Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
About
An open AI research lab shipping tools, agents, and experiments across the AI development stack.
Repos · 4
tigerless-labs/
autoharness
tigerless-labs/autoharnessPlugins
3.5k
tigerless-labs/
cost-xray
See what Claude Code and Codex actually send to the API — and what each part costs.
1.5k
tigerless-labs/
design-harness
Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for Claude Code & any SKILL.md-compatible agent.
217
tigerless-labs/
seo-ops
tigerless-labs/seo-opsSkills
SEO foundation checks as an Agent Skill: give it a URL, get a crawler's-eye pass/fail report with evidence. 26 structural checks, zero LLM, deterministic.
136
Not seeing a repo? Add it, or type sandbx.ai/tigerless-labs/repo-name.
What people say
No comments on tigerless-labs's repos yet.