Search awesome repositories

A PyTorch native platform for training generative AI models

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

Context Graph for AI Native SDLC

Gemma open-weight LLM library, from Google DeepMind

Library for building WebSocket servers and clients in Python

A programmable Mixture-of-Models router for heterogeneous LLM inference

It's not just a linter that annoys you!

mlpack: a fast, header-only C++ machine learning library

Model interpretability and understanding for PyTorch

OpenClaw-RL: Train any agent simply by talking

🍊 :bar_chart: :bulb: Orange: Interactive data analysis

CUDA accelerated rasterization of gaussian splatting

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.

Agent-ready RPA suite with out-of-the-box automation tools. Built for individuals and enterprises.

An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance

Socket.IO integration for Flask applications.

Supercharge Your Model Training

Rust bindings for the C++ api of PyTorch.

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Python-based continuous integration testing framework; your pull requests are more than welcome!

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Autonomous Hacking Agent for Red Team

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

A better Python REPL

Perceptual video quality assessment based on multi-method fusion.

Build distributed, production-grade, long-running agents.

A Python native, OS native GUI toolkit.

FastF1 is a python package for accessing and analyzing Formula 1 results, schedules, timing data and telemetry