Agent Control Plane Patterns is a public seed repository for agent control-plane architecture.
Reference patterns for agent control-plane architecture, not a competing implementation/product.
Early public seed repository. Candidate namespace only.
- Define the domain clearly.
- Collect prior art and adjacent ecosystem references.
- Provide reusable schemas, examples, and templates.
- Support human review and agent execution.
- Preserve provenance, auditability, and governance boundaries.
- This repo is not a universal standard.
- This repo does not claim ownership of the broader field or terminology.
- This repo does not canonize HUMMBL/BaseN/Ownward concepts unless explicitly marked and audited.
- This repo must not include private, internal, or secret operational content.
All content is exploratory unless later adopted through a reviewed governance path.
This repo is part of the HUMMBL AI governance architecture.
| Repo | Purpose |
|---|---|
| hummbl-governance | Governance runtime — kill switch, circuit breaker, cost governor, 34 primitives |
| mcp-server | MCP server for Base120 mental models — 120 reasoning operators for Claude/Cursor |
| base120 | 120 mental models for structured reasoning — stdlib-only Python library |
| crab | CRAB protocol — Check, Reason, Act, Bus for multi-agent turn execution |
| docs | Canonical public documentation — Mintlify-powered |
| hummbl-toolkit | HUMMBL utility toolkit |
Learn more at hummbl.io.
Reuben Bowlby — Founder, HUMMBL
- GitHub: @hummbl-dev
- X/Twitter: @ReubenBowlby
- LinkedIn: reuben-bowlby
- Website: hummbl.io