Open-source pipeline for rewriting AI-generated text into natural human prose. Need it in your app? Try the Lynote Humanizer API → lynote.ai/ai-humanizer-api
AI オープンソース
GitHub 上の注目すべき AI オープンソースを厳選：大規模モデル、エージェント、RAG、ローカルデプロイ、画像・音声…現在 1056 件を掲載。
Cloudflare、Vercel、Netlify などに無料でデプロイできるプロジェクトをお探しですか？ 無料デプロイ厳選 をご覧ください
すべて 1056🧠 大規模言語モデル 26🤖 AI エージェント 166🧩 アプリ開発プラットフォーム 23📚 RAG とナレッジベース 46💬 チャット UI とクライアント 42🖥️ ローカル推論とデプロイ 87👨💻 AI コーディング 99🛠️ 開発フレームワークと SDK 48🔌 MCP とツールエコシステム 35🎨 画像生成 25🎬 動画生成 17🎙️ 音声とオーディオ 43👁️ コンピュータビジョン 28📄 ドキュメント解析とスクレイピング 25🗄️ ベクトルデータベース 25🏋️ 学習・ファインチューニングと MLOps 76🧪 評価・可観測性・安全性 82🚪 API ゲートウェイとプロキシ 12🔎 検索とディープリサーチ 15⚙️ ディープラーニング基盤ライブラリ 57🏷️ データとアノテーション 32🔬 業界・研究向け AI 35⚡ 効率化ツール 12
Build production-ready AI agents in both Python and Typescript.
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Laminar - open-source observability platform purpose-built for AI agents. YC S24.
Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.
Bonsai Demo
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimizati
Open-source inference server and production cluster for all the models your agent needs.
II-Agent: a new open-source framework to build and deploy intelligent agents
An open-source background agents coding system
Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepS
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents
JAX-based neural network library
A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, To
🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.
Cortex - Generates interactive API documentation, typed SDKs, and MCP servers from OpenAPI, AsyncAPI, GraphQL, gRPC, OpenRPC, and Markdown.
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
One-stop spread model training tool with a graphic interface.
Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.
Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch and TensorFlow.
🦜💬 Web app for interacting with any LangGraph agent (PY & TS) via a chat interface.