#279279th of 324 in Skills, plugins and prompts
autoswarm
Skill that lets one coding agent delegate tasks to other installed agents
- Stars
- 2.2k
- License
- MIT
- Last commit
- Oct 2026
- Language
- Python
100 on 3 Jul 20262,207 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AutoSwarm installs as a skill and Python CLI (`autoswarm setup --host <id>`) into an agent you already use, then delegates subtasks to other locally installed agents such as Codex, Claude Code, OpenCode, Cursor and Copilot CLI. It selects agents by capability, runs work in parallel, shares context between them and verifies results before answering. Setup is performed by the host agent from a git clone.
Who it is for: Developers running several coding agent CLIs who want one entry point
Strengths
- Supports 11 host agents including Codex, Claude Code, OpenCode, Cursor, Copilot CLI and Grok Build
- Reuses existing native credentials, models and proxy settings of installed agents
- Runs delegated tasks in parallel and collects results with `wait --any`
- `autoswarm doctor --probe` checks that each provider replies and resumes
Weaknesses
- No tagged release and no automatic updater; upgrades need git pull and reinstall plus setup
- Doctor probe spends real model calls on each provider
- Needs each underlying agent CLI installed and authenticated separately
- README gives no benchmarks or failure-handling details; technical detail sits in an archive
What it needs
- no GPU
- Needs Python 3.10+, uv (optional), Installed agent CLIs such as Codex or Claude Code
- Models: Codex, Claude Code, OpenCode, Cursor, GitHub Copilot CLI
Quick answers
Is autoswarm open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |