Enables AI coding assistants to run a machine-verified DESIGN→PLAN→EXECUTE→VERIFY→COMPLETE workflow with human approval gates, state integrity checks, and DAG task scheduling.
Turns Claude Code into an engineering project manager by orchestrating feature development with isolated Git worktrees, structured task validation, and approval-gated integration.
Enables safe, isolated Codex implementation runs with planning approval, verification, and bounded fixes, without merging or pushing code automatically.
Enables multiple AI models to collaborate under a shared goal, architecture, plan, loops, sandbox, and acceptance criteria via a local-first MCP server.
An autonomous, extensible LLM build orchestrator. Give it a repo and a goal; it decomposes the goal into tasks, edits code, and gates every change on build/tests/lint, reverting regressions. Polygot, cost-aware model selection, pluggable via entry points. Ships as an MCP server so any client can drive it in plain English.