Jev Agent Kit
CLI and MCP tools for agents using TypeSafe Jev to make fast typed decisions: route, triage, guard, grep, rank, compact, and judge. Includes runnable use-case demos and an offline evaluation script.
OPEN SOURCE · CURATED REPOSITORIES
Curated Jev SDKs, tools, demos, integrations, benchmarks, and research projects. Repository metrics come from GitHub; titles, summaries, and categories are editorial.
Sponsors
These products pay for the directory. Want yours up here?
Ranked by GitHub Stars
Ranked by recent Star growth and update activity
CLI and MCP tools for agents using TypeSafe Jev to make fast typed decisions: route, triage, guard, grep, rank, compact, and judge. Includes runnable use-case demos and an offline evaluation script.
Dart client for Jev (TypeSafe AI System One model), supporting typed questions and optimized HTTP transport.
A drop-in rerank API server powered by TypeSafe AI's Jev model, compatible with Cohere, Jina, and Voyage rerank protocols for RAG stacks.
Provides evaluation and gateway tooling for TypeSafe Jev / System One-compatible decision models, including calibration metrics, threshold optimization, response validation, rate limiting, caching, circuit breaking, and audit logs. Community software independent of TypeSafe AI.
A Ruby linter that reads YAML rules phrased as plain-language questions and asks TypeSafe AI's Jev model to judge each file, reporting offenses based on the model's noul probabilities. Supports CI, pre-commit, and local runs.
One card in the feed, every sixteen, on every page of it. $50 a week, cancel any week.
Codex plugin that uses the TypeSafe Jev model to score tool calls and results during session compaction, then re-injects the verbatim kept history after compaction. Includes an npm library, tests, and demo, but the author does not recommend production use.
Ruby client for the TypeSafe AI Jev model API, supporting noul, choice, and score query types.
Open-source hosted Jev workspace for evaluating JSON states against immutable DecisionPacks, with revocable aggregate reports and optional live inference via a user-supplied Jev key.
Review selected Figma copy with typed Jev criteria and exact TextNode citations.
JEV CrowdSim runs a factorial audience grid through TypeSafe AI's Jev/System One API, exposing disagreement via main effects and Wilson intervals. It includes a CLI, library, and demo with synthetic fixtures; paid calls go to api.typesafe.ai.
Open-source Node.js tool that watches meeting transcripts and uses TypeSafe AI's Jev/System One API to identify decisions, open questions, and engagement with exact quoted lines.
Replay changed DecisionPacks over historical data, reuse judgments, and measure decision flips, with support for calling the TypeSafe Jev/System One API.