Developer Tools.

Public agent-readiness scoreboard. Crawl a URL for llms.txt, agent cards, OpenAPI, MCP, and pricing. Rank is the score, not a bid.

Pydantic is the end-to-end AI engineering stack for Python: data validation, type-safe agents, LLM proxy, and observability. This A2A card represents the Pydantic Logfire MCP server, the primary agent

AI agent readiness scanner — scan any URL to check how visible and usable it is to AI agents. 58 automated checks across 5 levels (Discoverable, Usable, Optimized, Indexable, Agent-Native), all verifi

HTTP-native rendezvous, chat and notes for LLM agents. Every operation — including writes — is one plain GET returning text/plain: no auth, no client library, no SDK, no JavaScript, no POST verb requi

Your engineers have agents. Your organization doesn't. Cosmos is the platform that closes the gap.

The best way to reach humans instead of spam folders. Deliver transactional and marketing emails at scale.

Dub is the modern link attribution platform for short links, conversion tracking, and affiliate programs.

RankBull: free SEO tools to compare websites, check keyword rankings, generate schema, meta tags, SERP previews, and grow visibility on Google, ChatGPT, and Perplexity.

The WebGPU library, designed for agents.

Score how ready a website is for AI agents, then get evidence and recommendations to improve it.

Instructions for AI Agents

A collection of beautifully designed, accessible, and customizable email components for React Email, MJML React, and JSX Email. Works with shadcn/ui.

A collection of beautifully designed, accessible, and customizable PDF components. Built on Takumi and Forme. Works with shadcn/ui.

Trace LLM calls and AI agents with OpenTelemetry. Inspect token usage, cost, latency, and errors with TypeScript, Python, or an existing OTLP integration.

Read-only agent that answers natural-language questions about The Website Specification — a platform-agnostic checklist of what a good website does. Send a message and the agent searches every spec pa

Infrastructure to build, measure, and interact with agents across your SDLC — so you ship more and spend less.

PostHog automatically diagnoses problems, fixes bugs, and generates pull requests – all without you having to prompt it.

Open-source TypeScript SDK that sends transactional email through 26 provider API adapters plus SMTP (Resend, SMTP, Postmark, SendGrid, Mailgun, Cloudflare Email Sending, Unosend, AWS SES, and more) b

FAFA (rhymes with Rafa) — the Voice of FAF. A narrow-domain, citation-mandatory agent for the .faf family: it cites the spec or says "I don't know" — no bluffing. Reads 5 canonical FAF docs live from

Customizable TypeScript testing framework for web, mobile apps and more.

DemoBot produces a visual demo of code changes in pull request comments. Verify changes without ever having to checkout branches locally or click around preview deployments.

Your collaborative AI assistant to design, iterate, and scale full-stack applications for the web.

Your collaborative AI assistant to design, iterate, and scale full-stack applications for the web.

Sim is the open-source AI workspace where teams build, deploy, and manage AI agents.

Design AI agent systems, microservices, UML diagrams, and sprint boards on an infinite, offline-first canvas with instant AI Text-to-Board generation.

Built to make you extraordinarily productive, agents turn ideas into code. Accelerate development by handing off tasks to Cursor.

热核算力付费 GPT API：GO 默认按本站模型基础计费的 2%，PLUS 7%，PRO 10%；按量扣费，兑换券人民币 5 元起。模型与价格见分组指南。

Cherry Studio is an open-source, free, and powerful AI desktop client. It includes AI agents, AI chat, AI image generation, knowledge base, and more, supports all major LLMs, runs on Windows/macOS/Lin

--loader-bg: #1e1e1e;

Clean, validate, match, transform, protect, and analyze data through one API. Zapinner gives developers production-ready data utilities without rebuilding them.

Watch or control coding agents, builds, servers, and long-running terminal commands from any device. Sign in and every linked machine

twigl.app is an online editor for One tweet shader, with gif or webm generator and sound shader.

Learn why thousands of companies rely on W&B as their system of record for training AI models and developing AI applications with confidence.

View in LangSmith

Build and scale high-performing websites & apps using your words. Join millions and start building today.

Open-source email infrastructure for developers: transactional email API, SMTP relay, campaigns, webhooks, and agent inboxes. Reloop Cloud or self-hosted.

146 animated React components and 76 blocks and templates for Next.js, built with Tailwind CSS and motion. 49 free, MIT licensed. Install with the shadcn CLI.

Free, personalized developer news aggregator. Stay on top of software development news, AI coding tools, and web dev - curated daily from trusted sources.

Reason Agent by Reason Machines is the autonomous AI software engineer and cloud coding agent. Connect GitHub, assign issues, and ship evidence-backed pull requests on autopilot.

Go from a simple prompt to a live website or web app in minutes. Macaly is the all-in-one AI platform for founders and small businesses.

A list of official AI agent skills provided by Expo for building, deploying, and debugging Expo and React Native apps.

TraeCode integrates seamlessly into your workflow, collaborating with you to maximize performance and efficiency.

LLM-Judge: Production Multi-Model LLM Comparison and Pairwise Evaluation Platform

An interactive tool for token visualization & control, model inspection, data annotation, and more.

A long-horizon primary care environment: recurring patients, rare diseases unfolding over months, limited resources and delayed consequences. Can AI agents still catch the rare cases?

Unify observability, evals, prompt optimization, and your LLM gateway in one platform.

Git-backed docs for humans and agents, in one markdown repo where each reader sees exactly their folders.

Control coding-agent actions before they run.

The platform for voice, video, and physical AI agents.

Headless, type-safe, composable tools for building modern web applications that work naturally for developers and reliably for agents.

Measure what real people think about your product, brand, or any other topic. Let AI conduct 100s of feedback sessions so you can launch with confidence.

Everything bull-board does, faster. Free needs no login at all. Pro adds login, users & roles, alerts, folders, flows and an audit log. USD 39/month or 390/year per installation.

Documentation for Railway

Where agents choose and review software. After real tasks, coding agents like Claude Code, Codex, Cursor and Antigravity review the tools they used: a rating out of 5, what worked and what got in the

We make your website clear to AI agents so they understand your business and give accurate information to potential customers.

Qodo is an agentic code review and integrity platform for improving code quality at every stage.

> Lovable is an AI-powered platform for building web and mobile apps, websites, and internal tools from natural-language prompts.

Build and deploy software collaboratively with the power of AI without spending a second on setup.

The directory of AI agent skills, MCP servers, and rules for iOS, Swift, and SwiftUI developers.

Aceternity UI is a React component library with 200+ copy-paste components, blocks, and landing page templates built with Tailwind CSS and Motion.

Build a beautiful website or app from your idea, with themeable React components, reusable presets, and a skill that guides your coding agent.

Rollcage snapshots your projects when Claude Code, Codex or Cursor starts, restores what agents delete, and keeps them out of your .env files.

Ship more software, faster, with code you trust. Independent AI code review, PR triage, change explanations, and continuous security monitoring.

High-performance, unified observability for the AI era. 140x lower storage cost.

Version-pinned code recipes for AI coding agents, re-tested on every library release, each with a last-passed receipt.

The agent that evolves with you.

Hacktron autonomously reviews your code, detects real vulnerabilities, and learns from your feedback — so your team fixes what actually matters before it ships.

lurq serves your agent before it ever installs a single package, so the versions agree and the stack runs when you deploy.

41 checks on how AI systems access, discover and understand your site. Score and findings free, no account needed.

Free tool that scores how well your ecommerce store works with AI agents and AI search, with a copy-paste prompt to fix each failing check.

Give your AI agent superpowers. Install a SKILL.md skill in 30 seconds. Works with Claude Code, Cursor, Codex CLI, GitHub Copilot, and 20+ agents.

Continuously improve AI agents with agent observability, evaluation, tracing, and experimentation.

Tabnine is the AI code assistant that accelerates and simplifies software development while keeping your code private, secure, and compliant.

One OpenAI-compatible AI gateway for production AI — adaptive routing, load balancing, guardrails, agent firewall, observability and governance across 200+ models.

Run npx -y viberaven before launch: check AI-built Vercel + Supabase apps for RLS, keys, env vars and Stripe webhooks. It runs locally. Advice, not a gate.

Open-source infrastructure for AI apps and agents to respond with interactive UI, not just text. Build with your own components, models and design system.

smlibpy is a Python library for 3D modeling on the SMLib NURBS kernel. It comes with an MCP server, so your agent can build parts too.

Specialized small models with exceptional precision at one-tenth the cost of large LLMs. Automate audit, accounting and billing, or build your own.

LaunchSafe builds AI agents that pentest web apps, iOS and Android apps, APIs, and LLM apps and agents.

Install the SDK, get an API key, and run your first call against Parse, Extract, Classify, Split, or Index — all from one platform.

Tiny, open, native coding agent. A minimal CLI written in Zig, optimized for research and embeddability as part of larger systems.

Databricks Documentation

Paste a Python tool. Vend verifies it in a locked CreateOS sandbox and sells it per call to any AI agent over HTTP 402 with Stripe. You keep 90%.

All gas, no breakages. Convex is the reactive backend platform that keeps up with you and your agents.

A public git host for AI agents. No account, no token, no key: push to a name and the repository exists.

Kenny Nguyen, indépendant IA à Bordeaux. Agents spécialisés, automatisation et accompagnement des équipes de développement.

Paste a URL. Get a complete DESIGN.md file in seconds. Extract design tokens, typography & component styles — ready for AI coding agents.

Give CodePress a feature, bug, production alert, or design change. It works inside your codebase through implementation, QA, review, and fixes.

Components, blocks, and charts built with MUI and Motion. Copy the code, install with a CLI, or connect via MCP.

Components, blocks, and charts built with MUI and Motion. Copy the code, install with a CLI, or connect via MCP.

White-label hackathon software for game jams, demo days and IT competitions: registration, teambuilding, judging, certificates and analytics.

The intelligent orchestration platform for DevSecOps, enabling teams and agents to ship trusted software at enterprise scale.

Send transactional and marketing emails and get them to the inbox on time, every time. Postmark is a fast and reliable email delivery service for developers.

See and control sensitive data across AI agents, MCP servers, endpoints, and SaaS — in real time. Legacy tools can't see this, let alone stop it.

Coordinate Claude Code, Codex and Pi as a persistent team. Give a lead agent your ideas and feedback while specialists work together on projects that span weeks or months.

Daily notes on .NET, C#, EF Core, MAUI, Blazor, and Flutter - for developers who ship.

Reusable React components built on shadcn and Base UI. Small prop APIs for dialogs, menus, forms and pickers, with consistent desktop and mobile behavior.

Build reliable background jobs, workflows, and AI agents without extra infrastructure. Automatic retries, flow control, and step-level observability.

Any model. Any harness. Any subscription. Cloudroom is a free & open-source platform to run agents in the Cloud, with the inference you already pay for.

Build and review software with teammates and agents in shared threads, with every conversation and code change kept in context.

Freebuff is the free coding agent: a free CLI coding agent and Freebuff Web, the free way to build full-stack apps. No subscription, no setup, no lock-in. The free alternative to Claude Code, Cursor,

Turn your MacBook notch into a Dynamic Island with 17 tools: calendar, Pomodoro, music, a file shelf and Claude Code usage. One-time price, no account.

Arc is live: a platform for global markets, real-time value movement, and agentic economic activity. Start building on Arc.

A persistent, programmable workspace for real CLI coding agents. Launch them, resume them, steer them, and let them coordinate inside a room that survives crashes, reboots, and reopenings.

Frigade Assistant is the AI digital adoption platform for in-app user onboarding, product adoption, and feature adoption. It learns your product by using it, then guides users through real workflows i

Ibrahim Ulukaya

The complete AI dev toolkit for Phoenix and Rails

Prompt2CAD is an AI CAD application for turning natural-language build briefs, reference images, and 2D drawings into real, editable parametric 3D CAD geometry. It supports conversational iteration an

Discover what people make with agents. Like the work, join the conversation, fork your own version, and publish what you make.

Robosoft designs, builds and maintains SaaS platforms, web applications and MVPs for startups and established businesses.

Taste Skill gives your AI agent good taste. Open-source skill files that stop AI from generating generic, boring frontends.

Agents fight over the evidence — running, verifying, and refuting claims — so you can decide with proof, not hype.

Turn a song, named character references, and a plot into a timed, rerollable, finished AI music video — by hand or with an agent.

Capability-style filesystem roots for Node.js apps that handle untrusted relative paths.

JavaScript and Node.js SDKs for Binance, Bybit, OKX, Gate, Bitget, KuCoin, Coinbase, Kraken, HTX, and Hyperliquid REST APIs and WebSockets.

A narrow always-on desktop companion that watches every harness, surfaces what each agent is doing, and asks you to tidy up the rulebook when chat contradicts it.

Bundle, install, and run JavaScript & TypeScript — all in Bun. Bun is a fast JavaScript runtime & toolkit with a bundler, test runner, and npm-compatible package manager built in.

The shift happened. The only question is how deep you go.

Next.js by Vercel is the full-stack React framework for the web.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Open reference of 32 interface design rules, from Fitts's Law to AI slop. Every rule has a visual study, examples and a Markdown twin agents can read.

Building the multiplexer for all work.

Stop switching branches. Manage Git worktrees, terminals, IDEs, workflows, and parallel AI coding agents in one desktop workspace for Windows, macOS, and Linux.

The animation engine for agents: blazingly fast math and 3D videos with Manim

- [Get started](https://factory.mastra.ai/index.md)

How far can a coding agent get with your product? AX Check grades the fundamentals and shows real agent sessions.

Track usage windows, credits, and resets across 69 AI coding providers from your macOS menu bar.

Build native applications, with the tools you already know.

Future-proof your website for the AI era. GetBotRank helps you optimize for Search Generative Experience (SGE), AI Overviews, and Large Language Model (LLM) agents. Score your site for AEO, GEO, and A

Create agentic, context engineered AI systems using Haystack’s modular and customizable building blocks, built for real-world, production-ready applications.

One click records the screen, the console, the network calls and the browser. The developer opens a single link and sees what happened.

The AI Engineer newsletter + Top technical AI podcast. How leading labs build Agents, Models, Infra, & AI for Science. See https://latent.space/about for highlights from Greg Brockman, Andrej Karpathy

A collection of powerful productivity tools all within an extendable launcher.

Avoid lock-in and ensure reliability with Grafana Cloud. The AI-powered platform built on open standards unifies metrics, logs, traces, profiles, and business data.

Ferndesk is a complete help center with an agent that checks every article against your product, catches what changed, and drafts the fixes for you.

Discover and install skills for AI agents.

Rowkery is a Mac app for Postgres and SQLite. Use it on your own, or let your AI agent read your database through it. Nothing changes until you press Commit.

A native HTTP repeater and intercepting proxy, with a local MCP server for AI agents.

An open source, MIT-licensed framework for building command-line tools that AI agents use to reach SaaS platforms: one grammar, self-describing commands, declared safety metadata, and a runtime that r

Connect any PostgreSQL database and get visibility into performance, queries, health, schema, and changes — with AI-powered explanations.

Part I of Context Over MCP. Two agents work on the same repository.

LinkSwap is a backlink exchange for coding agents. Sign in with Google to create your account, register sites you own, and swap relevant backlinks. You review and ship.

Astro builds fast content sites, powerful web applications, dynamic server APIs, and everything in-between.

Give humans and agents complete context to understand, oversee, and evolve the world

decomp.wtf is discontinued. The code stays on GitHub under the MIT license.

Tasks, chat, calendar, meetings, docs and approvals in one lean workspace for small teams. No AI forced into every screen. Open source, free during beta.

An open-source form builder. Make a form, share a link, read every answer.

A local-first desktop workbench for running and reviewing AI coding agents.

You vibe-coded the app. Now add payments that actually work. Skills, commands and a working Next.js starter for Polar or Stripe.

A local, open-source dashboard for Claude Code, Codex, Cursor, Gemini CLI and Antigravity chats: what needs you, what is working, your limits, and a reply box.

Your agents write the code. Tiden verifies it does what you actually asked for.

A native Mac app for running Claude Code, Codex, OpenCode and Gemini at once, each in its own worktree, with one dashboard that tells you which agent needs you.

AI agents map every journey in your app, test them on every pull request, and watch production. Know what broke, on which device, before you merge.

Design production-ready database schemas from plain English. Generate Postgres, MySQL, and SQL Server DDL with interactive ERD diagrams. Free tier + Pro from $5/mo.

A Claude skill that draws an idea as the real machine that does it: a live isometric figure you can turn, press and read.

Your coding agent builds the same app in SwiftUI, Jetpack Compose and TanStack Start from one spec, with no cross-platform runtime. Open source, by GeekyAnts.

Give AI agents a /feedback endpoint. Feedwire collects structured bug reports and missing features from agents using your API, for a human to review.

Your agent broke Supabase. You probably didn't notice. Sodabase detects broken Supabase tables, finds the cause, and fixes the issue automatically.

PDF to markdown with the frontier model you choose, every page at once.

Meet mux and muxcode: a desktop coding harness with plan-first orchestration, cloud sandboxes, and a shared code index for your team and agents.

Control your coding agents from any of your devices.

Vestara connects crashes, logs, replay context, RUM signals, runtime targets, and alerts into one clear failure trail for production debugging.

Pyronaut is a high-performance Python framework for building production services with rich data access, observability, cloud integrations, build-time validation, testing, and enterprise support.

Isolated worktrees, shared project memory, and a second agent reviewing the diff before you ship. Runs on your own agent accounts.

Muse gadgets are open source devices you build yourself. Program an off-the-shelf ESP32 board or set up a Raspberry Pi with our SDKs, then connect Muse to your displays, buttons, sensors, actuators, a

Wu is a fast, native code editor with the familiarity of VS Code. No AI features, no account, no telemetry.

A quiet status strip for macOS that tells you which Claude Code, Codex or Antigravity session needs you.

We obsess over getting your emails to the inbox (so you don't have to). Start sending in minutes. Only pay for what you use.

One image parser to pwn them all. Hacktron research into remote exploitation through production HEIF, HEIC, and AVIF image pipelines.

A Mac workspace for Claude Code and Codex. For everything between an idea and something you love.

Drop-in plugin that reduces Claude Code token spend while preserving quality.

Free Chrome extension: remaining usage for Claude Code, Codex, Cursor, Grok and Gemini in one side panel. Download the latest release.

Explore CT, MRI and X-ray images on your device. Review your scans with your agent using tools for Codex.

See what you changed, what an agent changed, and restore a form from any automatic checkpoint.

Build custom workflows across image, video, audio and 3D. Train on your art bible so every asset is unmistakably yours. One platform for creatives, one API for developers, one MCP for agents.

Hey there, this is my personal website and blog. I use this site to try out new things, share my knowledge, and document my journey. I hope you find something useful here!

Antithesis is an autonomous software testing platform that finds the bugs others miss.

ivue turns native TypeScript classes into fine-grained Vue 3 reactivity. No proxy per instance, no decorators, no component coupling, nothing paid until first access.

Transmutify is a headless API for AI-powered data transformation, turning messy spreadsheets and raw text into schema-shaped records with hosted human review.

Discover community-built plugins for Omarchy Quattro.

Build a product that fits in a subject line. A hackathon where the inbox is the product. Mux Robots × Resend.

Beautiful, Fun & Agentic Linux by DHH

Updates, ideas, and inspiration from GitHub to help developers build and design software.

JetBrains is a cutting-edge software vendor specializing in the creation of intelligent development tools, including IntelliJ IDEA – the leading Java IDE, and the Kotlin programming language.

LLM observability, monitoring, evaluation, and prompt management in one platform with one OpenAI-compatible API.

Carlos Alfredo Carpio Meza turns hidden patterns across AI, electronics, future energy, music, astrology, and numerology into working systems.

LangChain enables every company to own their intelligence. Control, govern, and compound intelligence with an open agent engineering platform. Trusted by 7k+ organizations.

Continue has been acquired by Cursor.