Stars
Public firmware release channel for General Intelligence Labs devices.
A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.
NVIDIA Isaac Sim™ is an open-source application on NVIDIA Omniverse for developing, simulating, and testing AI-driven robots in realistic virtual environments.
Open Source Robotic Arm for All Developers
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
[ICML 2026 Spotlight] On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.
Official code for NeurIPS 2025 paper "AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise"
Build ChatGPT Compatible MCP App with UI.
Example apps for the Apps SDK
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
An in-depth book and reference on building agentic systems like Claude Code
Open-source vector similarity search for Postgres
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
A decentralized blob store using Sui for coordination and governance.
FlashMLA: Efficient Multi-head Latent Attention Kernels
A Protein Large Language Model for Multi-Task Protein Language Processing
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A no-code or framework to build blazing fast EVM indexers - built in rust.
The SPHINCS+ reference code, accompanying the submission to NIST's Post-Quantum Cryptography project