Evolve — Goal-Driven Improvement Loop

What it does

Evolve provides a fully autonomous, operator-driven improvement loop: it selects the highest-value work (pinned queues, harvested findings, failing goals, testing gaps), runs a research/planning/implement/validate (/rpi) cycle, applies a regression gate, and repeats until a stop condition. It's designed to iteratively harden and improve codebases by automating selection, execution, and validation.

When to use it

Use Evolve when you want continuous, supervised autonomous development: landing bug fixes, tightening validation, generating tests, performing audits, or processing a roadmap (.agents/evolve/roadmap). It is suitable for day-time operator runs where code changes are expected and validated each cycle.

What's included

• Scripts: included integration with /rpi lifecycle and repository-level scripts (has_scripts=true)
• References: comprehensive docs and references folder covering fitness scoring, pinned-queue patterns, and teardown (has_references=true)
• Instructions: detailed step-by-step execution of selection ladder, execution, regression gate, and teardown; guidance on flags like --compile, --dry-run, --beads-only.

Compatible agents

Best fit for agent platforms that support code changes and lifecycle tooling (AgentOps CLI, RPI engine). Commonly used with Claude Code, Codex, Cursor and similar operator-capable agents.