map, Stripe revenue attribution, and tracking of which pages AI crawlers read.

Data stays with youOpen sourceSelf-hosted
What to know
How it works
run it on your server; real-time map, Stripe channels, AI-crawler pages
What's different
no cookies or consent banner, data never leaves your machine
Pricing
MIT

Watched for 6 days · last checked today

Details →

An open-source, self-hostable memory layer for AI agents that keeps episodic and semantic context within LLM token limits across sessions. For developers, not an end-user app.

Domain registered 3 months ago

Open sourceSelf-hosted
What to know
How it works
An open-source, self-hostable memory runtime for AI agents providing durable episodic and semantic memory, with ranked retrieval and token-bounded context bundles designed for LLM applications.
What's different
Treats memory as a first-class primitive that persists across sessions rather than an afterthought within a single conversation.
Best for
AI/ML engineers building autonomous agents with frameworks like LangChain, CrewAI or AutoGen.

Watched for 13 days · last checked 7d ago

Details →

Instant, no-signup temporary email aliases with rotating domains to dodge blacklists, plus a public API for developers who want to build it into their own workflows.

FreeNo sign-upData stays with youOpen source
What to know
How it works
Creates custom, instant temporary email aliases (any inbox name) without sign-up, receiving emails in real-time from multiple rotating domains to avoid blacklists; also offers a public API and open-source frontend.
What's different
Rotating domains to avoid blacklists, plus no popups, timers, or tracking, unlike traditional temp mail tools.
Pricing
Free.
Best for
People needing disposable email for sign-up verifications or testing, and developers who want to build disposable email into their own workflows via the API.

Watched for 14 days · last checked 8d ago

Details →

An open-source local tool for planning and executing encrypted-file key rotation with AI-assisted threat interpretation and policy controls.

Open source
What to know
How it works
An open-source local tool that turns recipient changes into reviewable key-rotation plans, with AI interpreting threat signals while deterministic policy controls approval and execution.
What's different
Keys, plaintext, and ciphertext never pass through the model; includes a bundled post-quantum sample vault run with Docker.

Watched for 4 days · last checked today

Details →

A canvas tool where dropped documents are read by AI to auto-build a live workspace of dashboards, maps, and timelines.

Open source
What to know
How it works
You drop documents onto a canvas; AI reads them, discovers connections, and assembles a living workspace of dashboards, maps, and timelines that updates automatically when a source file changes.
What's different
Open source, built in one week with Codex; answers trace back to their source through animated ribbons.

Watched for 4 days · last checked today

Details →

Gloss

Live

A hotkey tool that explains confusing technical instructions AI coding agents give you, like what an env file is and why you're being asked for it.

FreeOpen source
What to know
How it works
Highlight text, press a hotkey, get a plain-language explanation of what it means and what changes if you say yes or no.
Pricing
Free, open source.
Best for
Non-technical users following AI agent instructions they don't understand.

Watched for 4 days · last checked today

Details →

A practice platform teaching real open-source contribution skills like git mechanics, code review, and licensing through hands-on exercises.

Open source
What to know
How it works
188 practice problems requiring real commands and judgment calls, not multiple choice.
Best for
Developers who want to learn to contribute to open source projects.

Watched for 4 days · last checked today

Details →

BiliTV

Live

An open-source Bilibili client for LG TVs that runs entirely on-device with no external server, supporting 4K and bullet-comment overlays.

FreeWorks offlineOpen source
What to know
How it works
on-device Node.js service proxies the API/CDN directly on the TV
What's different
open source, MIT licensed, no PC or server needed
Pricing
free
Best for
LG webOS TV owners wanting Bilibili with danmaku and 4K support

Watched for 4 days · last checked today

Details →

An open-source toolkit that keeps HTML documents visually identical across browser preview, print, and PDF/EPUB export instead of reflowing per surface.

Open sourceCan export my data
What to know
How it works
maintains one canonical paginated document across HTML/CSS preview, print, and EPUB export
What's different
open source, works with React or framework-neutral core, no server renderer needed
Best for
developers building documents that must print exactly as previewed

Watched for 4 days · last checked today

Details →

VeloIQ

Live

An open-source Python framework that auto-generates a REST API, admin back-office, and React CRUD UI from your data models, for developers building internal tools locally.

Domain registered 2 months ago

Works offlineOpen source
What to know
How it works
define data models once in Python; generates API, admin panel, and UI automatically
What's different
open source, local-first, data stays on your infrastructure
Best for
developers building CRUD apps without hand-building each layer

Watched for 4 days · last checked today

Details →

An offline clipboard tool that automatically redacts PII and API keys before you paste into ChatGPT, coding assistants, or anywhere else.

Works offlineOpen source
What to know
How it works
detects and redacts secrets/PII from clipboard content before paste
What's different
fully local processing, open source
Best for
developers who paste code or data into LLMs and AI tools

Watched for 4 days · last checked today

Details →

Audits a website's SEO from real Search Console data and publishes the results as a public, verifiable proof page instead of a private report.

Domain registered 4 months ago

Open source
What to know
How it works
scores technical SEO, performance, E-E-A-T, keywords and strategy into one score, published publicly
What's different
open-source audit playbook you can inspect or run yourself
Watch out
weak signals are published too, not hidden

Watched for 4 days · last checked today

Details →

Set of open-source skills that let Claude Code or other AI agents scrape Google Maps business listings, extract emails and draft cold outreach.

FreeOpen source
What to know
How it works
8 installable skills covering scraping, email extraction, competitor and review analysis
Pricing
3 skills free/local; scraping skills use a paid API with free starting credits
Best for
Developers building automated local-business lead-generation workflows

Watched for 6 days · last checked today

Details →

A self-hosted studio bundling several open-source TTS/voice engines and Whisper transcription as a local, offline alternative to ElevenLabs.

Works offlineOpen sourceSelf-hosted
What to know
How it works
A fully-offline local studio bundling multiple open-source TTS engines (VibeVoice, Kokoro, Chatterbox, OmniVoice, VoxCPM, Qwen3-TTS) plus Whisper voice-to-text.
What's different
Self-hosted, open-source alternative to ElevenLabs.

Watched for 8 days · last checked 2d ago

Details →

A CLI tool that generates backend API integration tests by first understanding routes, handlers, and models, for developers using AI coding agents instead of writing tests manually.

Open source
What to know
How it works
CLI-only, open-source, requires an LLM key to generate integration tests.
Best for
Developers using AI coding agents who need structural understanding before test generation.

Watched for 2 days · last checked 1d ago

Details →

Tracks and converts LLM API spend across OpenAI, Anthropic and Gemini locally, instead of trusting a cloud dashboard with your usage data.

FreeWorks offlineOpen source
What to know
Pricing
Free and open source.
Best for
Developers juggling multiple LLM provider SDKs and costs.

Watched for 2 days · last checked 1d ago

Details →

A visual drag-and-drop editor for Mermaid diagrams inside VS Code that keeps diagrams as plain Git-friendly Mermaid source, instead of hand-writing diagram syntax.

Open source
What to know
How it works
Open a .mmd file, build on an infinite canvas; source stays in sync with the visual edits.

Watched for 2 days · last checked 1d ago

Details →

An open-source CLI that checks SPF/DKIM/DMARC/MX records, verifies addresses via SMTP, and flags disposable/role-based emails, for developers validating deliverability before sending.

Open source
What to know
How it works
DNS health scoring, SMTP RCPT TO verification, domain typo correction, 29 RBL blacklist scans, ~74k disposable domain detection; includes REST API.
Pricing
Free demo available.

Watched for 2 days · last checked 1d ago

Details →

An open-source library of React Native UI components you can copy, customize, and build on, styled after shadcn.

Open source
What to know
How it works
Beautifully designed React Native components you copy and customize, powered by NativeWind and Uniwind.
Pricing
Open source, open code.

Watched for 7 days · last checked 1d ago

Details →

Shows your next three calendar events on Apple Watch, iPhone, iPad, and Mac, with no ads or tracking.

FreeOpen source
What to know
Pricing
Free, open source

Watched for 5 days · last checked today

Details →

Local SMTP test server for developers to safely test signup, password reset, and OTP emails without sending anything to real inboxes.

FreeOpen source
What to know
How it works
Runs locally, app points to it, each test run gets an isolated inbox so parallel tests don't collide.
What's different
Open-source and free, no external delivery.
Pricing
Free
Best for
Developers testing email flows with Playwright, Vitest, Jest, or Node.

Watched for 5 days · last checked today

Details →

An offline scanner that checks Python projects for known CVE vulnerabilities using local AST analysis, instead of a cloud-based dependency scanner.

Works offlineOpen source
What to know
How it works
Static AST analysis run entirely locally, with no internet connection or external dependencies required.
Pricing
Open source, published on PyPI.
Best for
Developers who want fast vulnerability scanning without sending code to a cloud service.

Watched for 7 days · last checked 1d ago

Details →

A TypeScript library that renders algorithm functions as animated visual diagrams so developers can watch data structures change step by step while debugging.

Open source
What to know
How it works
Write TypeScript algorithm functions, run them with structured inputs, and watch arrays, matrices, trees, and pointers animate as the function executes.
Best for
developers learning or debugging data structures and algorithms.

Watched for 12 days · last checked 6d ago

Details →

Lets developers build SQL-driven embedded analytics dashboards for their product instead of building custom reporting from scratch.

Open sourceSelf-hosted
What to know
How it works
Build dashboards entirely in SQL
Best for
Software developers, data teams, SaaS companies

Watched for 1 day · last checked 1d ago

Details →

Lets Mac photographers browse and cull RAW photos without imports or catalogs instead of using Adobe Bridge.

Open source
What to know
How it works
Points at folders directly; rate and reject photos; stays compatible with Lightroom and Adobe Bridge via XMP metadata.
Pricing
open source

Watched for 1 day · last checked today

Details →

Lets artists turn up to 10 artworks into a walkable, ownable 3D gallery instead of relying on a hosted gallery platform.

Open sourceCan export my data
What to know
How it works
AI curates rooms and layout; deterministic code builds the space; export a self-contained website you host anywhere.
Watch out
requires bringing your own IBM watsonx or OpenAI-compatible key

Watched for 1 day · last checked today

Details →

Lets Windows gamers speed up or slow down single-player games in real time instead of needing a kernel driver.

FreeOpen source
What to know
How it works
Customizable hotkeys, five gear presets, and a hold-to-speed mode.
Pricing
free and open source

Watched for 1 day · last checked today

Details →

Lets developers build animated code presentations offline instead of using codeslides.app.

FreeWorks offlineOpen source
What to know
Pricing
free and open source

Watched for 1 day · last checked today

Details →

Lets people turn a learning goal into a visual, level-based roadmap instead of a plain checklist.

FreeWorks offlineOpen source
What to know
How it works
Milestone levels with sub-task checklists that unlock in sequence; works offline or syncs via Supabase.
Pricing
free and open source (MIT)

Watched for 1 day · last checked today

Details →

Lets developers inspect and tweak any live webpage's design instead of opening DevTools.

FreeOpen sourceNo tracking
What to know
How it works
Adds a floating toolbar with 7 keyboard-driven tools (Inspect, Typography, Edit Text, Search, Rulers, Outlines, Zoom).
Pricing
free

Watched for 1 day · last checked today

Details →

Lets Spanish public-sector job seekers get alerted to new postings instead of checking 18 separate regional bulletins manually.

FreeOpen source
What to know
How it works
Unifies BOE and all 17 regional bulletins into one search with email and Telegram alerts.
Pricing
free, open-source

Watched for 1 day · last checked today

Details →

Open-source cold-outreach platform with AI automation, email warmup, and real-time team collaboration for sales prospecting.

Domain registered 13 months ago

Open source
What to know
How it works
An open-source platform for cold outreach with AI automations, real-time collaboration, agents, and email warmup.
Best for
Sales teams doing cold email prospecting who want an open-source alternative.

Watched for 11 days · last checked 5d ago

Details →

Bundles five small free-tier developer APIs (WHOIS, company lookup, email validation, geolocation, sanctions screening) as a cheaper alternative to separate paid subscriptions.

FreeOpen source
What to know
How it works
Bundles five production APIs: Domain WHOIS via RDAP, Company Info from Wikipedia/Wikidata, Email Validator with MX+SMTP, IP Geolocation with dual-source fallback, and a Sanctions Screener with 20K+ OFAC/UN entities.
Pricing
Free tier: 100 requests/month, no credit card.
Watch out
Built with Cursor AI; open source on GitHub.

Watched for 8 days · last checked 2d ago

Details →

A free, open-source local app that lets multiple AI coding agents (Claude Code, Cursor, Codex, etc.) collaborate on one codebase over MCP while the user watches and approves each step.

FreeWorks offlineOpen source
What to know
How it works
Runs locally with no API keys or cloud account required; coordinates coding agents over MCP with step-by-step user approval.
Pricing
Free and open source.
Best for
Developers using multiple AI coding agents on the same codebase who want oversight of each step.

Watched for 7 days · last checked 1d ago

Details →

An open-source social network for finding coding partners by skill, interest or location using GitHub profiles — a matchmaking app for developers seeking collaborators.

Open source
What to know
How it works
An open-source social network where developers find coding partners by skill, interest, or location, chat in real time, share updates, host virtual meetups, and use AI-Connect to discover collaborators through natural conversation.
What's different
Uses GitHub-powered profiles for matchmaking rather than a generic profile form.
Best for
Developers looking to find coding partners or collaborators.

Watched for 12 days · last checked 6d ago

Details →

An open-source MCP server that lets AI agents compare model pricing and call multiple AI provider APIs (text, image, video, audio) directly.

Open source
What to know
How it works
Ships 31-77 tools covering text, image, video, audio, embeddings and translation APIs via MCP
Pricing
Open source
Best for
Developers building MCP agents that need to call multiple AI model APIs

Watched for 4 days · last checked 3d ago

Details →

Offline desktop API testing client (REST, GraphQL, gRPC) that keeps all your requests and tokens on your machine instead of a vendor cloud.

FreeWorks offlineData stays with youOpen source
What to know
How it works
runs 100% offline, stores collections in local SQLite and tokens in the OS keychain
Pricing
free, open source (MIT)
Best for
developers who don't want API collections synced to a third-party cloud

Watched for 6 days · last checked today

Details →

An open-source Python library that logs AI model inputs/outputs locally for audit trails without touching model weights.

Domain registered 3 months ago

Works offlineOpen source
What to know
How it works
Instruments scikit-learn/XGBoost/LightGBM inference, storing only inputs/outputs in a local SQLite queue
Pricing
Open source, pip install
Best for
Regulated finance teams needing audit trails without sharing model weights

Watched for 6 days · last checked today

Details →

DUI

Live

An open-source library of React UI components and blocks for developers building AI product interfaces.

Open source
What to know
How it works
Prebuilt React/Tailwind/shadcn components for landing pages, dashboards, and AI app UIs
Pricing
Open source

Watched for 6 days · last checked today

Details →

Gives voice-AI developers one account to meter spend across their whole vendor stack (LLM, speech-to-text, text-to-speech, telephony) with spend caps and kill-switches.

Open source
What to know
How it works
Server-side spend caps and per-agent kill-switches across multiple vendor APIs under one key
What's different
Open-source floe-guard component
Best for
Developers building voice AI products across several paid vendor APIs

Watched for 6 days · last checked today

Details →

Generates a 3D model from a single image entirely on-device using WebGPU, with no server uploads or accounts needed — an open-source tool for developers experimenting with local image-to-3D generation.

Works offlineData stays with youOpen source
What to know
How it works
Generates a 3D model from a single image entirely on-device using WebGPU compute in the browser, with no server uploads or accounts.
What's different
Open source and runs locally via WebGPU rather than requiring cloud GPU processing, also deployable on Vercel for instant testing.
Best for
Developers experimenting with local, private image-to-3D generation.

Watched for 10 days · last checked 4d ago

Details →

An open-source, self-hostable platform for building AI agents and connecting tools via MCP, using your own LLM provider keys — for developers who want to avoid vendor lock-in.

Open sourceSelf-hosted
What to know
How it works
An MIT-licensed, self-hostable platform for building AI agents, connecting tools via Model Context Protocol (MCP), generating code, and working with your choice of LLM provider using your own API keys.
What's different
Self-hosted and open-source, avoiding the vendor lock-in of hosted AI platforms.
Best for
Developers and businesses who want to self-host and customize their own AI agent platform.

Watched for 10 days · last checked 4d ago

Details →

A Raycast-style launchbar that groups your tabs, apps, links and notes into project workspaces instead of one generic list, for people juggling several projects through their full lifecycle.

Domain registered 11 months ago

No sign-upOpen source
What to know
How it works
A launchbar for browser and desktop that organizes tabs, apps, links and notes into project workspaces, with AI Spotlight Search to jump to anything instantly.
What's different
Organizes around project lifecycle rather than being a generic launcher like Raycast, and pulls native desktop apps into the same workspaces via a companion app.
Best for
People juggling several projects who want their tabs, apps and notes grouped by project instead of scattered.

Watched for 13 days · last checked 7d ago

Details →

Self-hosted, open-source monitoring for cameras and IoT sensors — footage stays on your own hardware while a hosted portal just handles remote access — a free alternative to Frigate, Blue Iris and Shinobi.

Domain registered 3 years ago

FreeOpen sourceSelf-hosted
What to know
How it works
An open-source Java agent turns cameras, sensors and physical systems into one automated setup using ONVIF/RTSP, Modbus and MQTT, with detection via YOLO or Gemini AI; a hosted portal provides remote access over WebRTC.
What's different
Video and sensor data stay on your own hardware — the hosted portal only handles connection and billing, unlike cloud-based VMS platforms.
Pricing
Free Community plan.
Best for
People self-hosting camera and IoT sensor monitoring who want an alternative to Frigate, Blue Iris or Shinobi.

Watched for 10 days · last checked 4d ago

Details →

An open-source Node.js library that wraps your OpenAI and Anthropic calls to enforce spending limits and log usage locally, with no telemetry. For developers guarding against runaway agent costs.

Open source
What to know
How it works
An open-source Node.js library that wraps OpenAI and Anthropic SDK calls to enforce hard spending limits, block calls once a budget is reached, and keep a local audit log.
What's different
Sends no telemetry — the audit log stays local.
Pricing
Open-source.
Best for
Developers who want to guard AI agents against runaway API spend without adding a telemetry dependency.

Watched for 14 days · last checked today

Details →

Open-source deterministic runtime for building controllable AI agents, separating probabilistic reasoning from deterministic state-machine execution.

Domain registered 11 days ago

Open source
What to know
How it works
An open-source runtime for building AI agents that separates probabilistic reasoning from deterministic execution, giving the runtime control over state transitions, tools, approvals, retries, concurrency and limits.
What's different
The alpha includes FSM workflows, human-in-the-loop policies, parallel tools, checkpointing, StateGraph orchestration, actor-based concurrency, tracing and multi-model support.
Best for
Developers building AI agents who need deterministic, controllable execution rather than pure LLM-driven control flow.
Watch out
This is an alpha release.

Watched for 10 days · last checked 4d ago

Details →

An open-source observability platform that stores compact telemetry summaries instead of every raw event, for engineering teams who want p95/p99 and anomaly tracking without ballooning storage costs.

Open source
What to know
How it works
An open-source observability platform that uses sketch data structures to answer production questions — p95/p99 latency, unique users, top events, anomaly movement, SLO burn — from compact telemetry summaries instead of storing every raw event. Includes a hosted playground, dashboards, Postgres durability, SDKs, and Docker/Helm/Kubernetes support.
What's different
Keeps only compact statistical summaries rather than raw event storage, cutting storage costs.
Best for
Engineering teams who want latency and anomaly tracking without their storage bill ballooning.

Watched for 9 days · last checked 3d ago

Details →

PgDog

Live

An open source Postgres connection pooler, load balancer and sharding proxy built by database engineers, for scaling Postgres without app changes.

Domain registered 18 months ago

Open source
What to know
How it works
An open source connection pooler, load balancer and sharding proxy that sits in front of PostgreSQL to scale it without requiring changes to the application.
What's different
Postgres-compliant proxy built by database engineers, aimed specifically at sharding and pooling rather than being a general API gateway.
Pricing
Open source.
Best for
Teams scaling a Postgres deployment who want pooling and sharding without rewriting their application.

Watched for 13 days · last checked 2d ago

Details →

A free, native Rust desktop app for testing HTTP/GraphQL/WebSocket APIs, for developers wanting a fast, low-memory alternative to Postman/Insomnia.

Open source
What to know
How it works
An open-source API client built in Rust with a native Iced GUI, supporting HTTP, GraphQL, WebSockets and more for API testing.
What's different
Native Rust performance with lower memory use than Electron-based API clients.
Pricing
Open-source.
Best for
Developers wanting a fast, low-memory alternative to Postman or Insomnia.

Watched for 9 days · last checked 3d ago

Details →

A single API call returns live, cryptographically signed data across 87 sources so AI agents and software can verify what they're consuming — a developer-facing trust layer, not a consumer app.

No sign-upOpen source
What to know
How it works
A single keyless API call returns structured JSON for 87 live tools across 19 verticals; each datapoint carries its source, licence, timestamp and an Ed25519 signature, optionally Bitcoin-anchored.
What's different
Data is cryptographically verifiable rather than just scraped and cited, and it works without signup or an API key via an MCP endpoint or batch POST.
Best for
Developers building AI agents or software that need to independently verify the live data they consume.

Watched for 17 days · last checked today

Details →

A self-hosted, open-source work log that tracks both human and AI agent activity in one timeline and turns it into reports, for teams that want to run it on their own infrastructure.

Domain registered 1 month ago

Open sourceSelf-hosted
What to know
How it works
An open-source, self-hosted work log that records both human and AI agent activity in one unified timeline and turns it into reports, with low overhead.
What's different
MIT-licensed and self-hosted on Cloudflare, so teams control their own infrastructure rather than using a hosted SaaS log.
Best for
Teams that want to track combined human and AI work on their own infrastructure.

Watched for 12 days · last checked 6d ago

Details →

Open-source CLI for developers to find and safely delete dev caches and build junk eating up Mac disk space.

Open sourceNo tracking
What to know
How it works
An open-source macOS CLI that scans for developer caches, build artifacts, Electron junk, and orphaned app data, showing an itemized list before deleting anything.
What's different
Never deletes without showing the itemized list first; pure bash, zero telemetry.
Pricing
Open source, MIT licensed.
Best for
macOS developers whose disk is being eaten by accumulated dev caches and build junk.

Watched for 9 days · last checked 3d ago

Details →

A floating always-on-top Windows window that runs Claude Code with screen awareness, so developers can ask about what's on screen and have it edit files or run commands.

Open source
What to know
How it works
A frameless, always-on-top Windows chat window for Claude Code, summoned by hotkey, that captures and reads your monitors before answering, then can edit files and run commands using your own Claude Code subscription.
What's different
Runs the full Claude Code agent on your existing subscription rather than requiring a separate API key, and has screen awareness rather than just chat.
Pricing
Open source (MIT).
Best for
Developers on Windows who want a floating Claude Code assistant that can see their screen while they work.

Watched for 13 days · last checked 7d ago

Details →

A local-first, self-hostable, open-source notes app with semantic search, autonomous research agents, and voice notes, where data never leaves the user's machine unless they choose to share it.

Works offlineData stays with youOpen sourceSelf-hosted
What to know
How it works
Stores notes locally and adds semantic search, ReAct agents, cited deep research, voice notes, and financial analysis on top, all self-hosted and MIT licensed.
Best for
Technical users who want an AI-augmented notes app without sending their data to the cloud.
Watch out
Requires self-hosting, so it needs technical setup compared to a hosted notes app.

Watched for 7 days · last checked 6d ago

Details →

Pulse

Live

An open-source AI revenue-ops copilot for sales and RevOps teams that turns pasted meeting notes into HubSpot updates, drafts follow-up emails, syncs Google Calendar context, and posts summaries to Slack, without writing to CRM or sending anything without approval.

No sign-upOpen source
What to know
How it works
Maps meeting notes to your HubSpot schema (deal stage, amount, custom properties, next steps) and drafts Gmail follow-ups.
Pricing
Browser demo needs no signup; source is open and self-hostable.
Best for
Sales and RevOps teams on HubSpot who want notes turned into CRM updates automatically.
Watch out
Nothing writes to CRM or sends without your approval, per the product's own description.

Watched for 7 days · last checked 5d ago

Details →

A free, open-source tool where six AI agents role-play as an investor, customer, competitor, regulator, employee, and analyst to attack a startup idea and produce a survival score, citing real startup failures.

FreeOpen source
What to know
How it works
six AI agents attack the idea simultaneously and reference failures like Webvan and Theranos; includes a public 'startup graveyard'.

Watched for 7 days · last checked 6d ago

Details →

Self-hosted, open-source email infrastructure for sending transactional email and campaigns from your own server with a developer API, instead of relying on a third-party email service.

Open sourceSelf-hosted
What to know
How it works
Sends transactional email, campaigns, and inbound mail from a self-hosted control plane, storing data in a single SQLite file and supporting SES, SMTP, direct MX, or a local sandbox.
Best for
Developers who want to run and own their email infrastructure rather than outsourcing it.

Watched for 7 days · last checked 6d ago

Details →

Hasir

Live

A free, open-source, self-hosted Protobuf schema registry for engineers who want to manage and version their Protocol Buffers without vendor lock-in, as a lightweight alternative to Buf.

FreeOpen sourceSelf-hosted
What to know
How it works
A self-hosted registry for managing, versioning, and distributing Protocol Buffers.
What's different
Lightweight alternative to Buf without vendor lock-in.
Pricing
Free and open-source.
Best for
Engineers.

Watched for 7 days · last checked 6d ago

Details →

An open-source, template-based design tool for building App Store and Play Store screenshots, feature graphics, and preview videos entirely in your browser or desktop app, with no account or upload required.

Domain registered 13 days ago

FreeNo sign-upData stays with youOpen source
What to know
How it works
pick a template, drop in your app screens, and export every required store size, including MP4 previews
What's different
an optional AI agent can build the whole listing from raw screenshots
Best for
app developers and designers preparing store listings

Watched for 7 days · last checked 6d ago

Details →

An open-source local control plane and MCP server for Cursor that recalls past fixes and playbooks, runs coding loops until tests pass, and can be driven from Telegram or integrated with tools like Jira and PostHog.

Open source
What to know
How it works
Ingests chats from Cursor, Claude Code, and Kiro, runs hybrid recall over past fixes, and runs coding loops until tests pass, exposed as a single MCP server with optional integrations.

Watched for 7 days · last checked 5d ago

Details →

A native, open-source desktop GUI for managing NATS messaging — connecting, publishing and subscribing, and managing JetStream, Key-Value, and Object Store — for developers on Windows, macOS, or Linux.

Open source
What to know
How it works
Cross-platform native desktop app for connecting to NATS servers and managing JetStream, Key-Value, and Object Store.

Watched for 7 days · last checked 5d ago

Details →

A debugger for AI agent runs that shows exactly what context each model call saw, for developers troubleshooting agents built with Claude Code, Codex, or Cursor.

Works offlineOpen source
What to know
How it works
Captures every step of an agent run, compares two runs, and can fork from any step to test changes
What's different
Local-first and open source, so traces never leave your machine
Best for
Developers debugging or comparing AI agent runs

Watched for 4 days · last checked 4d ago

Details →

An open-source SDK that gives your AI agent a phone number in a few lines of Python or TypeScript, pitched as the self-hosted alternative to hosted voice-AI platforms like Vapi or Retell. Built for developers who want to own the stack.

Open source
What to know
How it works
An open-source SDK that gives an AI agent a phone number in a few lines of Python or TypeScript, using Twilio, Telnyx or Plivo as the underlying carrier.
What's different
Pitched as the self-hosted alternative to hosted voice-AI platforms like Vapi or Retell, for builders who want to own the stack.
Pricing
Open source, MIT licensed.
Best for
Developers building voice AI agents who want to self-host rather than rely on a hosted platform.

Watched for 13 days · last checked 7d ago

Details →

An open-source, self-deployed portfolio template for actors and artists, with a browser-based admin for credits, gallery, showreel, and contact info, that keeps content in your own Vercel project instead of a locked-in SaaS.

FreeOpen source
What to know
How it works
Deploys as your own project on Vercel with a browser-based Admin panel for managing credits, gallery, showreel, and contact details; ships with a fictional demo profile to start from.
Pricing
Free and open source.
Best for
Actors and artists who want a portfolio they own and control instead of a subscription SaaS.
Watch out
Requires deploying your own instance on Vercel rather than signing up for a hosted service.

Watched for 11 days · last checked 5d ago

Details →

Elmo

Live

Self-hosted, open-source tracker for how ChatGPT, Claude, Perplexity and Google AI Overviews mention your brand versus competitors — a free alternative to Profound, Peec or Otterly.

FreeOpen sourceCan export my dataSelf-hosted
What to know
How it works
Tracks how AI answer engines like ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews mention, cite, and describe a brand, so teams can benchmark against competitors.
What's different
Open-source and self-hosted, so you run it on your own infrastructure, own your data, and can audit exactly how every metric is calculated — positioned as a free alternative to Profound, Peec, and Otterly.
Pricing
Free.
Best for
Developers and marketers who want to track AI visibility (AEO/GEO/LLMO) without handing data to a hosted vendor.

Watched for 18 days · last checked 2d ago

Details →

An edge-native transactional email service for Next.js/Vercel/Cloudflare apps, with a self-hosted open-source option, for developers who don't want to run their own email infrastructure.

Domain registered 4 months ago

Open sourceSelf-hosted
What to know
How it works
An edge-native transactional email service for Next.js, Vercel and Cloudflare Workers, with an open-source self-host option.
What's different
Runs at the edge alongside the deploy rather than as a separate hosted email service, and can be self-hosted.
Best for
Developers on Next.js/Vercel/Cloudflare who want transactional email without running their own infrastructure.

Watched for 9 days · last checked 3d ago

Details →

Turns a topic into a two-host AI video podcast with lip-synced avatars and captions, driven from the CLI or a studio UI using your own AI API keys. Open source.

Open source
What to know
How it works
Turns a single topic into a two-host video podcast with mixed AI voices, lip-synced avatars, and word-timed captions, rendered to MP4, driven from the CLI or a live studio interface.
What's different
Open source and runs on your own API keys, so you pay the underlying provider's rates directly.
Best for
Developers or creators who want to generate AI video podcasts from the command line.

Watched for 18 days · last checked today

Details →

An open-source declarative language for generating documents from one definition, compiling to HTML, PDF and Excel. A developer infrastructure tool for structured documents, not a spreadsheet replacement.

Domain registered 16 days ago

Open source
What to know
How it works
An open-source declarative language and intermediate representation for documents that compiles one document definition into HTML, PDF and Excel output, keeping business logic separate from presentation.
What's different
Replaces embedding programming logic into templates with a compact semantic syntax that Python applications and AI agents can generate directly.
Best for
Developers building document-generation pipelines who need one definition to produce multiple output formats.

Watched for 14 days · last checked today

Details →

A free, open-source daily digest of the top 50 Product Hunt launches with short AI summaries, so you can skim the day in two minutes instead of opening 50 tabs.

Domain registered 11 days ago

FreeNo sign-upOpen source
What to know
How it works
Automatically compiles the 50 most-upvoted Product Hunt launches each day into a digest, with a short AI-written summary of what each does, who it's for, and what stands out; it updates once daily rankings settle and keeps the last 7 days.
What's different
Open source (MIT) — you can run your own copy with your own API keys — and needs no account.
Pricing
Free.
Best for
People who want to skim the day's top launches in two minutes instead of opening 50 Product Hunt tabs.

Watched for 10 days · last checked 4d ago

Details →

An open-source, browser-based video editor built so AI agents like Claude can edit a JSON timeline over MCP while you direct — a technical tool for developers building agent-driven video workflows.

Nothing to installOpen source
What to know
How it works
An open-source, browser-based, Premiere-style video editor where AI agents like Claude edit by patching a JSON timeline over MCP, with the UI live-reloading in about 150ms.
What's different
Runs in the browser with no install or build step, and is built specifically so an AI agent can drive edits while the human directs.
Best for
Developers building agent-driven video editing workflows.

Watched for 14 days · last checked 8d ago

Details →

Turns a Figma frame link into baseline Swift UIKit code for AI coding agents like Cursor, Claude or Codex to build from. An open-source developer tool for iOS engineers, not a mobile app itself.

Open source
What to know
How it works
Give an AI coding agent a Figma frame link and it builds a clean cached design package, then generates baseline Swift UIKit code for Cursor, Claude, or Codex, with support for custom color/font/icon maps, base classes, full-screen coverage gates, and buffering against Figma 429 rate limits.
What's different
Works from a Figma link instead of screenshots or a raw file dump; open source, so you own the wiring for production APIs.
Best for
iOS engineers using AI coding agents to turn Figma designs into UIKit code.

Watched for 13 days · last checked 7d ago

Details →

An open-source, de-Googled Chromium build with fingerprint controls and SDKs for browser automation.

Domain registered 1 month ago

Open source
What to know
How it works
Provides engine-level fingerprint controls, reproducible builds, and drop-in SDKs for Playwright and Puppeteer.
Best for
Developers doing browser automation who need fingerprint control.

Watched for 12 days · last checked 6d ago

Details →

Pseudo

Live

A Chrome extension for LeetCode practice that turns your described approach into code with your own LLM key, without the AI quietly fixing your mistakes. For developers training for interviews.

Open source
What to know
How it works
A Chrome extension for LeetCode practice: describe your algorithm approach in natural language and it generates code with your chosen LLM exactly as described, right or wrong, plus an experimental 'Resource Units' metric for AI usage.
What's different
Does not silently improve or fix your described approach the way other AI coding tools do — the generated code reflects your reasoning as-is, mistakes included.
Best for
Developers training for coding interviews who want to practice their own problem-solving rather than let AI solve it for them.
Watch out
Requires bringing your own LLM API key (BYOK); there is no backend.

Watched for 14 days · last checked 8d ago

Details →

Syncs a support mailbox into GitHub, GitLab or Linear so you can run a service desk from your existing issue tracker instead of paying for separate helpdesk software.

Open source
What to know
How it works
Syncs a support mailbox to your issue tracker over standard IMAP/SMTP, turning incoming emails into tracked issues so you can run a service desk from GitHub, GitLab, or Linear.
What's different
Open-source and works with the automation pipelines you've already built in your issue tracker, instead of adding a separate per-seat helpdesk tool.
Best for
Teams already living in GitHub, GitLab, or Linear who want to handle customer email without buying dedicated helpdesk software.

Watched for 15 days · last checked today

Details →

An open-core platform for testing, simulating and monitoring multi-step AI agents in production, including an open-source framework for running adversarial conversation simulations before launch.

Open source
What to know
How it works
An open-core platform to test, simulate and monitor AI agents end-to-end, including multi-turn, multi-step, multi-agent systems, with an open-source framework (Scenario) for simulating full multi-turn agent conversations — including adversarial and edge-case paths — before production.
What's different
Tests agent behavior across full interactions the way software teams test software, rather than just grading single LLM outputs like most competitors.
Best for
Teams building complex or multi-agent AI systems who need to catch broken behavior before users do.

Watched for 18 days · last checked 2d ago

Details →

Backs up your Supabase Postgres database and storage files to your own S3-compatible bucket, then proves the backups actually work with weekly automated restore drills. Built for developers running Supabase in production.

Domain registered 24 days ago

Open source
What to know
How it works
Backs up a Supabase project's Postgres database and Storage files to your own S3/R2/B2 bucket, then runs weekly automated restore drills in a throwaway sandbox, verifying tables, rows, and checksums.
What's different
Proves backups are actually restorable through scheduled restore drills, rather than just taking backups on faith.
Best for
Developers running Supabase in production who need verified, restorable backups.

Watched for 13 days · last checked 7d ago

Details →

Open-source CLI that lets coding agents inspect live web pages, reverse-engineer network requests, and generate reusable browser-automation scripts — a developer tool, not for non-technical users.

Open source
What to know
How it works
An open-source, token-efficient CLI that lets a coding agent inspect live web pages, reverse-engineer network requests, and generate deterministic browser-automation scripts.
What's different
Produces inspectable, runnable, debuggable scripts instead of having an agent improvise at runtime from a prompt.
Best for
Developers using coding agents who want reliable, reusable browser automations rather than one-off prompted actions.

Watched for 14 days · last checked 2d ago

Details →

Plasma

Live

A free, open-source browser tool for designing WebGL gradient backgrounds, exportable as a raw shader, CDN script or no-code iframe embed — built for developers adding visuals to sites.

FreeOpen sourceCan export my data
What to know
How it works
Lets you design WebGL gradient backgrounds in the browser, customizing colors, flow speed, noise and grain live, then export as a raw WebGL shader, a lightweight CDN script, or a zero-code iframe embed link.
Pricing
Free and open-source.
Best for
Developers who want to add a customizable animated gradient background to a site without writing shader code from scratch.

Watched for 10 days · last checked 4d ago

Details →

A free, open-source, MIT-licensed penetration-testing agent bundling 90+ recon tools (nmap, nuclei, sqlmap and more) into a three-agent pipeline — for security engineers running assessments from the command line.

Domain registered 10 months ago

FreeOpen source
What to know
How it works
A reconnaissance agent that runs from inside the environment being tested (desktop, mobile, terminal or headless), bundling 90+ pentest tools like nmap, nuclei, sqlmap and aircrack-ng, plus native port scanning, device enumeration, WiFi discovery and packet capture. A three-agent pipeline (red team, validator, report) turns recon into verified findings.
What's different
Single Rust/Dioxus codebase across desktop, mobile, terminal and headless environments, and is MIT licensed so it can be inspected and extended.
Pricing
Free and open-source, MIT licensed.
Best for
Security engineers running penetration tests who want a bundled, extensible recon and reporting agent.

Watched for 10 days · last checked 4d ago

Details →

An open-source terminal coding agent with full file, command and app access on your machine; you supply your own Claude, GPT or other API key to power it.

Open source
What to know
How it works
A terminal-native coding agent with full machine access — reads files, runs commands, edits code, opens apps, and searches the web — with granular permissions on each action, persistent memory, and voice control.
What's different
Runs natively in the terminal with no cloud IDE or web sandbox in between.
Pricing
Free to start with open models included (Deepseek, GLM, Minimax, Kimi); bring your own API key for Claude, GPT, or other providers.
Best for
Developers who want a terminal-based agent with direct, broad access to their own machine.
Watch out
Grants full machine access — file reads, command execution, and app control — governed by granular permissions rather than a sandbox.

Watched for 17 days · last checked 11d ago

Details →

Turns your Android phone into a self-hosted MCP server so AI assistants like Claude, Cursor or Perplexity can pull your personal memory without sending data to the cloud. Aimed at developers already using MCP-compatible tools.

Works offlineData stays with youOpen sourceNo subscription
What to know
How it works
Turns an Android phone into a self-hosted MCP (Model Context Protocol) server by installing a Python MCP server inside Termux, with a secure tunnel giving the phone a stable public HTTPS URL that AI clients like Claude, Cursor or Perplexity can connect to for persistent memory.
What's different
Data is stored locally on the user's own phone instead of a vendor's cloud, with no subscription or vendor lock-in.
Pricing
No subscription.
Best for
Developers already using MCP-compatible AI tools who want to own their memory data instead of storing it in the cloud.
Watch out
Relies on a relay tunnel (relay.memplato.com) and requires Termux running on the phone, with a watchdog to restart the server if the phone reboots or Termux closes.

Watched for 10 days · last checked 4d ago

Details →

A free, open-source CLI and web tool that turns an OpenAPI spec into a ready-to-use client SDK in TypeScript, Python, Go, Dart or Java — a developer tool, not an API service.

FreeNo sign-upOpen source
What to know
How it works
Turns an OpenAPI spec into a production-ready SDK in TypeScript, Python, Go, Dart or Java, with a code preview, ZIP download, a CLI (npx sdkcraft), API change detection, and an AI documentation generator.
What's different
Free, open source and requires no signup.
Pricing
Free and open source.
Best for
Developers who need a client SDK generated from an existing OpenAPI spec instead of writing one by hand.

Watched for 13 days · last checked 7d ago

Details →

An open-source TypeScript SDK for spinning up sandboxes across providers like Vercel, E2B, Daytona and Upstash with one syntax, for developers building agent tooling.

Domain registered 12 days ago

Open source
What to know
How it works
An open-source TypeScript SDK for spinning up sandboxes with one syntax across multiple providers — Vercel, E2B, Daytona, Upstash and others — with integrations for tools like AI SDK, Eve and Mastra, plus included agent skills.
What's different
One consistent syntax across different sandbox providers instead of learning each provider's own API.
Pricing
Open source, MIT licensed.
Best for
Developers building agent tooling who need sandbox environments across multiple providers.

Watched for 11 days · last checked 5d ago

Details →

Inbix

Live

Open-source, Cloudflare-hosted email infrastructure for developers: disposable inboxes, webhook automation and REST/SDK/MCP access, aimed at testing and CI/CD pipelines.

Open source
What to know
How it works
Open-source, Cloudflare-native email infrastructure with disposable inboxes, real-time email receiving, webhook automation, and REST APIs, SDKs and MCP integration.
What's different
Open-source and Cloudflare-native, avoiding reliance on proprietary email infrastructure.
Best for
Developers needing email infrastructure for testing, CI/CD, or AI agents.

Watched for 11 days · last checked 5d ago

Details →

A set of open-source tools that simplify microcontroller prototyping for interactive projects — for hobbyist makers and hardware tinkerers, free forever.

Domain registered 4 months ago

FreeOpen source
What to know
How it works
A set of tools that simplify getting started with microcontroller prototyping for interactive projects.
Pricing
Free forever, fully open-source.
Best for
Hobbyist makers and hardware tinkerers prototyping interactive electronics.

Watched for 11 days · last checked 5d ago

Details →

Coterm

Live

An open-source, self-hosted tool that lets two developers pair-program together on the same live Claude Code session, with the collaboration backend running in their own Cloudflare account.

Domain registered 18 days ago

Open sourceSelf-hosted
What to know
How it works
A fork of Mosaic/cmux adding self-hosted real-time pair programming; two developers share one live Claude Code session, with the backend deployed to their own Cloudflare account.
Best for
Development teams who want real-time pair programming with Claude Code without relying on a third-party hosted backend.

Watched for 11 days · last checked 8d ago

Details →

A self-hosted, open-source alternative to paid media monitoring tools like Talkwalker and Brandwatch, built on Claude AI. Needs technical setup — for developers, not a plug-and-play product.

FreeOpen sourceSelf-hosted
What to know
How it works
A self-hosted media intelligence and social listening platform built on free data sources and Claude AI, positioned as an alternative to Talkwalker or Brandwatch.
What's different
Self-hostable and built on free data sources instead of a paid, hosted monitoring subscription.
Best for
Developers comfortable running and maintaining their own self-hosted setup.

Watched for 16 days · last checked 10d ago

Details →

Yerd

Live

An open-source, Docker-free local PHP environment for macOS and Linux — automatic HTTPS, per-site PHP versions, zero-config sites. A direct alternative to Laravel Herd for developers.

Open sourceNo subscription
What to know
How it works
A local PHP development environment: park a folder and every project inside becomes instantly live at .test; issues per-site HTTPS certificates automatically; installs multiple PHP versions side by side, pinned per site; runs MySQL, MariaDB, PostgreSQL, Redis and an SMTP catcher as native processes supervised by one daemon; streams Laravel dump()/dd(), queries, jobs and requests to a dedicated window.
What's different
Open-source, rootless and Docker-free — a direct alternative to Laravel Herd, MIT licensed with every feature included.
Pricing
Open-source, no subscription.
Best for
macOS and Linux developers running local PHP/Laravel projects who want to avoid Docker.

Watched for 18 days · last checked 2d ago

Details →

Shows a live badge on your Discord profile of which AI coding tool you're using right now, by watching for session file changes — it never reads your code. Free, open source, opt-in leaderboard.

Domain registered 16 days ago

FreeOpen source
What to know
How it works
Watches for changes in your local AI coding tool's session files (Claude Code, Codex, Cursor, Gemini CLI, etc.) and shows a live badge on your Discord profile indicating which tool you're using right now.
What's different
Never reads your code, only detects when session files change; open source with an opt-in leaderboard.
Pricing
Free.
Best for
Developers who want to show off or track which AI coding tool they're using on Discord.

Watched for 11 days · last checked 5d ago

Details →

A starter kit of open-source templates for building AI-native apps with shared state.

Open source
What to know
How it works
A starter kit of open-source templates for building AI-native apps with shared state.
Best for
Developers building AI-native applications who want a shared-state starting point rather than building from scratch.

Watched for 18 days · last checked today

Details →

RAI

Live

A self-hostable AI chat platform that routes queries to the cheapest LLM and adds live market data, positioned as an alternative to ChatGPT or Claude you run yourself. For developers and cost-conscious teams.

FreeOpen sourceSelf-hosted
What to know
How it works
A self-hostable, open-source AI chat platform that runs on your own infrastructure, integrates live financial market data into chat, and routes each query to the best/cheapest LLM automatically across OpenAI, Anthropic, SiliconFlow and others.
What's different
Self-hosted with full data ownership and no vendor lock-in, plus intelligent model routing claimed to cut API costs by up to 60% versus using a single provider.
Pricing
Free forever to self-host, with Free / Pro / MAX tiers and per-model quotas.
Best for
Developers and cost-conscious teams who want a ChatGPT/Claude alternative running on their own infrastructure.

Watched for 14 days · last checked 8d ago

Details →

An open-source governance layer that intercepts and enforces policies on every LLM call in production, streaming an audit trail to the cloud without adding a proxy.

Domain registered 17 days ago

Open source
What to know
How it works
Intercepts LLM calls, enforces policies locally in sub-millisecond time, and streams proof of compliance to a cloud audit trail.
Pricing
Free to start ($0).
Best for
Developers running production AI who need real-time policy enforcement and an audit trail.

Watched for 11 days · last checked 8d ago

Details →

An open-source Python agent runtime, installed with one pip command, with a local cache that skips repeat LLM calls — pitched as a lighter alternative to LangGraph for developers.

Open source
What to know
How it works
An open-source agent graph runtime with a BSP scheduler and a local semantic cache that skips redundant LLM calls when a similar routing request already happened, installed with a single pip command.
What's different
Positioned as a lighter, non-wrapper alternative to LangGraph, with a local cache to cut LLM call costs.
Pricing
Open source (Apache-2.0).
Best for
Developers building LLM agent pipelines who want to reduce redundant model calls.

Watched for 17 days · last checked 10d ago

Details →

An open-source Deno framework for routing prompts across multiple AI models with validation and quorum checks, plus safety gates before agents can mutate a repository — built for developers wiring up AI agent systems, not an end-user product.

Open source
What to know
How it works
An open-source Deno framework with two paths: Best Route fans a prompt out to independent model adapters, validates responses with Zod, requires quorum, and synthesizes the strongest answer; Agent Chat gives multiple models shared conversation context to challenge and converge across turns. Any repository mutation requires external SafeLoop authority, exact-digest approval, watched execution and verified artifacts.
What's different
Adds a fail-closed safety gate before agents can mutate a repository, rather than trusting agent output directly.
Best for
Developers building multi-model AI agent systems who need validation and safety checks before code changes land.

Watched for 15 days · last checked 9d ago

Details →

Converts YAML to JSON and back entirely in your browser, including multi-document Kubernetes manifests, with line-numbered parse errors, your config never leaves the browser.

Domain registered 21 days ago

FreeNo sign-upWorks offlineData stays with you
What to know
How it works
Converts YAML to JSON and back entirely in the browser, including multi-document files like Kubernetes manifests, with line-numbered parse errors.
What's different
Runs offline once loaded and your config never leaves the browser; the conversion core is open source.
Pricing
Free, no signup.
Best for
Developers who need to convert Kubernetes manifests or other YAML/JSON files without uploading them anywhere.

Watched for 14 days · last checked 8d ago

Details →

Impri

Live

An open-source approval inbox that pauses AI agent actions until a human approves, edits or rejects them via Slack, Discord, Telegram or the web - self-hostable for teams running agents.

Domain registered 17 days ago

Open sourceSelf-hosted
What to know
How it works
An approval inbox that pauses AI agent actions, such as sending an email, posting a comment, or running a command, until a human approves, edits or rejects them via Slack, Discord, Telegram, mobile or web.
What's different
The approval gate is a data dependency the agent can't skip, not just a prompt instruction.
Pricing
Open source (MIT), self-hostable.
Best for
Teams running AI agents who want a human-in-the-loop approval step before actions execute.

Watched for 14 days · last checked 8d ago

Details →

An open-source SDK that serves weather, ocean and elevation data as map tiles with values baked into the pixels, so you can restyle colormaps or switch to contours client-side without refetching. For developers.

FreeOpen source
What to know
How it works
Serves weather, ocean and elevation data as map tiles with the physical values baked directly into the pixels and decoded on the GPU, so you can change colormaps, switch to wind streamlines or contours, or re-scale client-side without refetching.
What's different
One open-source SDK works across MapLibre, Mapbox, Leaflet, OpenLayers, deck.gl and React, and the tile format is documented so you can decode it yourself without being locked to their renderer.
Pricing
Transparent pricing with a free tier.
Best for
Developers building map-based visualizations of weather, ocean or elevation data.

Watched for 15 days · last checked 1d ago

Details →

An open-source Python backtesting engine that traces trading signals through weights, orders, fills, and performance for reproducible research, for quant developers, instead of building a custom backtester from scratch.

Domain registered 19 months ago

Works offlineOpen source
What to know
How it works
Supports vectorized research or order-aware simulation with transaction costs, walk-forward testing, 80+ metrics, and 25+ charts; runs locally, with optional managed market data through an API.
Pricing
Open-source and runs locally; managed market data available through a paid API.

Watched for 13 days · last checked 9d ago

Details →

Aurict

Live

An open-source AI workspace bridging terminal, a local-first desktop app and mobile remote control using your own API keys for Anthropic, OpenAI or Gemini — built for developers wanting provider flexibility.

Domain registered 7 months ago

Works offlineOpen source
What to know
How it works
An open-source AI workspace where you bring your own API keys for Anthropic, OpenAI, or Gemini, bridging a terminal, a local-first desktop app, and mobile remote control with a command approval mechanism.
What's different
Open-source and provider-independent — no lock-in to a single AI model provider — with a secure command approval step for agent actions.
Best for
Developers who want to run AI agents across terminal, desktop, and mobile using their own API keys instead of a single vendor's app.

Watched for 13 days · last checked 10d ago

Details →

Open-source API that compresses prompts before OpenAI, Claude, Gemini or RAG calls, cutting token costs by about 65% while keeping the important content. For developers wiring it into their own LLM calls.

Open source
What to know
How it works
An open-source API that compresses prompts before they're sent to OpenAI, Claude, Gemini, RAG, chatbot, or agent calls, stripping tokens while preserving the evidence needed to answer correctly.
What's different
Claims to remove more than 65% of tokens on average while preserving over 98% of answer-critical content.
Best for
Developers wiring their own LLM calls who want to cut token costs without integrating a full new pipeline.

Watched for 17 days · last checked 11d ago

Details →

An open-source, self-hostable observability platform for developers to collect errors, events, sessions, and analytics via custom SDKs and view them in a multi-tenant dashboard.

Domain registered 26 days ago

Open sourceSelf-hosted
What to know
How it works
Custom SDKs send errors, events, sessions, and analytics data to a self-hosted, multi-tenant dashboard with organization/project management, API keys, and usage metering.
Best for
Developers who want self-hosted, open-source production observability instead of a third-party SaaS.

Watched for 11 days · last checked 5d ago

Details →

Open-source voice AI API for building production voice agents that receive and make phone calls, self-hostable or deployable to Vercel.

Open source
What to know
How it works
Built in Next.js on Vercel tooling: Vercel Workflows for post-call analysis, AI Gateway for realtime models, and Vercel Blob for call recordings, exposed as a REST API similar to Vapi or Retell.

Watched for 11 days · last checked 5d ago

Details →

Open-source TypeScript library for defining type-safe, reusable AI prompts with schema validation — a developer tool for building LLM features, not a cost-saving swap.

Open source
What to know
How it works
An open-source TypeScript toolkit for defining AI prompts with type-safe schemas, validating inputs before LLM calls, composing reusable prompt blocks, and compiling prompts for multiple AI providers.
Pricing
Open-source, MIT licensed.
Best for
Developers building production LLM features who want maintainable, schema-validated prompt code instead of ad-hoc prompt strings.

Watched for 11 days · last checked 5d ago

Details →

An open-source library of 116 customizable UI components across 33 categories, for developers and designers building interfaces.

Open source
What to know
How it works
A library of 116 handcrafted, customizable UI components spanning 33 categories that you can browse and drop into your own interfaces.
Pricing
Open source.
Best for
Developers and designers who want polished, ready-made UI components instead of building them from scratch.

Watched for 16 days · last checked 10d ago

Details →

A self-hosted agent that lets you talk to any REST API in plain English through its MCP layer, using your own LLM such as Ollama — built for developers.

Open sourceSelf-hosted
What to know
How it works
A self-hosted agent with an MCP layer that lets you talk to any REST API in natural language, using your own LLM (e.g. Ollama) instead of a hosted one.
What's different
Bring-your-own-LLM and fully self-hosted, so API credentials and data stay under your control.
Best for
Developers who want to interact with REST APIs conversationally while keeping their own LLM and data ownership.

Watched for 18 days · last checked 2d ago

Details →

Free, open-source starter templates for React, Vue and Svelte that replace CAPTCHAs with lightweight anti-bot mini-games, for developers who want protection without hurting UX.

FreeOpen source
What to know
How it works
Drop-in starter templates for React, Vue and Svelte that replace CAPTCHAs with interactive, zero-telemetry anti-bot mini-games.
What's different
Blocks bots without the usual CAPTCHA UX friction, and templates are free and open-source with no telemetry.
Pricing
Free and open-source.
Best for
Developers who want bot protection on a web project without hurting the user experience or paying for a CAPTCHA service.

Watched for 18 days · last checked today

Details →

Lets you e-sign a document by forwarding it via email, using your provider's DKIM signature as proof instead of a signing company; open source, self-hosted or hosted, pay-per-document.

No sign-upWorks offlineOpen sourceNo subscription
What to know
How it works
Forward a document to the service and type 'I sign this document' — your email provider's existing DKIM signature becomes the proof of signing, bundled into one self-contained file anyone can verify offline in a browser.
What's different
No third-party signing company is trusted with the signature — the proof relies entirely on infrastructure (DKIM) that already exists and would still verify even if this service disappeared.
Pricing
4 free signatures, then $0.25 per document, no subscription. Open source (Apache-2.0) — self-host or use the hosted version.
Best for
People who need a lightweight, verifiable e-signature for occasional documents without paying for a full e-signature platform subscription.
Watch out
The provider states it never holds a signing key and can't forge or alter documents — that's the product's own security claim, not independently audited.

Watched for 18 days · last checked 2d ago

Details →

Aiden

Live

A physical open-source USB device that watches your screen and can operate your phone or computer by voice, entirely offline with zero data collection. Built for makers and privacy-focused tinkerers.

Works offlineOpen sourceSelf-hosted
What to know
How it works
A physical USB device that plugs into any phone or computer, watches the screen over HDMI, and sends taps and keystrokes over USB HID to operate real apps the same way a person would — no app install, jailbreak, developer mode, or API required. It captures the screen, sends it to an AI model of your choice, decides the next action, and repeats until the task is done; voice mode runs on-device.
What's different
Works one layer below software integrations, so it can operate any app you can see and tap, including ones with no API or accessibility layer.
Best for
Makers and privacy-focused users who want to automate phone or computer tasks entirely offline without granting an app API access.

Watched for 18 days · last checked 2d ago

Details →

A shared memory and governance layer so multiple AI agents can recall what the others learned - backend infrastructure for developers building agent fleets, not an end-user app.

Domain registered 4 months ago

Open source
What to know
How it works
A shared memory layer for multi-agent AI fleets: agents write what they learn and recall what the fleet knows, with mandatory governance rules (Keystones) enforced at session start.
What's different
Detects contradictions between memories via RDF triples plus LLM analysis, and deduplicates near-duplicate memories into atomic facts with provenance via its Crystallizer.
Best for
Developers building multi-agent AI systems who need cross-agent recall without knowledge silos or leaks.

Watched for 13 days · last checked 2d ago

Details →

An open-source approval layer that intercepts AI agents before payments, refunds, emails or account changes so a human can approve, block or escalate the action first.

Open source
What to know
How it works
An open-source control layer that intercepts AI agent actions — payments, refunds, emails, account changes and other irreversible actions — and lets a human approve, block or escalate before execution.
What's different
Open-source and focused specifically on gating irreversible actions rather than general agent monitoring.
Best for
Developers building AI agents who need a human-in-the-loop checkpoint before high-stakes actions execute.

Watched for 13 days · last checked 2d ago

Details →

A free, open-source Mac app for developers that lists every open port and its process, lets you kill busy ports, and fix 'address already in use' errors.

FreeOpen source
What to know
How it works
A free, open-source Mac app that lists every open port and the process behind it, lets you kill processes on busy ports, and can block ports via the built-in macOS firewall.
Pricing
Free and open source.
Best for
Developers on macOS troubleshooting 'address already in use' errors or checking what's listening on their ports.

Watched for 13 days · last checked 7d ago

Details →

Branda

Live

Paste a company's URL and it auto-generates on-brand ad creatives for LinkedIn and X using that brand's logo, colors and copy style, no login or design skills needed. Open-source and self-hostable.

No sign-upOpen sourceSelf-hosted
What to know
How it works
You paste a website URL and it pulls the brand's logo, colors and campaign imagery via Context.dev's Brand API, reads the homepage to match the copy tone, then generates ready-to-ship ad creatives for LinkedIn and X.
What's different
No login or asset upload required, and it's open-source and self-hostable rather than a closed SaaS tool.
Best for
Marketers who need on-brand ad creatives quickly without design skills or manually assembling brand assets.

Watched for 13 days · last checked 7d ago

Details →

A free, open-source AI tool that edits JSON files from plain-English instructions instead of hand-written syntax, with diff review and version rollback.

FreeNo sign-upOpen source
What to know
How it works
An open-source AI workspace for editing JSON files: describe changes in plain English, review every edit as a diff, and roll back using full version history.
What's different
Diff review and full version rollback for every AI-made edit instead of blind overwrites.
Pricing
Free, no signup required.
Best for
Developers and teams who need to edit JSON without hand-writing syntax.

Watched for 14 days · last checked 2d ago

Details →

A free, open-source, browser-based ERD tool for visually designing database schemas and relationships before writing migrations. Built for developers, not graphic designers despite the tag.

Domain registered 4 months ago

FreeNo sign-upNothing to installOpen source
What to know
How it works
A browser-based tool for visually designing database schemas — drag out tables, define columns and relationships, and get an entity-relationship diagram.
Pricing
Free and open source.
Best for
Developers who want to plan a data model before writing migrations, not graphic designers.

Watched for 14 days · last checked 2d ago

Details →

A self-hosted, open-source intelligence dashboard layering live aircraft, satellite, weather and OSINT feeds onto one map — a general correlation tool, not built specifically for aviation.

Open sourceSelf-hosted
What to know
How it works
A self-hosted intelligence workspace that layers aircraft, satellites, earthquakes, weather, public radio, infrastructure, country intelligence, public cameras and open-source reconnaissance onto a single interactive map, letting you combine layers and inspect entities in place.
What's different
Open-source and self-hosted, built for active exploration and correlation across feeds rather than a passive dashboard.
Best for
Analysts or teams who want to correlate multiple live intelligence feeds on one map.

Watched for 14 days · last checked 2d ago

Details →

A self-hosted MRR and growth dashboard you deploy yourself for a one-time $49 instead of $108/month for Baremetrics. Built for indie hackers running their own infrastructure, not a plug-and-play SaaS.

Open sourcePay onceNo subscriptionSelf-hosted
What to know
How it works
Tracks MRR, churn rate, ARPU, Net New MRR, customer lifetime value, and 12-month revenue trends, with revenue data added manually or via API. Self-hosted on your own Railway + Supabase stack, works entirely offline with no third-party integrations required.
What's different
Sold as a one-time $49 purchase with full MIT-licensed source code instead of Baremetrics' $108/month subscription.
Pricing
One-time $49 purchase, no recurring fees.
Best for
Indie hackers at $0-$5k MRR who want a real growth dashboard before paying for Baremetrics.

Watched for 18 days · last checked today

Details →

A native macOS app for running AI agents fully offline with persistent memory and cryptographic identity — open-source infrastructure for developers building local agents, not a consumer chat app.

Works offlineOpen source
What to know
How it works
A native macOS harness for running AI agents fully offline, with persistent memory, autonomous execution and cryptographic identity, built in Swift.
What's different
Fully offline and open source, unlike cloud-based agent harnesses.
Pricing
Open source.
Best for
Developers building local AI agents on Mac who want offline execution and no cloud dependency.

Watched for 14 days · last checked 8d ago

Details →

Turns a CSV into a sellable data product, a directory, API, or feed, with Stripe checkout and SEO pages wired in, and lets coding agents run and fix it on a nightly loop before you approve changes. Self-hosted, MIT licensed, built for developers.

Open sourceSelf-hosted
What to know
How it works
Turns a CSV into a sellable data product — a directory, research database, API, or feed — with search, Stripe checkout, and SEO pages already wired in; a nightly agent loop checks traffic and revenue, drafts fixes, and stops for approval before anything goes live.
What's different
Agent-operable end to end via a --json CLI, MCP, and a SKILL.md that coding agents like Claude Code or Codex can read; self-hosted and MIT licensed.
Pricing
One payment; you keep your data and your own Stripe account.
Best for
Developers who want to turn a dataset into a paid product without building the commerce and SEO scaffolding themselves.

Watched for 13 days · last checked 7d ago

Details →

An open-source, self-hostable framework for running controlled experiments across your AI pipeline to statistically prove which changes actually improve output quality — for ML engineers, unrelated to restaurants.

Open sourceSelf-hosted
What to know
How it works
Treats every knob in an AI pipeline — retrieval, reranking, prompts, models, tools — as an experimental factor, runs factorial experiments, evaluates outputs with a configurable LLM or human reviewers, and applies mixed-effects models to measure which techniques help, by how much, and whether it's statistically significant.
What's different
Open source and self-hostable, replacing guesswork with statistically grounded experiment results.
Best for
ML engineers trying to prove which changes to an AI pipeline actually improve quality.

Watched for 13 days · last checked 7d ago

Details →

A self-hosted, open-source widget you embed in your app with one script tag, letting users request changes by text, voice or photo, which a Claude Code session then edits and commits. Built for developers who want an in-app AI coding agent they control.

Domain registered 1 month ago

Open sourceSelf-hosted
What to know
How it works
A single script tag embeds a prompt bar in your app; a user's typed, dictated, or photographed request triggers a Claude Code session on your own server that edits your codebase and commits the change.
What's different
Open source, self-hosted, and uses your own API keys.
Best for
Developers who want an in-app AI coding agent they fully control.

Watched for 13 days · last checked 7d ago

Details →

A free, open-source, git-tracked memory layer that carries context between AI coding tools like Claude Code and Cursor.

FreeOpen source
What to know
How it works
A git-tracked memory layer that carries context between AI coding tools like Claude Code, Cursor, and Antigravity, so context compounds across tools instead of resetting each time you switch.
What's different
Portable across multiple AI coding tools via git tracking rather than being locked into one tool's memory.
Pricing
Free and MIT open source.
Best for
Developers who switch between multiple AI coding tools and want shared context to carry over.

Watched for 14 days · last checked 8d ago

Details →

Ortu

Live

A cross-platform clipboard manager with full history, search and secret masking for anyone who copy-pastes constantly - handy for developers managing API keys, but useful for any heavy copy-paste workflow.

No sign-upWorks offlineOpen source
What to know
How it works
Remembers everything you copy - text, images, files - across macOS, Windows and Linux, with full-text search, a paste stack, secret masking with encryption, and smart auto-grouping.
What's different
Runs 100% locally with no account, and is open source.
Pricing
Not stated beyond being open source.
Best for
Developers and anyone who copy-pastes constantly, including people managing API keys via clipboard.

Watched for 16 days · last checked 10d ago

Details →

Two LLMs control stick-figure fighters with swords in a real physics simulator and you vote on who fought better — a playful but genuine benchmark for comparing model tactical reasoning.

FreeNo sign-upOpen source
What to know
How it works
Two LLMs control 2D stick-figure fighters in a real physics simulator, each receiving a JSON snapshot of the world every 3 seconds and choosing an action within 15 seconds; users pick the weapon and vote blind on who fought better, with per-weapon, per-zone Elo rankings.
What's different
Server-side randomization of which ragdoll is which color keeps voting unbiased, turning a joke concept into a tactical-reasoning benchmark.
Pricing
Free, no account required, open source.
Best for
People interested in comparing how different LLMs plan multi-turn tactics, in a more entertaining format than typical chatbot arenas.

Watched for 17 days · last checked 11d ago

Details →

An open-source C++/Python framework for running your own crypto funding-rate arbitrage and market-making bots on your own servers instead of a cloud platform — used at institutional trading desks.

Open sourceSelf-hosted
What to know
How it works
An open-source C++/Python framework for running crypto funding-rate arbitrage and low-latency market-making bots, with Python for strategy logic and C++ for execution; installable via pip.
What's different
Strategies, API keys and execution run entirely on your own infrastructure rather than a cloud bot platform, and it offers enterprise private deployment.
Best for
Institutional trading desks and developers wanting to self-host crypto trading strategies rather than use a hosted bot platform.

Watched for 13 days · last checked 7d ago

Details →

A local, open-source binary that meters and caps AI agent spend on your own machine for developers who want budget control without sending usage data to a dashboard.

Domain registered 18 days ago

Open source
What to know
How it works
A local binary sits in the request path, meters every token spent by AI agents, and enforces spend caps before they're exceeded; also compares your flat-rate plan against real metered rates.
What's different
Open source (MIT); sync and team budgets are planned but not yet available.
Best for
Developers running AI agents who want local spend control without a hosted dashboard.

Watched for 12 days · last checked 9d ago

Details →

An open-source, local-first CLI that records which lines of code were written by AI, by which model and tool, building a deterministic attribution ledger.

Domain registered 1 month ago

Works offlineOpen source
What to know
How it works
Records which lines of code were AI-written, which model and tool via which prompt, giving one ledger across Cursor, Claude Code, and other coding agents.
What's different
Deterministic and local-first; agents can query the CLI to surface context hidden behind existing code.

Watched for 12 days · last checked 9d ago

Details →

naden

Live

A free, open-source desktop SSH client for macOS with a built-in terminal, SFTP browser, jump host support, and an encrypted credential vault.

Domain registered 1 month ago

FreeOpen source
What to know
How it works
Provides SSH terminal access, SFTP file browsing, jump host chaining, and an encrypted vault for credentials.
Pricing
Free and open source.
Best for
Developers and IT professionals managing remote servers from a Mac.

Watched for 12 days · last checked 8d ago

Details →

Hooman

Live

An open-source AI agent runtime for the terminal, VS Code, and other ACP-compatible editors, letting you bring your own models or API keys instead of a hosted agent service.

Open source
What to know
How it works
Runs agent, plan, ask, and design modes with MCP integrations, reusable skills, subagents, and approval controls, using local (llama.cpp/MLX) models or your own API keys.
Best for
Developers who want to control their own agent stack instead of a closed hosted one.

Watched for 12 days · last checked 9d ago

Details →

A self-hosted WordPress plugin combining a visual workflow automation engine with an open-source AI agent that builds workflows and asks before acting, using your own LLM API keys.

Domain registered 2 months ago

FreeNo sign-upData stays with youOpen source
What to know
How it works
A low-code workflow builder plus an open-source AI agent and local executor run inside WordPress, with no SaaS component and data staying on your own server.
Pricing
Agent and executor are free; one license covers both paid plugins for the rest of the stack.
Best for
WordPress site owners who want automation without sending data to a third-party SaaS.

Watched for 12 days · last checked 9d ago

Details →

An open-source framework that turns your existing AI coding agent into a persistent virtual cofounder that remembers your venture across sessions, for solo technical founders.

Open source
What to know
How it works
An open-source install turns an existing AI coding agent — Claude Code, Cursor, Antigravity, Gemini CLI, GitHub Copilot — into a persistent virtual cofounder: one line installs it, `shotgun-init` injects it into a folder or codebase, and after a one-time onboarding it remembers your venture, builds your product, and keeps your data organized.
What's different
Open-source and works on top of whatever AI agent you already use, rather than being its own separate assistant.
Best for
Solo technical founders building without a human cofounder.

Watched for 17 days · last checked 11d ago

Details →

Showing the first 200 of 2,457 — ordered by how strong the evidence is, then by standing. Narrow it with a filter to see the rest.