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.
A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings.
Judges whether a finding was introduced by the change, is supported and merits a fix.
Shows execution records and reviewer judgments together.
Reviews a Git diff or a codebase in stages and displays review leads in a local dashboard.
Judges risk, files, evidence regions, mechanisms and severity before rule-based reviewer routing.
Connects review leads to concrete code for human inspection.
Helps coding Agents locate code, check change intent, triage test failures, and organize review findings.
Selects a fixed workflow and makes structured judgments over bounded diffs, code, or log excerpts.
Returns inspectable leads and states which parts were not checked.
Navigates a Neo4j graph one hop at a time, asking Jev which relationship to follow next.
Choice scores neighboring relationships and Noul checks goal completion; local beam search retains candidate paths.
Connects a natural-language goal to inspectable graph paths.
Finds files from a natural-language query using multiple walkers through the directory tree.
Jev scores file and directory names; code distributes walkers using those probabilities.
Searches without a vector index and reports the share of walkers reaching each path.
Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.
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.
Classifies Git commit messages and diffs with Jev for bug fixes, security fixes, CWEs, and change types.
Asks fixed-category questions about commits and saves results for filtering and HTML/CSV reports.
Organizes large commit histories into records for further review.
A Go Claude Code plugin using Jev to find files, answer bounded questions across code and handle large reads.
Screens and verifies code relevance before whole files enter the agent context.
Returns file locations and judgments for focused inspection.
Adds Jev checks to Claude Code review findings, debugging hypotheses, design options and search results.
Scores candidate defects, explanations or options against preset questions and local policies.
Keeps a second judgment and its probabilities available for comparison.
A Pi-based terminal coding Agent whose main model handles reasoning, edits and tools while Jev provides advice.
Jev suggests skills, reranks actual source candidates and triages failures without automatic retries or permission approval.
Preserves paths, line numbers, source and errors; the author’s bounded experiments do not establish universal gains.
Adds Jev-based selection before an existing test runner using diffs and test source.
Jev judges relevance; local policy runs tests on uncertainty, API failure or changes to the test file itself.
Supports shadow-mode comparison, but selected subsets cannot guarantee complete regression coverage.
A configurable GitHub Action that reviews catalog submissions or classifies PRs and updates a templated comment.
Answers policy questions over pinned repository evidence or PR patches, then applies classification rules.
Keeps question definitions, thresholds and comment templates inspectable.
One MCP tool that returns the files a coding agent should read.
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 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.
