Open-source projects built with TypeSafe Jev, with submissions reviewed by Jev.
Submit a project · How reviews work · Jev Review Action
22 projects.
- TypeSafe JavaScript SDK — Official JavaScript and TypeScript client for TypeSafe's typed decision API, with question builders and typed responses.
- TypeSafe Python SDK — Official Python client for TypeSafe's typed decision API, with synchronous and asynchronous clients.
- hono-jev-router — Hono router that uses TypeSafe Jev to match HTTP requests against natural-language route descriptions.
- Jev MCP — MCP server that uses TypeSafe Jev for claim verification, content screening, and semantic candidate ranking.
- Typesafe MCP — MCP server that exposes TypeSafe Jev structured evaluations to coding agents and desktop clients.
- Jev Codex Router — Codex proxy that uses TypeSafe Jev judgments to route coding turns to different models.
- Jev Review — Code-review workflow that uses TypeSafe Jev structured judgments to assess changes and codebases, with a local results dashboard.
- Jev Review Action — Configurable GitHub Action using Jev to review directory submissions and classify pull requests, with evidence links and template-generated comments.
- jev-curate — Synthetic dataset sifter that streams JSONL and Parquet rows through TypeSafe Jev Noul checks to disk.
- jev-git — Sub-second Git pre-commit and pre-push reflex gate that screens staged diffs for secrets and destructive commands using TypeSafe Jev.
- jev-scout — Zero-hallucination open-source repo and crate scout powered by TypeSafe AI Jev System One scoring.
- Leanest — Local-first test selection tool that uses TypeSafe Jev semantic judgments to decide which tests are safe to skip for a given code change.
- SemDecide — CLI that uses TypeSafe Jev for semantic predicates, classification, scoring, and filtering in Unix pipelines.
- Supercov — Code quality and coverage CLI for coding agents that uses TypeSafe Jev to assess source-code quality.
- TypeSafe AI Playground — Rust CLI with TypeSafe Jev experiments for PHI detection, code-comment review, tone analysis, and classification.
- Winnow — Claude Code tool-output filter that uses TypeSafe Jev to judge which blocks are relevant to the current task.
- hev reranker — Python library using Jev Noul judgments to score candidate documents for query relevance, then sort or filter the results.
- Jev Search — Web search using Jev to choose sources, time ranges and query candidates, then rank Search1API results by relevance.
- neo4jev — Neo4j graph navigation demo that uses TypeSafe Jev to select relationships and check goals during beam search.
- Jev Ultrafast — Python browser agent using Jev to select operations and DOM targets, with a separate text model for typing.
- typesafe-computer-use — macOS computer-use tool using Jev to choose actions from OCR and accessibility state, with a separate model for free-text writing.
- LitJev — Open reproduction of Jev's decision layer on Qwen models that serves the Jev /v1/systemone request and response schema (choice, score, noul) from a local Hugging Face checkpoint by reading option logits instead of generating text, with an MMLU-Pro direct-answer benchmark.
Add up to ten project entries in a PR using the contribution guide. Each project is reviewed independently. Source paths are optional—the reviewer looks for integration code automatically. You can also ask for help submitting.
Jev Review Action checks source evidence, reviews the project description and setup instructions, and suggests a category. Jev supplies typed judgments; code renders the comment. Maintainers decide what gets merged.
See the review policy and validation records.
An independent project by fatwang2, not affiliated with TypeSafe. Inclusion is not a certification. MIT licensed; listed projects retain their own licenses.