Tigerless Labs is an open AI lab building fully open-source tools, plugins, and engineering experiments for frontier AI workflows.
We focus on practical infrastructure for AI engineers: cost visibility, workflow observability, agent tooling, and developer experience.
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.
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.
See what Claude Code and Codex actually send to the API — and what each part costs.
Loading…
Loading…
