Best local desktop skills for AI agents

Use computers through an open agentic framework

Excellent quality, 12K stars, and a 25 use-case fit score.

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Excellent quality, 4.1K stars, and a 25 use-case fit score.

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

Excellent quality, 3.2K stars, and a 24 use-case fit score.

Agent Skills provides a structured approach for AI coding agents to follow production-grade engineering practices throughout the software development lifecycle.

Excellent quality, 45K stars, and a 24 use-case fit score.

A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/网页爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。

Excellent quality, 44K stars, and a 24 use-case fit score.

A comprehensive resource for enhancing workflows with Claude Code through various skills and tools.

Excellent quality, 45K stars, and a 24 use-case fit score.

A local-first AI agent with persistent memory, emotional intelligence, and a peer-to-peer skills economy.

Excellent quality, 1.9K stars, and a 24 use-case fit score.

Free, local, open-source 24/7 Cowork app for OpenClaw, Hermes Agent, Claude Code, Codex, OpenCode, Gemini CLI and 20+ more CLI | Customize your assistants | Star if you like it!

Excellent quality, 26K stars, and a 24 use-case fit score.

A comprehensive set of agent skills designed for various scientific and analytical applications.

Excellent quality, 25K stars, and a 24 use-case fit score.

OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.

Excellent quality, 25K stars, and a 23 use-case fit score.

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

Excellent quality, 39K stars, and a 23 use-case fit score.

FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making in a user-friendly environment.

Excellent quality, 23K stars, and a 23 use-case fit score.

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

Excellent quality, 38K stars, and a 23 use-case fit score.

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

Excellent quality, 17K stars, and a 23 use-case fit score.

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Excellent quality, 12K stars, and a 23 use-case fit score.

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

Excellent quality, 9.1K stars, and a 22 use-case fit score.

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

Excellent quality, 138K stars, and a 22 use-case fit score.

100+ AI Agent & RAG apps you can actually run — clone, customize, ship.

Excellent quality, 112K stars, and a 22 use-case fit score.

A marketplace for AI-assisted security analysis and auditing plugins.

Excellent quality, 5.3K stars, and a 22 use-case fit score.

A curated collection of agent skills focused on modern development practices.

Excellent quality, 5.0K stars, and a 22 use-case fit score.

Turn any website into LLM-ready markdown or structured data

Excellent quality, 123K stars, and a 22 use-case fit score.

The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices

Excellent quality, 5.1K stars, and a 22 use-case fit score.

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!

Excellent quality, 4.3K stars, and a 22 use-case fit score.

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

Excellent quality, 75K stars, and a 21 use-case fit score.

Multi-agent AI orchestration platform for automation, workflows, and developer tools. Golutra transforms Codex, Claude Code, and OpenClaw into a unified agent system with parallel execution, task orchestration, long-running workflows, and AI productivity workspace.

Excellent quality, 3.5K stars, and a 21 use-case fit score.

Universal memory layer for AI Agents

Excellent quality, 56K stars, and a 21 use-case fit score.

The simplest desktop client for OpenClaw 🦞 — bridge your Agent to WeChat, Feishu, Slack & Discord in one click. Works with Claude Code, Codex & any LLM. BYOK, Oauth, local-first, chat from your phone 24/7.

Excellent quality, 3.0K stars, and a 21 use-case fit score.

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.

Excellent quality, 52K stars, and a 21 use-case fit score.

Open Design is a powerful, local-first design tool that integrates multiple coding-agent CLIs for generating various design outputs.

Excellent quality, 50K stars, and a 21 use-case fit score.

🦞 OpenClaw & Hermes Agent 多引擎 AI 管理面板 — 内置 AI 助手（工具调用 + 图片识别 + 多模态），一键安装 | Tauri v2 跨平台桌面应用 | 11 种语言

Excellent quality, 2.7K stars, and a 21 use-case fit score.