awesomejev

Community project / Agent and developer tooling

pi-warden

Pi guardrails built on pi-typesafe that return Jev's verdict to the agent as a held tool result or a short steer instead of a dialog, check writes against a project rules file, and grade their own holds against the user's next message on recorded sessions; the action guard is calibrated on one user's 17k calls, the other guards on synthetic cases only.

Open the original resource ↗ See it in the full directory Browse all Agent and developer tooling
Awesome Jev share card for pi-warden Download share card

Share this listing

Maintaining this project? Share its link, badge, or image. Listed means included, not endorsed.

Download share card

This is an independent community listing. Check the source, license, data handling, and evaluation caveats before relying on a project. Inclusion is not an endorsement or security review.

Found an outdated or inaccurate detail? Report a correction →

Explore more in Agent and developer tooling

  • pytest-jev

    pytest plugin for semantic assertions about LLM output: jev.expect batches Noul claims about one text, reports each probability, and by default fails uncertain claims (holds needs at least 0.8, lacks at most 0.2); Choice checks the selected option and Score checks probability mass across ordered levels. It caches answers in .pytest_cache, skips Jev tests without a key by default, and sends tested text and context to TypeSafe or OpenRouter.

    Read listing →

  • Skillbox

    Self-hosted agent skill library with opt-in Jev recommendations over task text and authorized active skill descriptions, using an owner-provided TypeSafe, OpenRouter, or Vercel AI Gateway key. Failed, oversized, or rate-limited evaluations fall back to deterministic search rather than returning a partial model ranking.

    Read listing →

  • SkillRanker

    Rust CLI that uses Jev Choice and Noul judgments to shortlist and rerank agent skills against the current task, with a real none option, local replay, and opt-in network disclosure; fresh ranking sends redacted session context and skill excerpts to TypeSafe, and its license includes an OpenAI/Anthropic rider rather than plain MIT.

    Read listing →