🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Design principles for agent ergonomics. Higher accuracy with lower token cost than both MCP and regular CLI.

Port of pi-mono to Python; AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pod.

A powerful Python library for creating and managing isolated desktop environments using Docker containers.

Harness for running and evaluating AI agents against RL environments

NanoGPT (124M) in 90 seconds

[NeurIPS 2025] Encoder-Decoder Diffusion Language Models for Efficient Training and Inference

SoTA open-source TTS

A curated awesome list of lists of interview questions. Feel free to contribute! 🎓

AI agents can now use real Android and iOS apps, just like a human.

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)

Easily train a good VC model with voice data <= 10 mins!

Hierarchical Reasoning Model Official Release

[ICML 2025] The Diffusion Duality

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Onion addresses for anything.

Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Automation engine to build, test and ship any codebase. Runs locally, in CI, or directly in the cloud

Codemod is a tool/library to assist you with large-scale codebase refactors that can be partially automated but still require human oversight and occasional intervention. Codemod was developed at F…

LLaMA-BitNet is a repository dedicated to empowering users to train their own BitNet models built upon LLaMA 2 model, inspired by the groundbreaking paper 'The Era of 1-bit LLMs: All Large Language…

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

Implementation for MatMul-free LM.

1.58-bit LLaMa model

PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"

Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction fine-tuning, reward model training, and support for PPO and DPO algorithms with various c…