Claude Code multi-agent
Agentlas OS
The Open-Source AI Agent OS inspired by OpenAI Dots, Meta Muse, OpenClaw, Hermes & Mem0. Autonomous 3-tier headhunting, Receipt & Verifier loops, scoped memory, and BYOM for Claude Code, Codex & Cursor.
Install
/plugin marketplace add agentlas-ai/Agentlas-OSFound in the project README. Check it for setup steps after installing.
git clone https://github.com/agentlas-ai/Agentlas-OS.gitFrom the README
English · 한국어 · 中文 · 日本語 · हिन्दी Agentlas OS An open-source AI agent OS inspired by OpenAI Dots, Meta Muse, Claude Duet, Nous Hermes, and Mem0. Built to lead entire projects rather than isolated prompts. Model-agnostic (BYOM) and native to Claude Code, Codex, Cursor, Antigravity, and Agentlas Desktop. Most agent products take one of two approaches. Some are prompt loops that report a task as done without checking the result. Others run each agent in a virtual machine, in the cloud or on your computer, apart from your files, credentials, and tools; a local VM also holds memory and disk while it runs. Agentlas OS takes neither approach. It runs no VM: agents work in the terminal, files, and tools already on your machine, and a task is complete only after an independent verifier accepts its execution receipt. Install Agentlas Desktop via the button below for the full runtime and mobile pairing (One), or attach this repository's runtime packs directly to Claude Code, Codex, or Cursor. macOS · Windows · Linux · Android · iOS coming soon 12,000+ desktop downloads · Free to download, runs on your own AI plan or key · Apache-2.0 Website · Agent Hub · Discord · Developers ↓ Architectural Foundations Instead of stitching together single-purpose wrappers, Agentlas OS combines five agent patterns in one local-first runtime. - Persistent autonomous execution (inspired by OpenAI Dots): Goals survive across sessions. Work resumes from the last checkpoint, and a step counts as complete only after an independent verifier checks its execution receipt. - Domain-complete workflows (inspired by Meta Muse): Work runs to a finished deliverable across personal operations (One), investment research that keeps the inputs behind each calculation (Finance), and literature and…
Details
- Repository
- agentlas-ai/Agentlas-OS
- Website
- agentlas.cloud
- Language
- Python
- License
- Apache-2.0
- Last updated
- 9 November 2026
- Topics
- agent-orchestrationagentic-aiai-agentai-agentsai-assistantai-coworkerai-toolsautonomous-agentsclaudeclaude-codecomputer-usecowork
FAQ
What is Agentlas OS?
The Open-Source AI Agent OS inspired by OpenAI Dots, Meta Muse, OpenClaw, Hermes & Mem0. Autonomous 3-tier headhunting, Receipt & Verifier loops, scoped memory, and BYOM for Claude Code, Codex & Cursor. It is a multi-agent for Claude Code, from agentlas-ai/Agentlas-OS on GitHub.
How do I install Agentlas OS?
Run /plugin marketplace add agentlas-ai/Agentlas-OS inside Claude Code, then follow the setup in the README.
Is Agentlas OS popular?
agentlas-ai/Agentlas-OS has 1,450 GitHub stars and 107 forks. It was last updated on 9 November 2026.
More multi-agent & worktrees
Claude Code Prompts
1.2krepowise-dev/claude-code-prompts
Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.
Openmeld
1.4kamplifthq/openmeld
The open-source collaboration system for people and AI agents. Share context, coordinate tasks, and work in parallel with your team, cloud agents, Codex, Claude Code, Grok, Grok Bot, OpenCode, Antigravity, and Cursor.
amux
557mixpeek/amux
Control plane for running Claude Code agents in parallel with a shared task board and schedules.
AgentAPI
1.5kcoder/agentapi
HTTP API for controlling Claude Code and other agents programmatically.
Sleepless Agent
840context-machine-lab/sleepless-agent
Runs Claude Code around the clock via Slack, processing queued tasks in isolated workspaces.
Opslane
770opslane/opslane_old
Runs multiple Claude Code sessions in parallel.
Browse the most popular Claude Code mods, all multi-agent & worktrees, or the skills and MCP server directories.