5 projects
test-drive-skill
Helpers for the Test Drive agent skill
wicket
Fair admission of work to shared capacity: which waiting ticket may start now, by priority, fairness between tenants, and limits on concurrency and rate.
convy
Conversation tests for AI agents: a simulated user talks to your agent through its API, a judge checks every claim, and convy reports pass rate, tokens, time and what changed between builds.
langchain-skill-router
Per-turn skill routing for LangChain deepagents: a pluggable judge (Jev included, or your own) loads only the SKILL.md skills each turn needs, keeping a catalog of hundreds out of the prompt.
promptum
Async LLM benchmarking library with protocol-based extensibility
