Awesome Opensource Ai

Unified framework for building enterprise RAG pipelines with small, specialized models

A hyperparameter optimization framework

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

A framework for building realtime voice AI agents 🤖🎙️📹

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D avatar running locally across platforms

An open source implementation of CLIP.

Graph-Native Infrastructure for Context and Accountable AI Systems

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.

A framework for few-shot evaluation of language models.

Parallel computing with task scheduling

structured outputs for llms

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Open Machine Learning Compiler Framework

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

Build voice agents with open-source models

Minimal reproduction of DeepSeek R1-Zero

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

No description.

The Context Platform for your Data and AI Stack

No description.

The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

Access large language models from the command-line

A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Go ahead and axolotl questions

NumPy & SciPy for GPU

Agent S: an open agentic framework that uses computers like a human

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Retrieval and Retrieval-augmented LLMs

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

No description.

The ultimate training toolkit for finetuning diffusion models

AI Observability & Evaluation

A PyTorch-based Speech Toolkit

Low-code framework for building custom LLMs, neural networks, and other AI models

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Always know what to expect from your data.

🐍 Geometric Computer Vision Library for Spatial AI

Kimi Code CLI is your next CLI agent.

Pocket Flow: 100-line LLM framework. Let Agents build Agents!