Jev Directory indexes 50 runnable evals and 722 community builds, agent-ready
thisiskp_ · x · 2026-09-19
A community-built directory for Jev, compiled by @phanindraai, aggregates 50 runnable judge-model evals — each with the exact experimentalevaluate prompt — plus 722 real builds from the TypeSafe AI community, 621 of them linked to actual projects.
The directory ships an agent-ready setup prompt: an AI agent first loads a capabilities.md pack from GitHub covering all evals and builds, then matches user requests to the closest eval or build, asks for missing details once, and executes. Every build is searchable and copyable as a brief.
A useful, source-linked index for developers exploring what Jev (typesafe-ai/jev via Vercel AI Gateway) can actually do.
More from coding & agent
- DSPy crew ships lm15, a zero-dependency litellm alternative for multi-provider LLM calls — lateinteraction · 2026-09-19
- Clairvoyance integrates Jev to help persistent-memory AI agents recall the right context — draginol · 2026-09-19
- Claude Code desktop app doesn't mute its browser agent, scare ensues — scaling01 · 2026-09-19
- Six Real Workflows for the Jev Judgment Model: 24/24 Fact-Checks at 0.41s Median Latency — alexisgallagher · 2026-09-19
- NVIDIA's SoL-Pi auto-evolves agent harnesses, cutting tokens ~50% and API costs ~33% with no quality loss — omarsar0 · 2026-09-19
- AI video editing shifts from generation to agentic workflow execution — OwlZealousideal4779 · 2026-09-19