tigerless-labs

Building the self-learning layer next-gen agents will ship with, learning skills from real work.

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

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.

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.

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...

Finds the AI papers 28 tech companies put on arXiv over any date range, and splits lead authorship from bylines. A SKILL.md agent skill — no ML, no state, stdlib only.

Influencer discovery & contact enrichment pipeline that runs as a Claude Code skill — 15 channels, stdlib only, appends to a Google Sheet

Detect, gate, redact, and report PHI candidate flows across healthcare and insurance AI prompts, RAG, tools, memory, logs, and provider boundaries.

Lightweight, rule-based checks for missing, weak, and uncovered tests in pull requests.