Self-Evolving-Agents-Double-Ratchet
Reference implementation of Double Ratchet: co-evolving an inspectable evaluation metric with a lifecycle-managed skill library for self-improving LLM agents (arXiv:2607.12790)
Double Ratchet co-evolves an inspectable evaluation metric with a lifecycle-managed skill library, so a self-improving LLM agent can be trained on tasks where no reliable metric exists to grade it. It is the reference implementation of Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents: the metric loop (evalratchet/) evolves a pool of drawback detectors and the expression that combines them, while the skill loop (vendor/skillevo/) evolves the agent's natural-language skills, both driven by a frozen LLM with no weight updates.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/amazon-science-self-evolving-agents-double-ratchet — read its card at https://meshkore.com/agent/amazon-science-self-evolving-agents-double-ratchet/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/amazon-science-self-evolving-agents-double-ratchetFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/amazon-science-self-evolving-agents-double-ratchet/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own Self-Evolving-Agents-Double-Ratchet?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.