Open source · CC BY 4.0
A governed operating model for AI-assisted delivery.
Durable context, autonomous worker sessions, explicit human decision rights, isolated execution, quality gates, auditable provenance. Mother CLAUDE runs a team of AI coding sessions that ship real work — while a human keeps every decision that genuinely needs one.
01 — The system in one picture
The tracker is the coordination layer. Nothing else is.
A human and one interactive session spec features into self-contained Ready tickets: context, scope, acceptance tests, pointers.
Claim → reconcile → build. Each worker runs in its own git worktree on a per-ticket branch, so sessions never collide.
Every ticket lands as a PR into the integration branch. Tests and CI decide whether work is objectively done.
Green and objective merges automatically. Anything touching UX or judgment is escalated to the human with verify steps.
Product direction, visual judgment, production promotion. Chat is for attention only — never for state.
02 — Three layers
Memory, work, governance — stacked in that order.
Memory
A three-tier documentation architecture: lean per-project context, shared cross-project standards, deep docs loaded on demand, plus session handoffs that survive an ephemeral session.
Work
The issue tracker as the only coordination layer — roles, queues, claims, isolated worktrees, PRs. No session talks to another; status is the single source of truth.
Governance
Definition of Done, tests and CI as objective evidence, steward review, escalation paths, graduated trust, and explicit human decision boundaries.
03 — Governance
What the AI is not allowed to decide.
Autonomous sessions may make reversible engineering decisions, constrained by documented standards and tests. Everything else escalates. If it takes taste to judge, a human judges it.
“LLMs don't need more prompts — they need better institutional memory. Autonomy needs governance before it needs scale.”
04 — The electric fences
The agents roam freely. The field is fenced.
Guardrails the workers cannot cross, enforced at the gate by CI, a pre-push hook, and the steward's review — and the fence line keeps growing: every incident that teaches a new failure mode becomes a new wire the next morning.
“Adherence is the worker's job; verification is the steward's.”
“A smarter model doesn't solve coordination — structure does. Verification solves trust, isolation solves collision, workflow solves ambiguity.”
“The agents aren't coordinated by intelligence. They're coordinated by structure.”
↗ A Self-Coordinating AI Dev Team: The Operating Model“The parallelism was never the problem. Every meaningful failure traced to one thing — the issue tracker had quietly drifted out of sync with the code.”
↗ What broke the first time we ran three AI workers on one repo“Adherence is the worker's job; verification is the Steward's. That second, independent check — not the agents' good intentions — is what lets the trust dial climb without the work going feral.”
↗ A Self-Coordinating AI Dev Team: The Operating Model05 — In preview
in previewThe engineering brain, served over MCP.
Instead of every session re-reading a docs repo, the Mother CLAUDE MCP server serves the rules, the worker roster, and the incident history to a whole fleet of AI coding sessions — pointed at any docs source you own.
06 — Start here
Everything is a file you can read today.
07 — Hard-won lessons
From running it, not designing it.
Don't let agents share a mutable checkout — worktree isolation isn't optional.
A shared dependency tree is shared mutable state. Gate installs to an owner, or isolate.
Chat is not state. If it matters, it goes on the tracker.
Claim, then reconcile, then build — in that order, every time.
Never auto-merge work whose Definition of Done has no objective test.
An autonomous system needs liveness supervision that isn't one of its own sessions.
08 — Written as it was built
The article series
The whole system, documented as it was built — the documentation architecture, session handoffs, automated hooks, instant retrospectives, custom agents, and the operating model the AI team runs on today.
All posts on dev.to ↗