Topic

Tools for working with AI coding agents · Free

match your filters

answered today

arrived this week

stopped answering

Watching this group for 24 days, checked once a day · how we check

Heard

LiveWatched 21d

Adds a voice/audio output to AI coding agents, instead of only reading their activity as text logs.

FreeOpen source

What to know▼

How it works: Gives coding agents spoken audio output.

Details →

HeimWall

LiveWatched 15d

Local macOS scanner that blocks secrets and PII from leaking into AI coding-tool prompts, for engineers who don't want to rely on cloud DLP.

FreeWorks offline

What to know▼

How it works: A macOS app that scans prompts in real time before they reach AI coding tools like Cursor, Claude Code, and Copilot, flagging leaked API keys, credentials, and PII using 47 local detection rules in under 50ms.
What's different: Detection happens on-device before data leaves the machine, and uses soft notifications instead of hard blocks so it doesn't interrupt the coding flow.
Pricing: Free 15MB macOS application for engineers; an early-access dashboard is offered separately for organizations.
Best for: Engineers using AI coding assistants who want to avoid pasting live secrets into prompts.

Details →

Remote OpenClaw

LiveWatched 11d

Free directory of 13,000+ MCP servers, agent skills, and plugins for AI coding agents like Claude Code and Codex.

FreeNo sign-up

What to know▼

How it works: Search, filter, and copy install commands for MCP servers and agent plugins in one place
Pricing: free, no login required
Best for: Developers building with AI coding agents who need existing tools/plugins

Details →

CodexUsageBar

LiveWatched 13d

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

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.

Details →

Design Skills

LiveWatched 15d

A searchable directory of installable design 'skills' with live before/after demos for AI coding agents like Cursor and Claude Code, instead of hand-writing UI polish prompts yourself.

Free

What to know▼

How it works: A searchable directory of installable 'design skills' for AI coding agents, each with a live before/after HTML demo you can preview, then install via a single `npx skills add …` command into tools like Cursor or Claude Code.
What's different: Shows live interactive before/after demos instead of just README descriptions, and installs with one command.
Pricing: Free.
Best for: Developers using AI coding agents who want polished UI without hand-writing design prompts.

Details →

CodexSkin Store

LiveWatched 16d

A free, open-source tool that applies custom visual skins to Codex Desktop without modifying the app's official bundle.

Watch out · macOS and Windows.

FreeOpen source

What to know▼

How it works: Applies immersive backgrounds and visual styling to Codex Desktop through a local CDP session, without modifying the official app bundle or code signature; restores stock appearance with one click.
Pricing: Free, open source.
Watch out: macOS and Windows.

Details →

FindDiskKiller

LiveWatched 6d

See which apps are hammering your Mac's disk

FreeOpen source

What to know▼

How it works: İşlem başına disk okuma/yazma, CPU/ağ etkinliğini ve SMART/NVMe sağlığını canlı izler.
Pricing: Tamamen ücretsiz ve açık kaynak.

Details →

Braidkeep

LiveWatched 7d

Lets teams running multiple AI coding agents in parallel catch merge conflicts before they happen instead of discovering them one at a time after merging.

Watch out · predicts mergeability, not correctness

Free

What to know▼

How it works: Predicts conflicts using Git's merge-tree read-only, enforces per-agent file ownership, computes a safe merge order.
Pricing: free, Apache-2.0
Watch out: predicts mergeability, not correctness

Details →

Capsomnia

LiveWatched 8d

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

Watch out · Requires Caps Lock not already assigned to something else.

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.

Details →

Motiscope

LiveWatched 6d

Screen record any animation, get the code

FreeWorks offlineOpen source

What to know▼

How it works: ffmpeg ile ekran kaydındaki beat/easing/transform değerlerini ölçer, GSAP/CSS/Framer Motion/Lottie hedefine spesifikasyon üretir.
Pricing: Ücretsiz, açık kaynak, yerelde çalışır.

Details →

OpenChatCut

LiveWatched 12d

Open-source, local-first AI video editor with a real multitrack timeline where Codex, Claude, and MCP agents edit alongside you.

FreeWorks offlineOpen source

What to know▼

How it works: AI agents work on a real multitrack timeline locally
What's different: local-first, editable exports, open alternative to ChatCut
Pricing: free (AGPL)

Details →

Kodr

LiveWatched 16d

A browser-based AI coding IDE with GitHub sync and live previews, for developers who want to build web apps without a local setup.

FreeNothing to install

What to know▼

How it works: A browser-based IDE with an AI coding agent that writes code, debugs, and generates components, with live previews and GitHub sync.
What's different: Requires no local setup, and its AI Quick Edit lets you select a code block, describe a change in plain English, and have the AI rewrite it instantly.
Best for: Developers who want to build and preview web apps without configuring a local environment.

Details →

Nura Dev

LiveWatched 12d

Lets developers control and monitor a Claude Code session by voice from their phone, for coding away from the keyboard.

Free

What to know▼

How it works: Hear replies read aloud and approve tool calls by voice remotely
Pricing: free to download, 7-day trial then $4.99/mo
Best for: developers who want to keep a Claude Code session moving away from their desk

Details →

Chimlo

LiveWatched 10d

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

Details →

TraceBug

LiveWatched 13d

A bug-capture tool that records a browser session, console errors, and network requests into one file that Claude Code, Cursor, or Windsurf can debug via a local MCP server.

FreeNo sign-up

What to know▼

How it works: Captures a session replay plus console/network evidence into an offline HTML file, then exposes it to AI coding agents through a local MCP server.
Pricing: Free, MIT license, no account required.

Details →

WaitJI AI

LiveWatched 9d

VS Code extension that shows sponsored ads during Claude Code's 'thinking' pauses and pays developers a share of ad revenue.

Watch out · India-focused (UPI payments).

Free

What to know▼

How it works: Shows a sponsored line in the Claude Code spinner during its 5-30 second thinking pauses, paying developers 50% of ad revenue directly to their UPI account.
Pricing: Free to install; withdraw from ₹100 to UPI.
Watch out: India-focused (UPI payments).

Details →

ADE

LiveWatched 8d

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.

Details →

Codex Quota Panel

LiveWatched 10d

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

Details →

Shibaita.ai

LiveWatched 7d

Lets Claude Code users compare usage on a public leaderboard instead of only seeing their own local stats.

Watch out · unofficial, not affiliated with Anthropic

Free

What to know▼

How it works: A CLI reads local logs and submits only aggregate token counts, never prompts or code.
Pricing: free
Watch out: unofficial, not affiliated with Anthropic

Details →

A runtime security gate that intercepts and holds risky AI agent actions like sending emails, moving money, or deleting files for human approval before they execute, for people running their own AI agents instead of trusting them unchecked.

Free

What to know▼

How it works: Sits outside the agent, scans skills before install, holds irreversible actions (money, sends, deletes) for approval, and can rewind or kill actions.
Pricing: free to try
Best for: individuals running their own AI agents, not enterprise teams

Details →

tterm

LiveWatched 12d

macOS cockpit for working with Claude Code: stacked rows of explorer, Claude, and file viewer with a built-in Chromium browser and diff review.

FreeNo sign-upNo tracking

What to know▼

How it works: each project is a row of explorer, Claude pane, and file viewer
What's different: real browser inside, no editor; you review diffs and commit
Pricing: free for hobbyists on Apple silicon

Details →

KlaatAI

LiveWatched 9d

Routes prompts to the cheapest capable model tier and offers a terminal coding agent claiming lower cost than Claude Code on a benchmark.

Free

What to know▼

How it works: Routes every prompt to the cheapest model tier that can handle it, escalating only when needed; its terminal agent Klaat Code claims to solve the same 33-task benchmark as Claude Code at 5.4x lower cost ($0.027 vs $0.146/task).
Pricing: Free beta: 75 requests/day, no card; tool calls are free, only messages count against quota.

Details →

Google Maps Agent Skills

LiveWatched 12d

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

Details →

nable

LiveWatched 6d

One usage meter for every AI provider you pay for

FreeNo sign-upWorks offline

What to know▼

How it works: Kullanım yerel oturum kayıtlarından okunur, hesap/anahtar gerekmez; sabit planlarda kullanım, ölçülü planlarda tahmini dolar gösterir.
Pricing: Açık kaynak ve sonsuza dek ücretsiz.

Details →

ego lite

LiveWatched 9d

A free Chromium-based browser that lets external AI agents work on logged-in web tasks in isolated spaces.

Free

What to know▼

How it works: A Chromium-based browser that lets external AI agents work on logged-in web tasks in isolated Spaces while you keep browsing normally.
Pricing: Free.
Best for: People wanting to run AI agents on web tasks without disrupting their own browsing.

Details →

Claude Code WordPress Plugin

LiveWatched 6d

WordPress/WooCommerce plugin that lets you manage your whole site in plain English through a chat terminal in the dashboard — orders, products, posts, plugins, themes, users, SEO and database, via 96 tools.

FreeOpen source

What to know▼

How it works: Type commands like 'show me today's orders' or 'create a product at $29.99' in a chat terminal inside WP admin; bring your own Anthropic API key.
What's different: Includes auto backups and activity logging.
Pricing: Free and open source.

Details →

100xprompt

LiveWatched 8d

An agentic coding CLI with persistent codebase memory and context compaction for long refactor sessions, instead of AI assistants that start cold each session.

Watch out · "Unlimited" GLM access described as a current promotion, not permanent.

Free

What to know▼

How it works: Persistent memory (Chitta), prompt-injection/PII shield (UltraGuard), three-tier context compaction.
Pricing: GLM 5.2 unlimited right now, free.
Watch out: "Unlimited" GLM access described as a current promotion, not permanent.

Details →

AI Dimag

LiveWatched 10d

Persistent, evidence-verified memory for AI coding agents that flags stale or unproven beliefs instead of silently misleading them.

Free

What to know▼

How it works: Gives MCP-compatible coding agents persistent memory where every memory carries falsifiable evidence (shell checks, tests, commit anchors) that gets re-verified against your current repo.
Pricing: Free for teams of 10 or fewer.

Details →

MRDown

LiveWatched 16d

A macOS Markdown editor that shows AI-made edits to your files as reviewable diffs instead of silent rewrites.

Watch out · macOS-native app.

Free

What to know▼

How it works: Shows exactly what an AI agent changed in your Markdown files as a diff instead of silently rewriting them, and gives a 3-way view when you edit the same lines the AI touched.
What's different: History tracks the AI's version as an external rewrite rather than the accepted truth; lets you compare any two files with a keyboard shortcut.
Pricing: Free, MIT-licensed.
Watch out: macOS-native app.

Details →

Replay QA

LiveWatched 13d

A QA tool that automatically explores your app from a GitHub repo or URL, records sessions, finds bugs, and hands your coding agent the root cause.

Free

What to know▼

How it works: Explores the app, records every session, and surfaces the root cause of found bugs for an AI coding agent to fix.
Pricing: Free to try.

Details →

NexusAI

LiveWatched 8d

All-in-one AI assistant for developers and freelancers with web search, code generation in 40+ languages, file analysis and image generation.

Free

What to know▼

Pricing: free to try

Details →

Bothread

LiveWatched 13d

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.

Details →

CMO Harness

LiveWatched 9d

A marketing operator tool for Claude Code that turns a product repo into growth plans, landing pages, ads, and content.

Free

What to know▼

How it works: Turns a product repo into a marketing workspace for Claude Code, giving it source-aware briefs, channel playbooks, policy references, quality gates, approval rules, and memory to create growth plans, landing pages, emails, ads, SEO/AEO work, audits, and content calendars.
Pricing: Free.

Details →

PandaCoder

LiveWatched 9d

Free local AI coding assistant positioned as an alternative to token-limited cloud coding tools.

Free

What to know▼

How it works: Runs locally as a coding assistant with no token limits.
Pricing: Free.
Best for: Developers wanting a private, local alternative to token-limited cloud coding tools.

Details →

MergeForge

LiveWatched 9d

Three-pane merge conflict resolver for VS Code/Cursor with optional AI explanation, free and open source.

FreeOpen source

What to know▼

How it works: A three-pane merge resolver (yours | editable result | theirs) for VS Code and Cursor, with scroll-synced word diffs, authorship chips, a history timeline, and one-click apply for non-conflicting changes; optional AI reads your repo to explain and resolve conflicts.
What's different: Nothing hits git until you apply.
Pricing: Free and open source.
Best for: Developers resolving merge conflicts in VS Code or Cursor.

Details →

Unified TUI for multi coding agents

LiveWatched 9d

Rust terminal hypervisor for orchestrating parallel AI coding agents in isolated git worktrees.

Free

What to know▼

How it works: A Rust terminal hypervisor that orchestrates parallel AI coding agent workers in isolated git worktrees, distributed as a single binary.
Pricing: Free Community tier.
Best for: Developers running multiple AI coding agents in parallel.

Details →

Pointer: Custom Cursor Changer

LiveWatched 9d

Custom and animated cursor replacement tool with 100+ free styles and click effects.

Free

What to know▼

How it works: Replaces your mouse pointer with 100+ animated cursor styles, click effects, and pixel companions, with per-site rules.
Pricing: 100+ styles free; Pro unlocks 250+ cursors, screen annotation, and smart physics.
Best for: People who want to customize their cursor.

Details →

HuskyBIM

LiveWatched 20d

Lets Claude directly edit and create data inside Revit, AutoCAD and other BIM software instead of just reading it, free — built for AEC/construction teams.

FreeCan export my data

What to know▼

How it works: Lets Claude query, edit, and create data directly inside Revit, AutoCAD, ArchiCAD, Navisworks, MS Project, Sigma, and Dalux via plain-English requests — fixing fire ratings, renumbering rooms, running clash tests, taking off quantities, and exporting schedules. Works with Claude Desktop, Cursor, VS Code, and Microsoft Copilot.
What's different: Most 'AI for BIM' tools only read your model; this one actually edits and creates data in it.
Pricing: Free across all 8 supported apps and versions.
Best for: AEC and construction teams working in Revit, AutoCAD, or other BIM software.

Details →

Vibelika

LiveWatched 13d

A free macOS desktop app that shows a small isometric virtual town where your AI coding agent's status appears, so you can respond to permission prompts from Claude Code, Codex, or OpenCode without going back to the terminal.

Free

What to know▼

How it works: Run a focus timer alongside other engineers in a shared virtual space; your agent's status (working, thinking, needs you) floats above your character, and permission requests surface as in-game cards.
Pricing: Completely free.
Best for: Developers who code alone with AI agents and want a sense of shared presence.

Details →

IAXT

LiveWatched 24d

A free macOS menu-bar app that logs everything your AI coding agent (Claude Code, Cursor, Aider, Codex) did in a session, entirely local with no account or cloud.

FreeNo sign-upWorks offline

What to know▼

How it works: A menu-bar app that passively records what AI coding agents like Claude Code, Cursor, Aider and Codex do on your Mac, every command, file touched, package installed, git operation, and launch agent, then presents it in an Action Log with confidence and severity tiers per agent, with any row copyable as context for another LLM.
Pricing: Free.
Best for: Developers using AI coding agents who want a record of exactly what those agents changed on their machine.

Details →

CodeDrobe

LiveWatched 10d

Open-source theme manager that lets you one-click apply visual themes to AI desktop apps like Codex without touching your data.

FreeOpen source

What to know▼

How it works: Applies community themes to change appearance only, install/data untouched
Pricing: free, open-source
Best for: Users of AI desktop apps like OpenAI Codex or WorkBuddy wanting a custom look

Details →

multAIplayer

LiveWatched 10d

A free, open-source macOS app and CLI letting teams share and steer a local Codex coding session together in real time.

Watch out · Requires an existing Codex account; encryption is unaudited

FreeOpen sourceSelf-hosted

What to know▼

How it works: Shared local Codex session with Monaco editor, terminals, web previews, Git/PR review, and encrypted relay
What's different: Encrypted with RFC 9420 MLS; free hosted relay or self-host option
Pricing: Free, open source
Best for: Small trusted dev teams pairing on AI-assisted coding sessions
Watch out: Requires an existing Codex account; encryption is unaudited

Details →

Inferra

LiveWatched 10d

A free command-line AI coding assistant with auto-updates and no usage quotas or rate limits.

Free

What to know▼

How it works: A command-line AI coding assistant with one-line install and auto-update.
Pricing: Free, with no quota or rate limits.

Details →

TaskCooker

LiveWatched 14d

A free, open-source tool for managing tasks across multiple AI coding agent terminals instead of juggling tabs.

FreeOpen source

What to know▼

How it works: Organizes tasks across multiple AI coding agent terminals so you focus on the task instead of juggling 20-40 terminal tabs across worktrees, working with any AI subscription you already have.
Pricing: Free and open source.

Details →

Kalendar

LiveWatched 17d

A free Calendly-style scheduling tool with built-in MCP support, so AI agents like Claude or Cursor can book, reschedule, or cancel meetings for you.

Free

What to know▼

How it works: A scheduling tool like Calendly with built-in MCP support, so an AI agent such as Claude or Cursor can book, reschedule, or cancel meetings for you in chat. Lets you set flexible availability with multiple time blocks per day and copy your schedule across days.
What's different: Free with unlimited users and no per-seat fees, unlike typical scheduling tools.
Pricing: Free, unlimited users, no per-seat fees.
Best for: Developers and teams who want their AI agent to handle meeting booking directly through chat.

Details →

PokeTokenBar

LiveWatched 11d

A menu-bar app that turns your Claude Code/Codex/Gemini CLI token usage into a Pokémon-collecting game while tracking usage limits.

FreeWorks offlineOpen source

What to know▼

How it works: Reads local usage logs and hatches/evolves a Pokémon as you spend tokens
What's different: Runs entirely on-device, nothing sent anywhere
Pricing: free
Best for: Developers who want a fun way to watch their AI token usage

Details →

RippleCheck

LiveWatched 11d

Scans your codebase to show exactly what an AI coding tool's change would break before you accept it, using local static analysis.

Watch out · Runs 100% locally with no telemetry

FreeOpen sourceNo tracking

What to know▼

How it works: Real local AST analysis (not LLM guessing) detects impact and generates fix prompts
Pricing: Free forever, MIT licensed
Watch out: Runs 100% locally with no telemetry

Details →

growths.dev

LiveWatched 15d

A guide site teaching setup of Claude Code, Codex, OpenRouter, and local LLMs like Ollama.

Free

What to know▼

How it works: Beginner-friendly guides covering how to install Ollama, run LLMs locally, and set up Claude Code, Codex, and OpenRouter.
Pricing: Free.

Details →

Flanner

LiveWatched 16d

An open-source CLI and MCP server that versions and protects the planning markdown files AI coding agents generate.

Watch out · Works with Claude Code and Codex.

FreeOpen source

What to know▼

How it works: A CLI and MCP server that versions and protects the planning markdown files AI agents generate.
Pricing: Free, open source.
Watch out: Works with Claude Code and Codex.

Details →

Zaira Labs Guide

LiveWatched 19d

A reference database of 900+ developer tools with tradeoffs and agent-readiness scores, built to feed accurate facts to AI coding agents over web, REST or MCP. Free, no signup.

FreeNo sign-up

What to know▼

How it works: A reference database covering 900+ developer tools with tradeoffs, alternatives, constraints and agent-readiness scores, accessible over the web, REST API or MCP.
What's different: Built specifically to feed accurate, structured facts to AI coding agents choosing databases, frameworks or libraries, instead of relying on stale training data.
Pricing: Free, no signup.
Best for: Developers and coding agents that need current, structured facts on tool tradeoffs before picking a dependency.

Details →

Freebird AI

LiveWatched 18d

A free, lighter AI coding assistant built for indie developers and small teams as an alternative to Cursor and Copilot, running fully private and local via Ollama.

Free

What to know▼

How it works: Multi-file agent mode, inline edits, semantic codebase search, and AI commit messages, running fully private and unlimited via Ollama.
Pricing: 20 real AI edits/day forever free; Pro $6/mo or Team $25/mo for more.
Best for: Indie developers and small teams who want an AI coding assistant without enterprise pricing or throttled quotas.

Details →

Doodler.co

LiveWatched 19d

A free, on-device tool that lets you draw and talk over your screen so your AI coding agent sees exactly what you mean — built for Claude Code, Cursor and Codex users.

FreeNo sign-upWorks offline

What to know▼

How it works: Draw directly on your screen and talk while your coding agent watches, then get back annotated screenshots, a voice transcript, and a timeline of what you pointed at, all combined together.
What's different: Runs 100% on-device and works with Claude Code, Codex, and Cursor.
Pricing: Free, no account required.
Best for: Developers who need to show an AI coding agent a visual bug or layout idea instead of describing it in words.

Details →

Speculos

LiveWatched 23d

Deploys a frontend or full-stack app to a live shareable link about 15 seconds after you type "deploy" inside Claude Code. Built for developers already coding with Claude Code, free for frontend apps with no sign-up.

FreeNo sign-up

What to know▼

How it works: Type "deploy" inside Claude Code and the app — frontend and backend — goes live at a shareable link about 15 seconds later; the agent can also trigger the deploy on its own.
What's different: Deploys from directly inside Claude Code without leaving the editor or setting up a separate hosting pipeline.
Pricing: Free for frontend apps, no sign-up required; teams get their own domain, link permissions, and company data connections.
Best for: Developers already coding with Claude Code who want a fast path to a live link.

Details →

Cerebrumma

LiveWatched 20d

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.

Details →

VisualEther

LiveWatched 19d

Turns Wireshark network captures into readable sequence diagrams, with an MCP server that lets Claude Code explain what broke -- a debugging tool for developers and network engineers.

Free

What to know▼

How it works: Converts Wireshark packet captures (PCAPs) into readable sequence diagrams; its MCP server lets Claude Code analyze a capture and explain failures in plain English, citing frame numbers as evidence.
Pricing: Free Community edition; a 45-day trial unlocks AI analysis, triage, and CI features.
Best for: Developers and network engineers debugging network issues from packet captures.

Details →

Check My Vibe

LiveWatched 19d

A free passive security scanner paired with a checklist for reviewing the security of websites built with AI and vibe-coding tools.

Free

What to know▼

How it works: Runs a passive security scan paired with a practical checklist for reviewing websites built with AI and vibe-coding tools.
Pricing: Free.
Best for: People who built a site with AI/vibe-coding tools and want a security check.

Details →

Love2Flow

LiveWatched 24d

Converts a React and Tailwind export from Lovable's AI-generated site into deterministic, paste-ready sections for the Webflow Designer, for people handing a vibe-coded site off to a real CMS.

FreeCan export my dataSelf-hosted

What to know▼

How it works: Takes a React and Tailwind CSS export from Lovable and converts it into deterministic, paste-ready sections for the Webflow Designer.
What's different: Bridges the handoff gap between AI vibe-coding tools and a proper CMS/hosting setup, which neither side solves on its own.
Best for: People who vibe-coded a first design in Lovable and now want to move it into Webflow's CMS and visual editor for long-term maintenance.

Details →

Suitest

LiveWatched 24d

A self-hosted QA tool that generates and runs end-to-end tests with video evidence for AI coding agents like Claude Code and Cursor, pitched as a free TestSprite alternative.

FreeSelf-hosted

What to know▼

How it works: A self-hosted QA platform that generates, runs and publishes end-to-end tests with video evidence from Claude Code or Cursor, and works with or without an LLM.
What's different: Free and self-hosted, positioned as an alternative to TestSprite.
Pricing: Free.
Best for: Developers using AI coding agents who want reviewable E2E test evidence.

Details →

Bromure Agentic Coding

LiveWatched 17d

A hardware-isolated VM for running Claude Code, Codex, or Grok Build so your API keys and AWS credentials stay protected from malware, exfiltration, and prompt injection.

FreeOpen source

What to know▼

How it works: Runs agentic coding tools in an isolated VM on Apple Silicon or via OpenAI/Anthropic, reachable by app, CLI, or SSH.
Pricing: Free and open source.
Best for: Developers running AI coding agents who want their credentials isolated from supply-chain and prompt-injection attacks.

Details →

QASkills.sh

LiveWatched 17d

A free, open-source directory of 394+ QA testing skills that developers install into Claude Code, Cursor, and 30+ other AI coding agents.

FreeOpen source

What to know▼

How it works: one command installs QA expertise (Playwright, pytest, API, and AI-eval testing) into a chosen AI coding agent

Details →

How it works: enforces YAGNI/stdlib-first code, answer-first prose, compact JSON/ESON handoffs between agents, and renders bulk reads as images to cut token cost
Pricing: free, MIT license
Best for: developers running AI coding agents (Claude Code, GPT, etc.) who want lower token usage

Details →

FreeOpen source

Details →

Watched the longest, still answering

The ones we have been checking the longest that still respond today. This is the whole point of the site: not what launched, what survived.

Bugboard.ai - Issue Tracking

LiveWatched 24d

A keyboard-first issue tracker built for dev teams working alongside AI coding agents, linking to GitHub/GitLab/Gitea and exposing 40+ MCP tools so agents can file and resolve issues.

Free

What to know▼

How it works: A keyboard-first issue tracker with board, list, calendar, and roadmap views that links directly to GitHub, GitLab, and Gitea, catches duplicate reports automatically, and exposes 40+ MCP tools so agents in Cursor or Claude Code can search, file, and resolve issues.
Pricing: Free forever for solo devs; simple seat pricing for teams.
Best for: Dev teams that work alongside AI coding agents and want issue tracking reachable from their agent tools.

Details →

Bleek.dev

LiveWatched 23d

A free web scanner that checks apps built with Lovable, Bolt or v0 for leaked API keys, open databases and missing security headers, no signup needed.

FreeNo sign-up

What to know▼

How it works: Scans apps built with tools like Lovable, Bolt or v0 for issues those builders tend to skip: leaked API keys, publicly readable databases, and missing security headers.
What's different: Targets the specific gaps left by AI app-building tools rather than doing generic security scanning.
Pricing: Free, no signup.
Best for: People who built an app with an AI app builder and want a quick check for exposed keys or open databases.

Details →

Skills UI

LiveWatched 20d

A marketplace of drop-in design style files for AI coding tools like Claude, Cursor and Lovable, so AI-built apps look designed instead of generic.

FreeNothing to install

What to know▼

How it works: A marketplace of downloadable design style files (Glassmorphism, Cyberpunk, Fintech, Art Deco, etc.) — drop two small files into Claude, Cursor, Lovable, or another AI dev tool so it builds with a defined visual direction.
What's different: Targets the specific gap of AI-generated apps defaulting to the same gray-card, blue-button look.
Best for: Vibe coders who can ship a working AI-built app but struggle to make it look distinct.

Details →

Free

8 of 22

See the group →

MCP Peek

LiveWatched 7d

FreeData stays with you

Details →

AgentBoard

LiveWatched 4d

FreeOpen source

Watched 6d

A desktop workspace for Claude Code. ✅

FreeOpen source

What to know▼

How it works: Community sürümü ücretsiz ve açık kaynak; Starter Kit rehberli kurulum, kişisel CLAUDE.md, başlangıç ajanları ve slash komutları ekler.

Details →