Awesome Opensource Ai

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

A programming framework for agentic AI

🧠 Train a 64M-parameter LLM from scratch in just 2h!

No fortress, purely open ground. OpenManus is Coming.

The open-source AI voice studio. Clone, dictate, create.

Deepfakes Software For All

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

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

Learn it. Build it. Ship it for others.

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

LlamaIndex is the document processing platform for AI

Hindsight: Agent Memory That Learns

We write your reusable computer vision tools. 💜

Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

aider is AI pair programming in your terminal

Learn how to develop, deploy and iterate on production-grade ML applications.

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

Apache Spark - A unified analytics engine for large-scale data processing

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Build resilient agents.

Build, run, and manage agent platforms.

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

Making large AI models cheaper, faster and more accessible

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

A library for efficient similarity search and clustering of dense vectors.

Official inference framework for 1-bit LLMs

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

A generative speech model for daily dialogue.

Extremely fast Query Engine for DataFrames, written in Rust

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

DSPy: The framework for programming—not prompting—language models

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

Cross-platform, customizable ML solutions for live and streaming media.

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

open-source coding agent

A reliable coding agent for complex software engineering tasks.

SGLang is a high-performance serving framework for large language models and multimodal models.

"Vibe-Trading: Your Personal Trading Agent"

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.