Tools for developers — Runs on someone else's model

18 match your filters — 18 of them answered our check today.

Watching this group for 20 days · how we check

This week1 new arrival

Narrow it down

Free3Open source4No subscription1

Duply

Live

A library of ready-made interface style files you feed to AI coding tools like Claude and Cursor so they stop guessing your design — for developers building with AI.

What to know▼
How it works
A library of real interface styles packaged as DESIGN.md files that you feed to AI coding tools like Claude, Cursor, and OpenAI models, so they start with concrete typography, spacing, color, component, and layout direction instead of guessing.
Best for
Founders, developers, and 'vibe coders' building products with AI coding tools who want more consistent UI output.

Watched for 15 days · last checked 9d ago

Details →

i18n SaaS

Live

A free-beta localization platform for dev/product teams that uses Gemini and DeepL for context-aware UI translation with team collaboration, instead of manual string translation.

Domain registered 2 months ago

Free
What to know▼
How it works
Provides context-aware UI translation powered by Gemini and DeepL with team collaboration and organization management, integrated with Nuxt and Go.
Pricing
Currently in free beta with all features included.

Watched for 8 days · last checked 2d 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 →

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 →

FlyDocs

Live

Connects AI coding tools like Cursor, Claude Code and Codex to Linear and Jira so tickets auto-update — gives engineering leads visibility into AI-assisted work.

What to know▼
How it works
Connects AI coding tools (Cursor, Claude Code, Windsurf, Codex) to Linear and Jira, so tickets auto-update as agents work and every AI session follows your team's standards.
What's different
It isn't a coding agent or a PM tool itself — it's specifically the bridge that gives leads visibility into what AI agents are doing.
Best for
Engineering leads who want visibility into AI-assisted work without asking developers to manually update tickets.

Watched for 18 days · last checked 2d ago

Details →

Plugsky.com

Live

An OpenAI-compatible API layer that lets teams run multiple AI models across their own cloud, on-prem, or Plugsky's infrastructure without being locked to one provider.

What to know▼
How it works
An OpenAI-compatible API layer for running multiple AI models, agents, RAG, and tools, deployable on Plugsky Cloud, your own cloud, regional infrastructure, or on-prem.
What's different
Not locked to one provider, one usage limit, or one deployment style, and designed for easier migration from existing OpenAI-style apps.
Best for
Teams that want unlimited AI access with private or flexible deployment instead of being tied to a single AI provider.

Watched for 15 days · last checked 2d ago

Details →

DevShop

Live

A marketplace selling ready-to-deploy developer templates and bring-your-own-API-key AI tool kits for a one-time crypto payment with instant, lifetime-access delivery.

Pay onceNo subscription
What to know▼
How it works
Browse Next.js SaaS starters, AI tool templates, dashboards, and e-commerce templates; pay in USDT or 300+ other cryptocurrencies and get instant delivery.
Pricing
One-time crypto payment per product, lifetime access, no card or bank needed.
Best for
developers who want to skip boilerplate setup for a new SaaS or AI tool.

Watched for 12 days · last checked 6d ago

Details →

Ricochet coding

Live

An open-source AI coding agent that works in your editor, terminal, or via Discord and Telegram, with approvals and diff review before it touches code. For developers who want to supervise an agent, not just chat with one.

Open source
What to know▼
How it works
An open-source, local-first AI coding agent for VS Code-compatible editors, CLI/TUI, and messengers via Ether Live Mode (Discord, Telegram), keeping a reviewable task timeline with approvals, checkpoints and pending diffs, and routing across BYOK or Grik-hosted models.
What's different
Keeps a reviewable approval timeline instead of running as an editor-only assistant, with swarm workers for recurring checks and remote follow-ups.
Best for
Developers who want to supervise and approve an AI agent's changes rather than just chat with it.

Watched for 18 days · last checked 2d ago

Details →

API Hub

Live

A single OpenAI-compatible API endpoint that lets you swap between DeepSeek, Qwen and GLM models without rewriting your integration.

What to know▼
How it works
Change base URL and API key, keep your existing OpenAI-format SDK, switch models by name
Pricing
trial credits on signup, overseas billing via PayPal
Best for
Developers wanting multi-model access without rewriting their SDK integration

Watched for 5 days · last checked 3d ago

Details →

AgentKavach

Live

A Python SDK that enforces hard spending limits on AI agents calling OpenAI, Anthropic, Gemini or Mistral, with Slack/email/PagerDuty alerts when a budget is hit.

Domain registered 3 months ago

What to know▼
How it works
A Python SDK that tracks usage and cost per AI agent in real time across OpenAI, Anthropic, Gemini, and Mistral, and can alert or stop further API calls when a defined spending budget is hit. Sends alerts via Slack, email, or PagerDuty.
Best for
Developers running AI agents in production who need to cap runaway API spend.

Watched for 11 days · last checked 11d ago

Details →

Nexum Router

Live

An unlimited-usage LLM API gateway for a flat weekly subscription, routing OpenAI-compatible requests across models like Qwen and DeepSeek for developers.

What to know▼
How it works
Provides an OpenAI-compatible API that routes requests across multiple frontier models (Qwen, DeepSeek, MiniMax, MiMo, GLM) through a single interface, billed as unlimited usage for a flat weekly subscription.
Best for
Developers who want to integrate multiple LLMs through one API without per-token billing.

Watched for 11 days · last checked 11d ago

Details →

AgentX-Ray

Live

A continuously changing adversarial test suite for evaluating whether an AI model holds up under pressure, instead of static benchmarks models can memorize. For teams shipping models to production, not casual users.

What to know▼
How it works
Generates a dynamic adversarial test environment on every run — injecting unique variables and shifting context mid-task — instead of running a fixed, memorizable test suite, to evaluate how an AI model performs under pressure.
What's different
Static benchmarks can be memorized by labs optimizing for the leaderboard; AgentX-Ray's tests are different every run, so there's no fixed answer key.
Best for
Teams shipping AI models into production who need to know how the model behaves outside its training conditions, not casual users comparing leaderboard scores.

Watched for 11 days · last checked 11d ago

Details →

Consortium

Live

A drop-in proxy for LLM API calls that blends responses from multiple cheaper models to cut cost and improve reliability — developer infrastructure, not an end-user app.

What to know▼
How it works
Acts as a drop-in proxy for LLM API calls (a one-line URL change) that fuses responses from multiple cheaper models via ensemble topologies, and runs durable DAG execution with automatic retries and result parsing.
What's different
Claims comparable performance to a top model for 1-6% of the cost by fusing cheaper models, plus built-in benchmarking and prompt optimization.
Best for
Developers building LLM-powered apps who want lower cost and higher reliability without changing their app logic.

Watched for 13 days · last checked 10d ago

Details →

MDMA - GenUI for apps

Live

An open-source Markdown extension that lets LLMs output interactive UI — forms, tables, approval gates — instead of plain text, shipped with a CLI and MCP server for developers.

Domain registered 1 month ago

Open source
What to know▼
How it works
An open-source Markdown extension (fenced ```mdma``` blocks) that lets LLM output render as interactive UI — forms, tables, approval gates, charts, callouts, webhooks — instead of plain text. Ships component renderers for React and React Native, a validator, prompt packs for OpenAI/Anthropic/Google/xAI, a CLI, and an MCP server.
What's different
Deterministic parsing with a headless runtime that includes an audit log and PII redaction.
Pricing
Open source, MIT license.
Best for
Developers building chat interfaces who want LLMs to output structured, renderable UI components rather than plain text.

Watched for 14 days · last checked 2d ago

Details →

Gaio DataOS

Live

Lets developers build data pipelines, ETL flows and AI-powered dashboards in one low-code environment, with a chat layer over your data via OpenAI, Deepseek or Grok.

Domain registered 2 years ago

FreeSelf-hosted
What to know▼
How it works
A low-code platform for building data pipelines, ETL flows and integrations, with a 'Data Chat' feature for exploring data via LLMs (OpenAI, Deepseek, Grok) and AI-generated dashboards.
What's different
Centralizes data pipeline building, chat-based data exploration and dashboarding in one platform, and can process large volumes of data.
Pricing
Free, self-hosted Community Edition available via Docker.
Best for
Developers and data teams building pipelines and analytics who want a chat layer over their data.

Watched for 14 days · last checked 2d ago

Details →

New AI tools by IFTTT

Live

Prebuilt IFTTT recipes that plug Grok, Gemini and Perplexity into apps you already use — summarize meetings, transcribe audio, or route AI replies into Slack or Drive.

Domain registered 17 years ago

What to know▼
How it works
Prebuilt IFTTT recipes that plug AI tools like Grok, Gemini, and Perplexity into apps you already use — summarizing meetings when they end, transcribing audio, generating images on a schedule, and routing AI responses into apps like Google Drive, Notion, Slack, or SMS. Set up once and it runs whenever the trigger conditions are met.
Best for
Developers, content creators, or anyone wanting to automate AI-related tasks across their existing apps without building anything custom.

Watched for 12 days · last checked 6d ago

Details →

ContactBoxTools

Live

A unified API gateway offering discounted access to multiple LLM providers (Claude, GPT, Gemini) through one endpoint.

What to know▼
How it works
A unified LLM API gateway giving single-endpoint access to GPT, Claude, Gemini, and other top models via bulk credits.
Pricing
Starting from 90% off standard API costs.
Best for
Developers and AI builders wanting to cut API bills across multiple model providers.

Watched for 9 days · last checked 6d ago

Details →

AutoRouter

Live

A single API gateway giving OpenAI-SDK-compatible access to 200+ AI models with pay-as-you-go billing.

Domain registered 2 months ago

What to know▼
How it works
A single AI API gateway giving one-click access to 200+ large models, compatible with the OpenAI SDK, with pay-as-you-go billing, enterprise-level routing, and support for text, image, and video calls.
Pricing
Pay-as-you-go billing.
Best for
Indie developers, SaaS teams, and enterprise AI platforms.

Watched for 10 days · last checked 7d ago

Details →