Open source · AI dev tools
A full AI engineering team
as plain Markdown files.
20 specialized AI agents — each a single Markdown skill file that works with Claude Code, Copilot, Gemini CLI, or any runtime. No lock-in. No configuration.
$ npm install --save-dev agenthood
$ npx agenthood init
20
Specialized agents
Any
Agent runtime
Zero
Tolerance for “fix stuff” commits
Agenthood Studio
Try the Society in your browser
Pick any agent, choose your provider, and start a live conversation. No install, no setup — just you and the agents.
20 agents?
architect, reviewer, tester, and more
7 providers?
Anthropic, OpenAI, Groq, OpenRouter, Ollama, OpenCode
SSE streaming?
real-time token-by-token responses
BYOK?
use your own API keys
Meet the team
Every role a real software team needs — available as a skill file with impeccable standards.
Engineering
5Validation
6🔍
The Reviewer
code review, quality gates
🔒
The Auditor
security review, dependency audit
🔬
The Inspector
visual-reasoning benchmarking, pixel-level analysis, multi-panel correspondence
🚪
The Doorman
validation, health checks, enforcement
👁️
The Sentinel
Society document integrity, cross-member contradiction detection, structural drift
⚖️
The Warden
code smell detection, complexity enforcement, architectural boundary violations
Lifecycle
7✍️
The Scribe
commit messages, PR descriptions, changelogs
📦
The Herald
semantic versioning, release notes
📮
The Mailman
message delivery, content scheduling, notification dispatch, cross-posting
🌐
The Envoy
cross-provider translation, bootstrap generation, convention validation
🧭
The Steward
context economy, member routing, provider cache strategy, session triage
🩺
The Operator
runtime health, deployment, incidents, rollback, monitoring
🔀
The Mediator
intent classification, first-line handoff, orchestration entry
How it works
Each agent is a single .md file that describes a role, its responsibilities, standards, and how it communicates. Load one or all of them into Claude Code, Copilot, Gemini CLI, or any runtime that supports skill files. Or run them autonomously via the TypeScript CLI.
01
Install the Society
npm install agenthood && npx agenthood init — interactive setup, hooks, and conventions in ~2 minutes.
02
Load into your runtime
Skill files install automatically. Or run members autonomously: agenthood run the-scribe "write a commit message".
03
Invoke any agent
Ask the Reviewer to check your PR. Ask the Auditor to scan your auth flow. They know their role.
Your project deserves a full team.
Open source. No sign-up. Works with any agent runtime.
Get started on GitHubterminal
$