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.
Ranked by GitHub Stars
Ranked by recent Star growth and update activity
walidboulanouarwalidboulanouar/jev-agent-kitCLI 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.
SolidoSolido/jev_dartDart client for Jev (TypeSafe AI System One model), supporting typed questions and optimized HTTP transport.
gbessegbesse/jev-rerank-serverA drop-in rerank API server powered by TypeSafe AI's Jev model, compatible with Cohere, Jina, and Voyage rerank protocols for RAG stacks.
gbessegbesse/jev-decisionopsProvides 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.
gbessegbesse/jev-datagouv-joinIndependent JavaScript tool that calls TypeSafe AI's Jev API to resolve ambiguous joins between French public datasets, returning auditable candidates and review cases. Includes a local demo and tests; no live performance benchmark is claimed.
viroleavirolea/lintusA 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.
leonaaardobleonaaardob/fast-dev-compactionCodex 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.
viroleavirolea/jevRuby client for the TypeSafe AI Jev model API, supporting noul, choice, and score query types.
gbessegbesse/jev-codebookA Python CLI and library that applies a qualitative codebook to open-ended text using TypeSafe AI's Jev (System One), with a review queue, confidence intervals, and inter-rater reliability metrics.
gbessegbesse/decision-hubOpen-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.
gbessegbesse/figma-jev-reviewReview selected Figma copy with typed Jev criteria and exact TextNode citations.
gbessegbesse/decision-workbenchLocal decision studio that imports evidence, calls the TypeSafe Jev model for evaluation, preserves human review, and exports results.
