Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
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 1047 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 1047🧠 大規模言語モデル 26🤖 AI エージェント 164🧩 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 41🖥️ 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 47🔌 MCP とツールエコシステム 34🎨 画像生成 25🎬 動画生成 17🎙️ 音声とオーディオ 44👁️ 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 24🗄️ 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 75🧪 評価・可観測性・安全性 81🚪 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 56🏷️ データとアノテーション 31🔬 業界・研究向け AI 34⚡ 効率化ツール 13
Extract structured data and insights from documents using LLMs and decision models
Build LLM-powered applications in Ruby
Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks. Free, MIT-licensed
A Julia machine learning framework
The leading open-source AI copilot for JetBrains. Connect to any model in any environment, and customize your coding experience in any way you like.
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed inform
Code Editor for the AI Agents Era. Run multiple Claude Code and Codex agents across projects on your machine.
🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.
Large-scale LLM inference engine
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower develo
Magenta RealTime 2: An Open-Weights Live Music Model
Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨
Large-scale AI training tools for cleaning and sorting data.
Interpretability and explainability of data and machine learning models
MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
A neurosymbolic perspective on LLMs
Synthetic data curation for post-training and structured data extraction
The React library for LLMs
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.
TT-NN operator library, and TT-Metalium low level kernel programming model.
OpenMLDB is an open-source machine learning database that provides a feature platform computing consistent features for training and inference.
AI Novel Writing Software: Organizes inspirations, characters, worldbuilding, outlines, chapter drafting, review, and revision into a controllable
Automated Machine Learning on Kubernetes