# harness-canopy

> harness-canopy — univerlab-harness-canopy. Use this tool when you need to orchestrate and coordinate multiple AI agents, requiring features like persistent memory, scheduling, and multi-agent coordination. It solves problems of complex agent management and synchronization, providing a unified interface for agent operations. With inputs from git and outputs to MCP, it streamlines agent workflows in a single Rust binary.

Canonical page: https://skillsregistry.net/skills/univerlab-harness-canopy  
JSON: https://api.skillsregistry.net/v1/skills/univerlab-harness-canopy

## Description

Agent operations center over MCP — orchestration, persistent memory, scheduling, and multi-agent coordination in one Rust binary. https://univerlab.org/canopy/

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-24

## Source

- **Source listing:** [GitHub](https://github.com/UniverLab/harness-canopy)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "univerlab-harness-canopy"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/univerlab-harness-canopy` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/univerlab-harness-canopy/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt