Last commit on October 8, 2026·Created on June 9, 2026
tigerless-labs/autoharness
“A self-learning skill layer that distills session lessons into durable agent preferences.”
Combined rank
#56
across all skills
Stars
11.1k
+1.2% in last 7d
Forks
629
+2.3% in last 7d
Watchers
257
-0.4% in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR
Autoharness enables AI agents to capture and codify reusable lessons from active coding sessions. It identifies corrected approaches and non-trivial techniques, transforming transient conversation history into a structured skill library.
This process helps automation builders maintain a consistent set of durable preferences and technical rules, ensuring that corrected mistakes are remembered and superseded by the most current methods.
WHO IT'S FOR
AI agent / automation builders
creating self-improving skill libraries for agents
Claude Code power users
automating the capture of durable coding preferences
Platform / DevEx teams
standardizing AI coding rules across a team
Technical leads / architects
governing the evolution of AI agent knowledge
Claude
HermesWant to install it?
Claude Marketplace · Claude Plugin · Clone to Claude · Manual CopyRepository instructions