Explore the directory

A production platform for building AI-powered chat bots that connect large language models to Discord, Slack, Telegram, WeChat, Lark, DingTalk and other messaging platforms from one codebase.

• Backend
• Workflow automation

A GPU-optimized library for training transformer language models at scale, providing both a ready-to-run reference training setup and composable building blocks for custom large-model training pipelines.

• Models

An open collection of Agent Skills that teach context engineering and harness engineering for production AI agent systems, covering how to curate a model's context window, design agent operating loops and evaluate agent behavior.

• Agent skills

A curated, continually updated list of papers, surveys, benchmarks and datasets on multimodal large language models, covering instruction tuning, in-context learning, chain-of-thought reasoning and evaluation.

• Curated lists
• Papers

An open source tool that automatically generates an interactive wiki for a GitHub, GitLab or BitBucket repository, analyzing the code and producing documentation, diagrams and a guided code map.

• Documentation tools

A harness that connects a language model directly to a real browser over an editable Chrome DevTools Protocol connection, letting the agent write and reuse its own helper functions for browser tasks as it works.

• Browser automation

A workspace manager that coordinates multiple AI coding agents, such as Claude Code and GitHub Copilot, working on different tasks at once, persisting their work state in git so context survives restarts.

• Coding agents

An open-source agent operating system, written in Rust, that runs autonomous agents on schedules around the clock rather than only responding to a typed prompt, compiling to a single binary.

• Agent frameworks

A one-stop tool for creating a personal AI chat persona from exported chat history, fine-tuning a language model on the logs to match an individual's writing style and connecting the result to a chatbot.

• Models

A private AI platform for building agents, assistants and enterprise search, with an agent builder, document analysis across many file formats, deep research tools and API connectivity to external tools.

• Agent frameworks
• RAG

An interaction control harness for building customer-facing AI agents whose conversations must stay consistent, on-brand and compliant, by narrowing the model's context in real time to what is relevant to the current turn.

• Agent frameworks

An example fullstack application that pairs a React frontend with a LangGraph-powered research agent, showing how to build a conversational AI that generates search queries, searches the web, and answers with citations.

• Tutorials

An AI-native cloud operating system built on Kubernetes that covers the whole application lifecycle, from cloud IDE development to managed databases and one-click app deployment, with per-workspace multi-tenancy.

• Containers
• Hosting

A JSON-based communication protocol and ORM library that lets a backend expose CRUD, search, and remote function calls without writing per-endpoint API code, while the client shapes the JSON it gets back.

• APIs
• Backend

A security scanner for AI agent skills used by Claude Code, Codex and other MCP-based tools, checking for prompt injection, data exfiltration, privilege escalation and other risks before a skill is installed.

• Security

An open-source evaluation framework for large language model applications, agents and RAG pipelines, similar to Pytest but specialized for scoring outputs with metrics such as answer relevancy, hallucination detection and task completion.

• AI evals

A developer-centric API and integration testing tool that records real API traffic, database queries and streaming events, then replays them as tests and mocks.

• Testing

A lightweight reinforcement learning framework for training AI agents using their existing, unmodified harnesses, by proxying model calls and turning the resulting interactions into training data.

• Agent frameworks
• Models

A generative AI framework for researchers and developers building automatic speech recognition, text-to-speech, speaker diarization and speech translation models, with tools to create, customize and deploy new models from existing code and pretrained checkpoints.

• Speech

An official guide and set of recipes for building with Meta's Llama model family, covering getting started with inference, fine-tuning and retrieval-augmented generation, plus end-to-end use cases across model providers.

• Tutorials

A lightweight web interface for Hermes Agent, a self-hosted autonomous agent that remembers what it learns across sessions, giving the same functionality as its command-line interface through a browser.

• Agent frameworks

A self-hosted app that runs Claude Code, Codex, Copilot, OpenCode and Pi coding agents on a user's own machine and controls them from desktop, mobile, web or the command line, with no telemetry or forced accounts.

• Coding agents

An embeddable, performant flexbox layout engine with bindings for multiple languages, targeting web layout standards.

• Libraries

Open Chinese LLaMA and instruction-tuned Alpaca language models that extend the original LLaMA vocabulary for Chinese, further pretrained and fine-tuned on Chinese text and instructions, for local CPU or GPU deployment.

• Models