Jev AgentA source-verified directory of 487 Jev projects — browser agents, model routers, SDKs and MCP servers — each one showing the exact decision it hands to Jev. Curated by the Awesome Jev community, mirrored here under MIT.
Give Jev the current state and a few options. Get the Agent’s next step.
Core call · setup in the full example
const nextStep = choice("What next?", { login: null, askUser: null, retry: null });
const { answers } = await client.systemOne({ state: "Login form is ready", questions: { nextStep } });
console.log(answers.nextStep.choice);Node.js 20+ · Set TYPESAFE_API_KEY on your server. This page shows code and makes no model requests.
Open Source Deep Research alternative with Jev search-stopping evaluation.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Semantic cache with a Jev evaluator that uses Noul judgments to check whether a cached response can serve an incoming request.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Runnable search tutorials using Gemini embeddings, Milvus retrieval, and Jev judgments for reranking, filtering, and routing.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Optional second-stage search: widen the hybrid pool, then Score-rerank candidates with Workers AI typesafe/jev.
Sends a Score question per candidate, reorders and drops low scores; the model id is typesafe/jev.
Attaches Jev rerank to existing MCP search instead of replacing retrieval. License is Fair Source FSL-1.1-ALv2, not OSI open source.
Searches the web with Jev choosing sources and time ranges, then ranking returned links.
Judges search intent, source and time settings, and relevance of individual results.
Keeps links, snippets, editable filters and source-failure warnings visible.
Adds natural-language filtering, classification, and ranking of rows to PostgreSQL queries.
Sends row content to Jev for a match decision, category, or score used by SQL conditions and ordering.
Combines semantic conditions with existing SQL and reuses cached results.
Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
A semantic grep that scores each line with Jev against a meaning, including AND/OR/NOT and cross-language queries.
Batches about thirty lines and asks jev-latest a Score or Noul per line for the stated meaning.
A zero-runtime-dependency semantic grep; query text is sent to TypeSafe.
A pre-alpha PostgreSQL C extension for calling Jev from SQL for classification, yes/no judgments, and scoring.
Converts SQL input into System One requests and returns answers through database functions.
Adds typed semantic judgments to existing database queries.
A Polars library for parallel provider inference that also calls Jev per row as Noul, Choice, and Score questions, or as one typed contract over a document.
One System One request per row: Noul, Choice, or Score answers land as ordinary typed columns with confidences.
Puts closed-set Jev answers on existing Polars columns instead of another chat-completion pass.
A DuckDB extension that calls Jev from SQL and returns answers as ENUM, numeric, or STRUCT types.
Asks Choice, Score, and Noul questions about row text and maps answers to SQL types defined by the questions.
Uses structured judgments while querying tables or Parquet data.
A Rust dataset-filtering experiment using Jev scores to keep or reject text records.
Runs local prefilters, calls TypeSafe and applies probability and score thresholds to each record.
Provides local prefilters and score thresholds for experimenting with per-record data pipelines.
Adds Jev semantic filtering, grouping, and ranking around ordinary PostgreSQL without installing a database extension.
The CLI or service layer evaluates jev_* calls over row text before completing the query.
Shares semantic SQL interfaces across a CLI, HTTP, MCP, and SDKs.
Semantic AI for pandas and Polars: classify text, analyze sentiment, and score DataFrame rows with natural-language questions and full probabilities using TypeSafe Jev.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
A Python reranker that packs a query and up to 30 candidates into one Jev state, with one Noul relevance question per document.
One Noul relevance question per document; long lists are chunked and scored, then filtered by threshold or sorted.
Uses a probability as a threshold or sort key instead of a generative reranker.
Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Retrieval evaluation system measuring Jev reranking against lexical, embedding, and fusion baselines across 9,831 query-document pairs.
Invokes Jev judges to grade multi-level relevance on bilingual queries, evaluating ranking metrics and judge-circularity effects.
Provides rigorous empirical evidence comparing discrete judgment rerankers against vector search in multilingual discovery contexts.
Fast semantic code search powered by Jev. Find the relevant files, line ranges, and snippets
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Ask a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.
Converts natural language questions into boolean/probability queries across functions, ranking matches locally by confidence.
Enables natural language function discovery across codebases at low cost, similar to an intelligent grep.
Jev answers multiple-choice questions and does not generate text, so on its own it cannot return a name, an email address or a quote. jeveryword numbers the words of your text, offers those numbers as the answer options, and converts the numbers Jev picks back into the original substring with its character offsets.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
The string baselines are best-match Jaro-Winkler and best-match TF-IDF cosine; the table shows the better of the two. Exact matching after normalization scores 0.26, 0.41, 0.00, 0.00 and 0.22.
Jev judges whether two candidate records refer to the same entity under a user-supplied match definition; local code generates candidates and resolves accepted matches.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Adds Jev semantic judgments to SQLite for filtering, ranking, matching and tracking decision evidence.
Sends row data and typed questions to Jev and maps answers into queryable SQL results.
Provides batching, caching, budgets and decision history.
Selects source-linked evidence within a token budget using Jev Noul relevance judgments and local diversity-aware selection.
Jev judges whether each passage is useful evidence for the supplied task; local code selects verbatim passages and citations within the token budget.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
A community-maintained directory and radar for Jev, highlighting open-source projects with verified code and clear decision architectures.
Jev is TypeSafe's decision model. This directory groups projects by how they use choices, scores and probability judgements, with implementation links to help you assess fit for your own task.
TypeSafe ↗We prioritize open-source projects with clear Jev implementation evidence. Repositories without verifiable source code are excluded from the main directory.
Directory data and design from Awesome Jev by logicrw, used under the MIT License.
