A skills set and methodology for coding agents: clarify the task, plan, write tests, then code. The agent works with more discipline.
The AI movement's repository database
The best AI repositories
224 living projects — from agent frameworks to prompt-injection defense. Each comes with our own note: why it matters, who it is for and how to start in three steps.
Stars, forks and activity refresh daily via the GitHub API · updated October 6, 2026
- repositories
- 224
- categories
- 11
- stars in total
- 11M
- new stars in 30 days
- +235K
Last 30 days
Growing fastest
The most new stars over the last 30 days.
A service that turns any website into clean Markdown or structured data for models. It can search, scrape, crawl a whole site and even click through a page.
A small Microsoft utility that converts PDF, Word, PowerPoint, Excel and other files into Markdown that is easy to hand to a language model.
An open coding agent for the terminal with a desktop app. It is not tied to one provider: plug in whichever models you have.
A toolkit for spec-driven development: principles and a spec first, then a plan and tasks, and only then code. Works with several coding agents.
OpenAI's lightweight coding agent that runs in the terminal and works on your project's code. Written in Rust.
Categories
Agent frameworksFrameworks and orchestration: what agents and multi-agent systems are built from.23 repositoriesCoding agents & CLIAgents that write code in the terminal and editor, and the methods for working with them.21 repositoriesMCPThe Model Context Protocol spec, official SDKs and the best servers.20 repositoriesOpen models & inferenceOpen weights, local runs, fast inference and fine-tuning.38 repositoriesRAG & vector DBsSearch over your own data: document parsing, crawlers, vector databases, knowledge graphs.19 repositoriesEvals & observabilityHow to measure a model or agent and see what happens inside it.17 repositoriesPrompting & contextPrompts, structured output, skills and context engineering.16 repositoriesVoice, video, multimodalSpeech recognition and synthesis, voice agents, images and video.19 repositoriesAutomationNo-code workflows, browser and computer-use agents.15 repositoriesAwesome lists & learningCourses, books and awesome lists worth starting with.21 repositoriesSecurityPrompt injection, guardrails, red teaming and agent scanners.15 repositoriesMissing your favorite?Suggest a repository — we will review it and add it if it earns a spot.Suggest a repo →
Catalog
16 repositories
Anthropic's official collection of Agent Skills: folders with instructions and scripts that Claude loads for a task. A good reference for writing your own.
Formerly Awesome ChatGPT Prompts: a huge community library of prompts plus an interactive book on prompting. You can deploy your own private copy.
A collection of system prompts and tool descriptions from popular AI products: Cursor, Devin, Windsurf, Lovable, Manus and others. Useful for studying how pros build them.
A detailed guide to prompt engineering: techniques from few-shot to chains of thought, papers, lectures and notebooks. Recently extended with context engineering and agents.
A collection of examples and guides for the OpenAI API: from basic requests to function calling and RAG. Most code is Python.
Recipes from Anthropic as notebooks: tools, RAG, multimodality, subagents and other techniques for working with Claude. The code is ready to copy into your projects.
Google's library for extracting structured data from text with LLMs: each field is tied to a spot in the source, and results can be viewed in an interactive visualization.
A framework where instead of hand-tuning prompts you describe a program from modules, and the system tunes prompts and examples against a quality metric.
Anthropic's interactive prompting course: 9 chapters with exercises where you can try things right away and see how Claude's answer changes.
Twelve principles for building LLM apps good enough to put in customers' hands: own your prompts, own your context, small agents, explicit control flow.
A language for controlling generation: you mix text and constraints right in Python, and the model must produce exactly the required format, including schema-bound JSON.
A structured-generation library: the model returns an answer strictly matching a type or Pydantic schema. Works with different providers and local models.
The most popular way to get validated Pydantic objects out of an LLM: define a data model and the library retries the request when validation fails.
A project template for context engineering with Claude Code: rules in CLAUDE.md, code examples and commands that turn a feature description into a detailed brief and then into a working implementation.
A dedicated language for describing LLM calls as typed functions: prompt, response schema and tests live together and compile into a client for your language.
Compresses long prompts and context up to 20x with little quality loss by dropping low-value tokens. Saves money and speeds up responses.
Did we miss something?
Suggest a repository
Send a GitHub link and a few words on why it belongs here. Every suggestion is reviewed by hand — not everything gets in.