Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Production-ready platform for agentic workflow development.

IdeaVim – A Vim engine for JetBrains IDEs

The open source coding agent.

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

fast trainer for educational purposes

AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models

Go ahead and axolotl questions

A bunch of kernels that might make stuff slower 😉

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

AllenAI's post-training codebase

🙌 OpenHands: AI-Driven Development

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

verl: Volcano Engine Reinforcement Learning for LLMs

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

🎃 A fast, out-of-the-box terminal built for AI coding.

Production-grade engineering skills for AI coding agents.

Run agents that work for you based on what you do. AI finally knows what you are doing

Mobile client for Claude Code and Codex — control coding agents from your phone via WebSocket bridge

Democratizing Reinforcement Learning for LLMs

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

LM engine is a library for pretraining/finetuning LLMs

PyTorch building blocks for the OLMo ecosystem

Our library for RL environments + evals

The interactive graphing library for Python ✨

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Supercharge your command line with LLMs and get shell scripting assistance in Fish. 💪