agentrigs
+ submit rig
~ / rigs / AutomatosAI / automatos-ai

AutomatosAI/automatos-ai

The open-source AI Operating System — run a workforce of AI agents on your own machine. Any model, 1,000+ tools, a Knowledge Graph, and your own Claude Code as agents. Self-host with docker compose.

↗ GitHub ★ 48 Apache-2.0 updated today project Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~4.6k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit AutomatosAI/automatos-ai/.claude ./rig-automatos-ai  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit AutomatosAI/automatos-ai/.claude/skills/prd-classify .claude/skills/prd-classify
$ npx degit AutomatosAI/automatos-ai/.claude/skills/register-tool .claude/skills/register-tool
$ curl -fsSL --create-dirs -o .claude/agents/canonical-term-checker.md https://raw.githubusercontent.com/AutomatosAI/automatos-ai/main/.claude/agents/canonical-term-checker.md
$ curl -fsSL --create-dirs -o .claude/agents/migration-reviewer.md https://raw.githubusercontent.com/AutomatosAI/automatos-ai/main/.claude/agents/migration-reviewer.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/block-secrets.sh"
          }
        ]
      }
    ]
  }
}

Skills (2)

prd-classifyregister-tool

Subagents (2)

canonical-term-checkerGreps the working tree (or a diff) for legacy terms that violate CLAUDE.md §10 canonical naming — Recipe→Playbook, Workflow/Job→Mission, Activity→Command Center, Output/Artifact→Deliverable, Business
migration-reviewerReviews Alembic migrations for safety — locking risks, NOT NULL on large tables, missing downgrades, idle-in-transaction risk, and online vs offline DDL. Use PROACTIVELY before merging any PR that tou

Hooks (3)

eventmatcherruns
PreToolUseEdit|Write$CLAUDE_PROJECT_DIR/.claude/hooks/block-secrets.sh
PostToolUseEdit|Write$CLAUDE_PROJECT_DIR/.claude/hooks/warn-os-getenv.sh
PostToolUseEdit|Write$CLAUDE_PROJECT_DIR/.claude/hooks/warn-hardcoded-llm.sh

Similar rigs

omerakben/agent-context-center
One offline, committed HTML dashboard that maps a repo's AI context — CLAUDE.md, AGENTS.md, Cursor rules, MCP servers, skills, agents, hooks, commands, docs, and TODOs. Markdown stays the source of truth; the dashboard is the human map.
★ 3 project Claude CodeCodexCursor 2 mcp 2 skills 1 agents 1 hooks 4mo ago
Pragmatist 6.8k tok ·
chase0213/dotfiles-claude
—
★ 0 setup Claude Code 4 skills 10 agents 1mo ago
Orchestrator 1.6k tok ·
stuartshields/claude-setup
Educational Claude Setup
★ 2 setup Claude Code 16 skills 28 agents 24 hooks 5mo ago
Fort Knox 3.7k tok ·
AlexisBalayre/claude-code-config
Opinionated Claude Code config: path-scoped rules, 34 skills, 12 subagents, deterministic hooks, and a multi-agent PR review. Stack-agnostic; run /adapt-to-project to fit any repo.
★ 2 setup Claude CodeCodex 1 mcp 34 skills 12 agents 7 hooks 4d ago
Fort Knox 6.4k tok ·
copied ✓