最も幅広いグループです。チャット画面、SDK やフレームワーク、プロンプトや評価のツール、そして大規模言語モデルを使ったさまざまなアプリケーションが含まれます。多くは複数のプロバイダーのモデルに対応し、中には自分のハードウェアでモデルを動かせるものもあります。
製品に使うつもりなら、まず三つの事実を確認しましょう。ライセンス（人気のプロジェクトでも商用利用を制限していることがあります）、すでに使っているモデルプロバイダーに対応しているか、そして今もメンテナンスされているか。各プロジェクトページの「ひと目でわかる」欄が、ライセンスとメンテナンス状況を GitHub のデータから答えます。
35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
General technology for enabling AI capabilities w/ LLMs and MLLMs
Examples and tutorials to help developers build AI systems
LLM training code for Databricks foundation models
CISO Assistant is a one-stop-shop GRC platform for Risk Management, AppSec, Compliance & Audit, TPRM, BIA, Privacy, and Reporting. It supports 200+ global frameworks with automatic control mapping, including ISO 27001, NIST CSF, SOC 2, CIS, PCI DSS, NIS2, DORA, GDPR, HIPAA, CMMC, and more.
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
拼多多、千牛、抖店 AI 客服机器人：自动回复客户咨询、商品答疑、售后申诉处理，支持微信、小红书、京东、抖音、B站、微博等多平台统一接待；可接入 DeepSeek / 通义千问 等大模型，支持自有知识库定制。
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code.
🤖 A visualization mcp & skills contains 25+ visual charts using @antvis. Using for chart generation and data analysis.
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理
AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.
Preswald is a WASM packager for Python-based interactive data apps: bundle full complex data workflows, particularly visualizations, into single files, runnable completely in-browser, using Pyodide, DuckDB, Pandas, and Plotly, Matplotlib, etc. Build dashboards, reports, and notebooks that run offline, load fast, and share like a document.
eBPF Observability - Distributed Tracing and Profiling
Optimizing inference proxy for LLMs
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站：
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / Ultralytics / MMEngine / Keras etc.
AdalFlow: The library to build & auto-optimize LLM applications.