56 curated projects. AI-scored for beginner friendliness, with live good-first-issue counts and hand-picked collections. Built for people who want to ship real open source, not browse awesome-lists.
Three paths to your first contribution. Pick the one that matches where you are today.
Answer 4 questions. Get a ranked list of projects that match your language, time, and interests.
151 production-ready AI agent skills. Works with Claude Code, Cursor, the API, or any agent framework.
Hand-picked groupings like 'Perfect first PR', 'Active this week', 'Build an MCP server'.
All tracked agentic AI projects with powerful filters: language, category, recency.
Production-grade AI agent skills across 14 disciplines. Each one is a self-contained persona you can drop into Claude Code, Cursor, the Anthropic API, or any framework that takes a system prompt.
Curated groupings to match what you're looking for.
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.
Most open good-first-issues, scored by AI for beginner fit.
A high-throughput and memory-efficient inference and serving engine for LLMs
LLM inference in C/C++
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Commits in the last 7 days — fastest reviewers.
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
High-impact projects with beginner-friendly practices and strong momentum.
LLM inference in C/C++
A high-throughput and memory-efficient inference and serving engine for LLMs
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
Data infrastructure for AI
Pick a project, read the contributing guide, claim an issue, and make your first PR to the agentic AI ecosystem.