Explore the directory

A self-learning skill layer for Claude Code that distills reusable skills from a developer's real sessions, merges near-duplicates, updates them in use, and prunes the ones that stop being used.

• Coding agents
• Agent skills

An open-source programming framework for building AI agents and coordinating multiple agents to solve tasks together, formerly known as AutoGen.

• Agent frameworks

An HTTP(S) mock server and proxy for testing that mocks APIs, inspects and modifies live traffic, and injects failures for chaos engineering.

• Testing

An open dataset and pipeline code for RedPajama-V2, a 30-trillion-token dataset built from CommonCrawl for training large language models.

• Models

An opinionated set of Oxlint rules that reject low-evidence and low-signal TypeScript and JavaScript patterns, meant to be vendored and adapted rather than installed as a fixed dependency.

• Code quality

A curated catalogue of real-world agentic AI patterns, repeatable tricks, workflows and mini-architectures that help autonomous or semi-autonomous agents get useful work done in production.

• Curated lists

Mistral's open-source command-line coding assistant, offering a conversational interface to a codebase powered by Mistral's own models.

• Coding agents

A TypeScript runtime and command-line tool for discovering and calling Model Context Protocol servers from a terminal, a script, or a generated standalone CLI.

• MCP servers

A lightweight, self-hosted workspace for browsing databases, editing data, running queries, and viewing schema relationships, with optional AI features connected to a provider of the user's choice.

• Databases

An MCP server that connects AI agents to Exa for web search, content fetching and multi-step research.

• MCP servers

PyTorch's open-source stack for running AI models locally on phones, wearables, laptops, browsers, embedded systems and microcontrollers.

• Inference

A toolkit for deploying and serving open-source text-embedding and sequence-classification models, supporting popular families such as FlagEmbedding, GTE and E5.

• RAG
• Inference

An open-source proxy for agentic AI that provides connectivity, security, observability and governance for agent-to-LLM, agent-to-tool and agent-to-agent communication, built on the MCP and A2A protocols.

• MCP servers
• LLM gateways

An archived, open-source, cloud-native machine learning and large-model AI platform covering the full MLOps pipeline, from notebook development to distributed training and inference serving.

• Models
• Data engineering

A hands-on beginner's guide that walks programmers with no AI background through training a convolutional neural network to classify dolphin and seahorse images using Caffe and DIGITS.

• Tutorials

A free desktop app and open-source Python library for building, evaluating and optimizing AI systems, covering evals, RAG, agents, fine-tuning and synthetic data in one workbench.

• Agent frameworks
• AI evals

A self-evolving 'librarian' agent that searches across multiple retrieval methods and opens source documents directly to answer questions grounded in a user's own files, superseding the original AutoRAG pipeline-optimization tool.

• RAG

A collaboration tool that lets AI engineers and domain experts build and label high-quality datasets for text classification, LLM and multimodal projects.

• Models
• Data engineering

A guide and curated collection of Agent Skill resources, tutorials, and practical examples, explaining the open Agent Skills specification and how to install and structure a skill.

• Agent skills
• Curated lists

A machine learning library that extracts, parses and restructures raw scholarly documents such as PDFs into structured XML/TEI-encoded data, focused on technical and scientific publications.

• RAG

A self-hosted MCP server that gives ChatGPT a secure, password-approved connection to a person's own machine so it can read, edit, search and run code in real local projects.

• MCP servers

The official Go software development kit for building Model Context Protocol clients and servers, maintained in collaboration with Google.

• MCP servers

An efficient, scalable, multi-modality reinforcement-learning training framework for language and vision-language models, forked from veRL to add vision-language support.

• Models

A self-hosted, enterprise-grade registry for publishing, versioning, and governing agent skill packages behind a firewall, with RBAC, audit logs, and search.

• Agent skills