Curated groupings that help you find the right project fast. Each collection has a specific angle and is updated automatically as project data changes.
Highest beginner scores and open good-first-issues
Projects scored 7+ out of 10 for beginner friendliness, with at least one open good-first-issue. Clear docs, responsive maintainers, and claimable work.
Shipping code right now
Projects pushed to within the last 7 days. Active repos mean faster PR reviews, responsive maintainers, and momentum worth joining.
Read the whole codebase in an afternoon
Smaller repositories where you can understand the full architecture in one sitting. Often the best place to make meaningful contributions without weeks of ramp-up.
The protocol shaping agentic AI
Model Context Protocol is the emerging standard for connecting AI assistants to tools and data. Every database, API, and service needs a server. Early contributors shape the ecosystem.
AI that writes and edits code
The fastest-moving category in agentic AI. Contributing here puts you at the frontier of developer tools, where weekly releases and new capabilities are the norm.
Vector DBs, memory layers, retrieval
The infrastructure that gives LLMs persistent memory and access to real data. Production-grade systems with active development and technical depth.
The largest side of the ecosystem
All tracked agentic AI projects written primarily in Python. LangChain, CrewAI, AutoGen, LlamaIndex, and dozens more.
Node-native agentic AI
Projects built on TypeScript or JavaScript. Good fit if you want frontend + AI work or ship with Node/Bun/Deno runtimes.
Systems-level agentic AI
Rust-based inference engines, vector databases, and MCP SDKs. Smaller ecosystem with less competition per issue and strong performance requirements.
The building blocks
Libraries for composing LLM-powered agents. The most mature category — large ecosystems, many integration opportunities, and clear contribution paths.