tigerless-labs

tigerless-labs

autoharness

★ 4,336

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.

tigerless-labs

cost-xray

★ 2,016

See what Claude Code and Codex actually send to the API — and what each part costs.

tigerless-labs

agent-memory

★ 939

Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.