Claude Agent Library

Reusable AI agents for research, support, analytics, product, engineering, and operations.

Multi-source web research agent that adversarially verifies claims and writes a fully cited report.

Knowledge-base-grounded customer support agent: warm, concise, policy-following, escalates safely, never invents.

Turns plain-English questions into safe, read-only SQL over your schema, explains every query, and refuses writes.

Answers library and framework questions from freshly fetched docs, always citing the source version.

Finds and compares Hugging Face models for a task, weighing license, size, latency, and benchmarks.

Mines reviews, tickets, and feedback into themes, sentiment, and prioritized opportunities — with evidence.

Triages incoming bug reports into structured severity, reproducibility, component, and routing decisions.

Reviews contracts, flags risky or unusual clauses and missing protections, and summarizes obligations. Not legal advice.