openlayer-ai/jevals
Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.
About the project
A library for evaluating and guarding AI agents: instead of an LLM judge it uses typed questions to Jev/Kev/Laya models, returning calibrated probabilities in a single request. Lets you check every trace quickly and cheaply, including inside the agent loop.
Useful for
- Run Grounded, AnswerRelevancy and PHI metrics on an agent trace in one request
- Add a gate inside the agent loop to block out-of-scope answers or PHI leaks
- Compare the agent's tool choice against the expected one via ToolChoice and UsedToolResult
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 0 stars so far today, about 23 expected by the end of the day.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 2 days old and already has 49 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Show HN: jevals – replacing LLM judges with typed Jev decisions” — 42 points, 1 day ago.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 49
- Today
- 0 · ≈ 23 by evening
- Forks
- 2
- Issues and pull requests
- 0
- Watchers
- 0
- Language
- Python
- License
- MIT
- Created
- September 20, 2026
- Last push
- September 22, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Hacker News discussions
- Show HN: jevals – replacing LLM judges with typed Jev decisions42 points, September 20, 2026
Spotted in
- September 22, 2026Spotted on Hacker News
- September 21, 2026Spotted on Hacker News
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/openlayer-ai/jevals)Similar by description
-
8.7
mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.
-
5.0
AnotiaWang/awesome-jev
A curated list of applications, libraries, and resources for Jev, TypeSafe's System One model that evaluates typed questions against a state and returns structured answers with probabilities.
-
4.0
itsmostafa/typesafe-mcp
A Go MCP server that gives AI agents access to TypeSafe's Jev model: instead of parsing prose, the agent gets typed answers with probabilities it can branch on. One-command setup for Claude Code, Claude Desktop, Codex,…