OpenClaw-RL: Train any agent simply by talking
-
Updated
Apr 19, 2026 - Python
OpenClaw-RL: Train any agent simply by talking
🦞 MCP server for OpenClaw - secure bridge between Claude.ai and your self-hosted OpenClaw assistant with OAuth2 authentication
简单安装配置OpenClaw 龙虾 Codex ClaudeCode等工具
Autonomous AI agent orchestrator — run multi-model dev teams (Claude, Gemini, GPT) with YAML workflows, daemon scheduling, and MCP integration. 100% Rust.
🦞The missing visual interface for GMClaw, turning complex agent orchestration into a seamless dashboard experience.
Local-first AI operating system. Persistent memory, 178 cognitive modules, multi-model reasoning. Runs on your hardware, not theirs. I am releasing SOMA to the world as I have reached the technical ceiling of what I am capable of so treat her good and enjoy.
AI-powered development framework with task management, 41 agents, 83 skills, and MCP tools for Cursor, Claude Code, Gemini, Codex & OpenCode. File-based memory that survives across sessions.
minist openclaw implement:一个极简版的 AI 助手,用 400 行代码实现核心功能:Telegram 集成 + LLM 工具调用 + 文件操作
Run long-running coding agents (Codex, Claude Code, etc.) in tmux sessions that survive restarts, with automatic resume on interruption.
Autonomous AI Agent for Windows - Your intelligent, always-on AI assistant with screen understanding and task automation.
An Identity, Security, and Governance Framework for autonomous agents
A three-layer persistent memory system that transforms Home Assistant's Gemini (or any LLM) conversation agent from a stateless chatbot into an intelligent assistant that **remembers, learns, and self-improves** over time.
The Silicon Hippocampus for your Agentic Workflow
Add a description, image, and links to the open-claw topic page so that developers can more easily learn about it.
To associate your repository with the open-claw topic, visit your repo's landing page and select "manage topics."