KeploreAI-Lab

MindAct — AI skill for Claude Code

AI community

AI Agent + Specific Knowledge = A true Autonomous AI.

How to install MindAct

This entry records only its repository, not the path inside it, so there is no exact command to give. Open KeploreAI-Lab/MindAct and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What MindAct does

AI Agent + Specific Knowledge = A true Autonomous AI.

Alternatives in AI

WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, an 26.9k ★
Ralph For Claude Code — by Frank Bria - An autonomous AI development framework that enables Claude Code to work iteratively on project 8k ★
Osaurus — Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cry 5.1k ★

README

[![Claude Code](https://img.shields.io/badge/Claude_Code-Powered-d97706?style=flat-square&logo=anthropic&logoColor=white)](https://docs.anthropic.com/claude-code) [![AI Agent](https://img.shields.io/badge/AI_Agent-Desktop-3b82f6?style=flat-square&logo=electron&logoColor=white)](https://github.com/KeploreAI-Lab/MindAct) [![Obsidian](https://img.shields.io/badge/Obsidian-Compatible-7c3aed?style=flat-square&logo=obsidian&logoColor=white)](https://obsidian.md) [![RAG](https://img.shields.io/badge/RAG-Knowledge_Retrieval-f59e0b?style=flat-square)](https://github.com/KeploreAI-Lab/MindAct) [![Knowledge Graph](https://img.shields.io/badge/Knowledge_Graph-D3.js-8b5cf6?style=flat-square)](https://github.com/KeploreAI-Lab/MindAct) [![CLI](https://img.shields.io/badge/CLI-Rust-orange?style=flat-square&logo=rust&logoColor=white)](https://github.com/KeploreAI-Lab/physmind-cli-rust) [![License](https://img.shields.io/badge/License-AGPL--3.0-green?style=flat-square)](./LICENSE)

[![Discord](https://img.shields.io/badge/Discord-Join-5865F2?style=flat-square&logo=discord&logoColor=white)](https://discord.gg/hpq9t4QQ) [![GitHub Stars](https://img.shields.io/github/stars/KeploreAI-Lab/MindAct?style=flat-square&color=DAA520)](https://github.com/KeploreAI-Lab/MindAct/stargazers)

[English](./README.md) | [中文文档](./README.zh.md)

**From ReAct to MindAct.** [ReAct](https://arxiv.org/abs/2210.03629) (Reasoning + Acting) is the standard paradigm behind most AI agents — interleaving chain-of-thought reasoning with tool use. MindAct takes it further: before your agent acts, it checks what it knows, what it doesn't, and how confident it should be.

**MindAct** is a desktop AI workspace that