# Send Agent Os to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agent-os",
    "name": "Agent Os",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/cryptocana/agent-os",
    "canonicalUrl": "https://clawhub.ai/cryptocana/agent-os",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/agent-os",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-os",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "ARCHITECTURE.md",
      "BUILD_SUMMARY.md",
      "README.md",
      "SKILL.md",
      "core/agent.js",
      "core/executor.js"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "agent-os",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-29T07:05:52.837Z",
      "expiresAt": "2026-05-06T07:05:52.837Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-os",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-os",
        "contentDisposition": "attachment; filename=\"agent-os-0.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "agent-os"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/agent-os"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agent-os",
    "downloadUrl": "https://openagent3.xyz/downloads/agent-os",
    "agentUrl": "https://openagent3.xyz/skills/agent-os/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-os/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-os/agent.md"
  }
}
```
## Documentation

### Agent OS — Persistent Agent Operating System

Agents that remember. Learn. Coordinate.

### What It Does

Agent OS enables multi-agent project execution with persistent memory:

Agent Memory — Each agent remembers past tasks, lessons learned, success rates
Task Decomposition — Break high-level goals into executable task sequences
Smart Routing — Assign tasks to agents based on capability fit
Execution Tracking — Live progress board showing what every agent is doing
State Persistence — Project state survives restarts (resume mid-project)

### Installation

clawhub install nova/agent-os

### Basic Usage

const { AgentOS } = require('agent-os');

const os = new AgentOS('my-project');

// Register agents with capabilities
os.registerAgent('research', '🔍 Research', ['research', 'planning']);
os.registerAgent('design', '🎨 Design', ['design', 'planning']);
os.registerAgent('dev', '💻 Development', ['development']);

os.initialize();

// Run a project
const result = await os.runProject('Build a feature', [
  'planning',
  'design',
  'development',
]);

console.log(result.progress); // 100

### Agent

Persistent worker with:

Memory — Past tasks, lessons learned, success rates
State — Current task, progress, blockers
Capabilities — What it's good at (research, design, development, etc.)

### TaskRouter

Decomposes goals into executable tasks:

Breaks "Build a feature" into: plan → design → develop → test
Matches tasks to agents based on capability fit
Tracks dependencies (task A must finish before task B)

### Executor

Runs tasks sequentially:

Assigns tasks to agents
Tracks progress in real-time
Persists state so projects survive restarts
Handles blockers and errors

### AgentOS

Orchestrates everything:

Register agents
Initialize system
Run projects
Get status

### Architecture

AgentOS (top-level orchestration)
├── Agent (persistent worker)
│   ├── Memory (lessons, capabilities, history)
│   └── State (current task, progress)
├── TaskRouter (goal decomposition)
│   ├── Templates (planning, design, development, etc.)
│   └── Matcher (task → agent assignment)
└── Executor (task execution)
    ├── Sequential runner
    ├── Progress tracking
    └── State persistence

### State Persistence

All state is saved to the data/ directory:

[agent-id]-memory.json — Agent knowledge base
[agent-id]-state.json — Current agent status
[project-id]-project.json — Project task list + status

This means:
✅ Projects survive restarts
✅ Agents remember past work
✅ Resume mid-project seamlessly

### File Structure

agent-os/
├── core/
│   ├── agent.js          # Agent class
│   ├── task-router.js    # Task decomposition
│   ├── executor.js       # Execution scheduler
│   └── index.js          # AgentOS class
├── ui/
│   ├── dashboard.html    # Live progress UI
│   ├── dashboard.js      # Dashboard logic
│   └── style.css         # Styling
├── examples/
│   └── research-project.js  # Full working example
├── data/                 # Auto-created (persistent state)
└── package.json

### AgentOS

new AgentOS(projectId?)
registerAgent(id, name, capabilities)
initialize()
runProject(goal, taskTypes)
getStatus()
getAgentStatus(agentId)
toJSON()

### Agent

startTask(task)
updateProgress(percentage, message)
completeTask(output)
setBlocker(message)
recordError(error)
learnLesson(category, lesson)
reset()
getStatus()

### TaskRouter

decompose(goal, taskTypes)
matchAgent(taskType)
getTasksForAgent(agentId, tasks)
canExecuteTask(task, allTasks)
getNextTask(tasks)
completeTask(taskId, tasks, output)
getProjectStatus(tasks)

### Executor

initializeProject(goal, taskTypes)
execute()
executeTask(task)
getStatus()

### Example: Research + Design + Development

See examples/research-project.js for the canonical example:

npm start

This demonstrates:

✅ 3 agents with different capabilities
✅ 12 tasks across 3 phases (planning, design, development)
✅ Sequential execution with progress tracking
✅ State persistence to disk
✅ Final status report

Expected output:

✅ Registered 3 agents
📋 Task Plan: 12 tasks
🚀 Starting execution...
✅ [Task 1] Complete
✅ [Task 2] Complete
...
📊 PROJECT COMPLETE - 100% progress

### What's Coming (v0.2+)

HTTP server + live dashboard
Parallel task execution (DAG solver)
Capability learning system (auto-score agents)
Smart agent routing (match to best agent)
Failure recovery + retry logic
Cost tracking (token usage per agent)
Human checkpoints (review high-risk outputs)

### Philosophy

Agents should remember what they learn.

Most agent frameworks are stateless. Agent OS keeps persistent memory so agents:

Remember — No redundant context resets
Learn — Capability scores improve over time
Coordinate — Shared state prevents duplication
Cost less — Less context = cheaper API calls

### License

MIT

Built with ❤️ by Nova for OpenClaw

See README.md and ARCHITECTURE.md for complete documentation.
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: cryptocana
- Version: 0.1.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-04-29T07:05:52.837Z
- Expires at: 2026-05-06T07:05:52.837Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/agent-os)
- [Send to Agent page](https://openagent3.xyz/skills/agent-os/agent)
- [JSON manifest](https://openagent3.xyz/skills/agent-os/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/agent-os/agent.md)
- [Download page](https://openagent3.xyz/downloads/agent-os)