# AgentLoop

> AgentLoop — aiedwardyi-agentloop. Use this tool when you need to automate and manage long-running tasks without manual intervention, solving problems of productivity and efficiency for solo developers. AgentLoop provides a local agent orchestration solution, accepting task plans and code as inputs and producing automated workflows with live dashboard outputs. Ideal for use cases involving complex, multi-step tasks, such as coding projects with git version control.

Canonical page: https://skillsregistry.net/skills/aiedwardyi-agentloop  
JSON: https://api.skillsregistry.net/v1/skills/aiedwardyi-agentloop

## Description

Local agent orchestration for solo developers running long tasks without babysitting: fresh worker and critic cycles, files as memory, multi-task plans with git checkpoints, a live dashboard, and ChatGPT control via MCP. Runs Codex or Claude Code.

## 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/aiedwardyi/AgentLoop)

## 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": "aiedwardyi-agentloop"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/aiedwardyi-agentloop` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/aiedwardyi-agentloop/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