Skip to content
TakoAPI
Back to skills

agent-os

by cryptocana

Coding Agents & IDEs
321Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Persistent agent operating system for OpenClaw.

Description

What This Skill Does

Agent OS is a persistent multi-agent orchestration system for OpenClaw. It gives agents memory across sessions, routes tasks by capability, and tracks project state so work survives restarts. Multiple agents coordinate on a shared project without duplicating effort.

Unlike stateless agent frameworks, Agent OS persists memory and project state to disk, so agents accumulate knowledge and projects resume mid-execution without restarting from scratch.

When to Use It

  • Running a multi-phase software project across planning, design, and development agents
  • Resuming a long-running agent task after a server restart
  • Assigning research subtasks to a specialized research agent while a dev agent handles implementation
  • Tracking which agent is blocked and why during complex project execution
  • Building an agent pipeline where task B only starts after task A completes

Example Workflow

INPUT

User asks: Build a new feature with planning, design, and development phases

AGENT
  1. 1

    Register three agents with capabilities: research/planning, design/planning, development

  2. 2

    Call os.initialize() to set up the system

  3. 3

    Call os.runProject('Build a feature', ['planning', 'design', 'development'])

  4. 4

    TaskRouter decomposes the goal into sequential tasks and matches each to the best-fit agent

  5. 5

    Executor runs tasks one by one, persisting state to disk after each completion

OUTPUT

Project completes at 100% progress with all task outputs saved; agents retain lessons learned for future runs

Installation

clawhub install cryptocana/agent-os

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links