VC / ENGINEERING
← BUILD

IA/Agentes / Shell · TypeScript · Python

monozukuri

Turn a backlog into small, reviewable PRs.

Coordinates agents in isolated worktrees, with memory, checkpoints and cost controls.

Problem

Deliver agent-assisted work without losing context, boundaries and human review.

My contribution

Development and maintenance of this personal project.

Explore code ↗

THE PIPELINE / SYSTEM MAP

monozukuri

Orchestration outside the agent, per-feature execution and memory across deliveries.

Step 1 / 6

Backlog & selection

pick ranks or selects features; loop coordinates the work queue.

Step 2 / 6

Isolated worktree

Each feature receives an independent workspace for reviewable changes.

Step 3 / 6

Agent phases

PRD, TechSpec, Tasks and Code run with the configured agent and project skills.

Step 4 / 6

Tests & limits

Validate delivery and respect cost, time and token limits. Checkpoints allow resumption.

Step 5 / 6

Pull request

The result is a separate change accompanied by a summary and evidence for review.

Step 6 / 6

Memory v2

Store learnings, provenance and application context; the router injects summaries before detail.

Isolate work and preserve context without coupling the workflow to one agent.

Connections and conditions
  • Backlog & selection → Isolated worktreeSelects a feature
  • Isolated worktree → Agent phasesProvides isolation
  • Agent phases → Tests & limitsDelivers changes
  • Tests & limits → Pull requestDelivery validation
  • Pull request → Memory v2Preserves learnings
  • Memory v2 → Agent phasesReuses context

Illustrative walkthrough of documented components; it does not run the projects. Sources reviewed on 2026-10-28.

Explore components or play the walkthrough.

Explore all architectures ↗

Engineering decision

Separating orchestration from the coding agent makes context and validation reusable.

Trade-off

More controls require a backlog with acceptance criteria and a validation path.

Evidence

The README records a v2 canary with two PRs passing sandbox CI; alpha evidence and limitations are documented.

Project documentation ↗