Skip to main content
Open source · AI dev tools

A full AI engineering team
as plain Markdown files.

16 specialized AI agents — architect, reviewer, security expert, DevOps engineer, strategist, operator, and more — each a single Markdown skill file any agent runtime can load into any project. Features autonomous agents with memory, RAG, CI enforcement, and multi-member orchestration. No lock-in. No configuration. Just drop them in.

View on GitHubHow it works
$npm install --save-dev agenthood
$npx agenthood init
16
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.

Open PlaygroundAbout Studio
16 agents?
architect, reviewer, tester, and more
6 providers?
Anthropic, OpenAI, Groq, 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.

✍️
The Scribe
Commits, PRs, changelogs
🏗️
The Architect
System design, ADRs, tech decisions
🔍
The Reviewer
Code review, standards enforcement
🧪
The Tester
TDD, coverage, edge cases
🐛
The Debugger
Error triage, root cause analysis
🔒
The Auditor
Security, vulnerability scanning, dependency audit
📦
The Herald
Releases, versioning, changelogs
📝
The Librarian
Documentation, API references
🚪
The Doorman
Validation, branch protection, health checks
🔮
The Oracle
Institutional knowledge, authoring templates
🌐
The Envoy
Cross-provider translation, convention validation
👁️
The Sentinel
Integrity, cross-member contradiction detection
⚖️
The Warden
Code health, complexity enforcement
🧭
The Steward
Context economy, provider cache strategies
🎯
The Strategist
Goal refinement, requirement discovery
🩺
The Operator
Runtime health, deployments, rollback

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 GitHub