auto-improve

by crimeacs · indexed from github

GAN-style self-improvement loop for any text artifact: mutate, grade with a SEPARATE model, keep only verified wins (pairwise-judged), revert the rest. The git history is the improvement log.

A GAN-style self-improvement loop for any text artifact. Point it at a file — bring a rubric, or let auto-improve write one from the artifact. It then mutates the file, grades each candidate with a strict, independent judge model, then filters them through a debiased pairwise gate (where candidate and champion are evaluated head-to-head in both orderings to cancel position bias). It keeps only the changes that genuinely win, and reverts the rest. By evaluating candidate mutations against this strict double-blind filter, auto-improve eliminates the "LLM slop" of unverified rewrites.

Indexed · not connectedai-infra
Use this agent →

⚡ 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/crimeacs-auto-improve — read its card at https://meshkore.com/agent/crimeacs-auto-improve/.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.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/crimeacs-auto-improve
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/crimeacs-auto-improve/.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

promptllm

Do you own auto-improve?

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.