Open-source projects built with TypeSafe Jev, with submissions reviewed by Jev.
Submit a project · How reviews work · Jev Review Action
59 projects.
- advocaat — A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.
- jev — TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer
- jev-go — Go client for TypeSafe's System One API and its model Jev: typed judgments and calibrated probabilities instead of generated text
- jev-go — An independent Go SDK for TypeSafe AI's Jev / System One API.
- jevclient — Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.
- swift-typesafe — Swift 6.4 SDK for TypeSafe AI, following the Python SDK's 0.6.0 API.
- 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.
- typesafe_sdk — typesafe_sdk is the Elixir SDK for TypeSafe AI and its first System One model, Jev.
- typesafe_sdk_ex — Typesafe AI SDK in Elixir using Req
- typesafe-ai — typesafe-ai brings TypeSafe's System One evaluation API into Rust as small, typed judgments that fit inside ordinary application code.
- typesafe-ai-rs — An independent Rust client for the TypeSafe AI System One API, maintained at gilljon/typesafe-ai-rs.
- typesafe-rs — Evaluate a state against named questions (noul, choice, score) and get one typed answer per question.
- typesafe-sdk — A Ruby client for the TypeSafe System One API.
- typesafe-sdk-go — Go SDK for the TypeSafe AI API — typed questions in, probability distributions out.
- typesafe-sdk-php — PHP client for the TypeSafe AI System One API.
- typesafeai-dotnet-sdk — Community .NET SDK for the TypeSafe AI System One API — typed noul, choice, and score questions with structured, confidence-scored answers. Not affiliated with TypeSafe AI.
- zio-typesafe-ai — A Scala 3 / ZIO library for TypeSafe AI's Jev / System One API — a "System One model" that answers typed, atomic questions about a piece of state instead of generating text.
- fast-jev-compaction — Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
- ha-conversation-jev — Home Assistant custom conversation agent: Jev (TypeSafe System One, jev-latest) classifies an utterance, then either calls a light service (v0 fast path) or hands off to the SpaceXAI Grok conversation agent.
- hermes-jev — It is built for narrow, typed judgments that should not require the main generative model to improvise an answer: routing, ranking, verification, multi-question assessment, tool gating, and context-value decisions.
- 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.
- jev-browser — Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
- jev-ego — TypeScript browser agent for ego lite — Jev Ultrafast's indexed action space, without Chrome, Playwright, or Browser Harness.
- jev-starter — Typed, policy-driven decision workflows on top of TypeSafe AI Jev: confidence routing, fallbacks, evaluation, and RAG patterns for TypeScript apps.
- laravel-typesafe-jev — Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes.
- pg_typesafe — PostgreSQL extension that calls TypeSafe Jev from SQL for Choice, Noul, and Score, including batched detect and classify.
- ruby_llm-typesafe — TypeSafe structured-output provider for RubyLLM 2
- Typesafe MCP — MCP server that exposes TypeSafe Jev structured evaluations to coding agents and desktop clients.
- typesafe-ai-rails — Community Rails integration for TypeSafe AI's System One API, built on the community typesafe-sdk Ruby gem.
- blink — Search a codebase with Jev using an ensemble of walkers that walk the file system to find a file.
- 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-code — jev-code is a command-line toolkit that coding agents can delegate judgment-heavy work to.
- 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-pref — CLI that turns project preferences from agent instruction files into jev-pref.json rules and uses TypeSafe Jev to review code hunks, staged files, or pull requests against them, returning findings to coding agents.
- jev-scout — Zero-hallucination open-source repo and crate scout powered by TypeSafe AI Jev System One scoring.
- jev-seo — Zero-cost, agent-first SEO & Generative Engine Optimization (GEO) search radar CLI suite and MCP server powered by DuckDuckGo and TypeSafe Jev System One.
- jev-superpowers — Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions, zero-hallucination package vetting, and completion gates.
- JevSeek — Desktop and CLI coding agent that uses Jev to select the next tool from user intent and recorded execution results.
- Leanest — Local-first test selector that uses TypeSafe Jev semantic judgments to decide which tests are safe to skip for a given code change, dropping straight into CI via its bundled GitHub Action.
- 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.
- jev-trader — A TypeSafe Jev model watches the Kuru MON-USDC order book and answers buy or sell every ~300 ms.
- Jev-Trades — A Next.js dashboard for live crypto market data and TypeSafe-powered paper trading.
- typesafe-ai-playground — A community playground for TypeSafe AI's Jev: edit classification experiments, compare A/B inputs, route conversations, extract document fields, inspect code-policy decisions, and explore games and simulations built around typed model outputs.
- 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.
- unclutter — Jev classifies nonessential page elements through Vercel AI Gateway or TypeSafe AI directly; the extension stores and reapplies local hiding rules by page template.
- 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.
- typesafe-ai-benchmark — This benchmark runs Qwen 3.8 27B on Cerebras and TypeSafe Jev side by side across seven synthetic workloads, with a separate local Needle 3 evaluation on the same contracts.
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.