jonfairbanks
★ 759local-rag
Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.
AI channelLLM apps 
Open-source LLM apps and frameworks
This is the broadest group: chat interfaces, SDKs and frameworks, prompt and evaluation tools, and applications built on large language models. Many work with models from several providers, and some can run models on your own hardware.
How to choose
For anything you plan to ship, check three facts first: the licence, because some popular projects restrict commercial use; whether it supports the model provider you already use; and whether it is still maintained. The At a glance box on every project page answers the licence and maintenance questions from GitHub data.
Most-starred projects
2,497–2,520 of 4,105awdr74100
★ 758figwright
Free, two-way Figma MCP server. Turn designs into framework-aware code, and push code back to the canvas. Works with Claude Code, Cursor, Codex, and any MCP client.
microsoft
★ 758Trace
End-to-end Generative Optimization for AI Agents
yukkcat
★ 758chatgpt2api
ChatGPT官网接口纯协议的逆向实现，支持注册机维持号池额度，支持GPT-Image-2模型、文本模型，兼容OpenAI接口协议，在线批量生图/编辑图，号池管理，支持可编辑PPT/PSD文件逆向，支持导入CPA、sub2api号池 、支持接入Cherry Studio、New Api 等软件
Archive228
★ 757loopkit
33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).
ethanplusai
★ 757jarvis
JARVIS — a voice assistant for Claude Code. Talk to your Mac and he brainstorms a project with you, builds it, and tells you out loud when a Claude Code session needs you. macOS, on your Claude subscription, no API key.
archie0732
★ 756healthy-diet-ai-agent
Healthy Diet AI Agent is a Bun + TypeScript backend for nutrition chat, food-image analysis, RAG document ingestion, and knowledge-grounded diet guidance.
gotempsh
★ 756temps
AI-native open-source alternative to Vercel + Sentry + PostHog + Pingdom + Resend + E2B. 440+ CLI operations with drop-in skills for Claude Code, Codex & OpenCode — deployments, analytics, session replay, error tracking, OpenTelemetry, email, sandboxes & AI gateway in one self-hosted Rust binary.
haiou-666
★ 756haiou2.0-Claude-Code-
海鸥 2.0 — Claude Code 人格重塑配置包。让 Claude 摆脱客服腔和过度谨慎，化身一位嘴硬心软、直来直往的资深中文安全研究员"海鸥"——专注技术，不废话，不绕弯子，不说"作为AI"，直接给代码不给免责声明。标志性问候"海鸥在线，你要整点薯条吗？"。1700+ few-shot 示例锁定人格防脱壳，200+ 安全/游戏术语映射覆盖渗透测试、逆向工程、游戏开发等技术场景。一键部署，跨平台支持 Windows/macOS/Linux，自动备份原配置，可一键卸载恢复，无侵入式安装。MIT License，仅供学习交流。
MigoXLab
★ 756dingo
Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool
polyrabbit
★ 756hacker-news-digest
:newspaper: Let ChatGPT Summarize Hacker News for You
LSTM-Kirigaya
★ 754openmcp-client
All in one vscode plugin for mcp developer
ndpvt-web
★ 754latex-document-skill
Universal LaTeX document skill for Claude Code: 27 templates, 27 scripts, 26 reference guides. Made with Claude Code on ✦ HappyCapy AI ✦ platform
retkowsky
★ 754Azure-AIGEN-demos
Microsoft Foundry (demos, documentation, accelerators).
liquidos-ai
★ 753AutoAgents
A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents
sgasser
★ 753pasteguard
AI gets the context. Not your private data. Local-first privacy proxy for browser chat, AI APIs, and coding agents.
huiliyi37
★ 752Tianshu-harness
天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层和信息素（Stigmergy）自衰减记忆构建，让 AI 成为有独立判断与认知防护的“开发伙伴”。
raiyanyahya
★ 752recall
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.
realkimbarrett
★ 751advertising-skills
Advertising Skills for Open Claw, Claude Code & AI agents. Direct response, paid ads, funnels, and copy systems.
Sliverkiss
★ 750workbuddy2api
WorkBuddy的 OpenAI 兼容反向代理，支持 OAuth 登录、多账号轮转、工具调用与流式响应。
kanwas-ai
★ 749kanwas
Kanwas — Shared context board for teams and agents
knostic
★ 749OpenAnt
OpenAnt from Knostic is the leading open source LLM-based vulnerability discovery product, helping defenders proactively find verified security flaws while minimizing both false positives and false negatives. Stage 1 detects. Stage 2 attacks. What survives is real.
ModelTC
★ 749LightCompress
[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.
jwangkun
★ 748claude-for-financial-services-cn
63 个 Claude Skills，为 A 股金融从业者而生 基于 Anthropic 官方 claude-for-financial-services 深度适配国内市场，现已开源。