Minimalistic large language model 3D-parallelism training
AI Open Source
Hand-picked AI open-source projects on GitHub worth following: LLMs, agents, RAG, local deployment, image and speech… 1047 projects so far.
Looking for projects you can deploy for free on Cloudflare, Vercel, Netlify and more? See Free Deploy Picks
All 1047🧠 Large Language Models 26🤖 AI Agents 164🧩 App Development Platforms 23📚 RAG & Knowledge Bases 46💬 Chat UIs & Clients 41🖥️ Local Inference & Deployment 87👨💻 AI Coding 99🛠️ Frameworks & SDKs 47🔌 MCP & Tool Ecosystem 34🎨 Image Generation 25🎬 Video Generation 17🎙️ Speech & Audio 44👁️ Computer Vision 28📄 Document Parsing & Scraping 24🗄️ Vector Databases 25🏋️ Training, Fine-Tuning & MLOps 75🧪 Evaluation, Observability & Safety 81🚪 API Gateways & Proxies 12🔎 Search & Deep Research 15⚙️ Deep Learning Libraries 56🏷️ Data & Annotation 31🔬 Industry & Science AI 34⚡ Productivity Tools 13
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
An open-source data logging library for machine learning models and data pipelines. 📚 Provides visibility into data quality & model performance over time. 🛡️ Supports privacy-preserving data collection, ensuring safety
MCP proxy that converts between stdio and SSE/HTTP transmission.
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
법제처 국가법령정보를 LLM에서 바로 조회하는 MCP 서버. 법령·판례·조례 검색과 인용 검증 | MCP server for Korean law — search statutes, precedents, and ordinances, and verify citations
Self-learning agent browser
Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic, DeepSeek, Ollama, Mistral and OpenAI models remotely.
Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6
모두 파싱해버리겠다 — HWP·HWPX·PDF·Office 문서를 Markdown으로. 양식 자동 채우기와 신구대조를 갖춘 CLI·MCP 서버 | Convert Korean documents (HWP, HWPX, PDF, Office) to Markdown — CLI and MCP server with form filling and diff
Build, run and scale AI agents like API and microservices
Modular Python framework for building AI workflows with memory and tools.
Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
Hugging Face's Lightweight LLM Assessment Toolbox.
An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.
Apache Ossie, industry wide specification effort to standardize how we exchange semantic metadata across analytics, AI and BI platforms, providing a vendor neutral, single source of truth for semantic data
🤗 Evaluate: A library for easily evaluating machine learning models and datasets.
Machine learning metrics for distributed, scalable PyTorch applications.
An open-source framework for machine learning and other computations on decentralized data.
A simple, performant, and scalable Jax LLM!
Seamlessly integrate LLMs as Python functions
Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app
Bionic is sovereign Agentic AI for the enterprise — Runs on-premise and can securely work with your sensitive data and systems.