Evolving Agents — Development skill for Claude Code

Evolving Agents

**An open lab for agents that learn how a team works — and can show what they learned.**

A **director** keeps the team's way of working as a memory of small, linked, verifiable statements. It plans by walking that memory, hands each step to a frontier model or to small local specialists, and learns from every task — each lesson a gated, versioned patch that can be blamed or bisected. Every number below was measured, including the ones that came back flat.

[](https://github.com/EvolvingAgentsLabs/evolving-agents/stargazers) [](https://opensource.org/licenses/Apache-2.0) [](ROADMAP.md)

Your CLAUDE.md, actually followed

You wrote the rules down. Your agent still breaks them under pressure — **on 14 real situations, a Claude Code session with the rules loaded planned by them 0.589 of the time; the director, walking the same rules compiled into linked statements, 0.929.** If you keep a `CLAUDE.md`, an `AGENTS.md` or Claude Code's memory, this is for you:

• it recalls the rule at the moment it applies — and cites the statement it followed in every step of its plan;
• it learns from your corrections — each lesson proposed, checked against what it already knew, and kept