Auto-Harness
Self-Learning Skills for Claude Code
AISTEADY● live
Visit site ↗First seen 1d ago · 1 platform
⚿ 4 contact fields stay closed. Everything it says about itself is open; how to reach it needs an account. Open them →
What it offers as proof1
“docs -> https://github.com/tigerless-labs/autoharness/tree/main/docs”
About
autoharness is a self-learning skill layer for Claude Code. It learns skills from your real sessions, merges same-scenario ones instead of stacking near-duplicates, updates them in use, and prunes any that stop getting used — so the layer stays clean on its own, touching only the skills it wrote itself. Same model, different harness — 42% → 78% on CORE-Bench (HAL). The harness does much of the work (swyx's Big Model vs Big Harness), yet it's still rebuilt by hand every model generation.
Discussion (0)
Posting is closed while we rebuild accounts — reading stays open.
No thesis posted yet. Be the first.