Jev MCP

An MIT-licensed, local-first conversation memory app that transcribes meetings, calls and voice memos on-device into Markdown you own. Its live voice path runs evaluations through Jev, and 34 MCP tools plus a 58-command CLI let coding agents query the history you choose to share.

A Python decision gateway and stdio MCP server that exposes Jev through OpenRouter's alpha decisions endpoint. Five tools cover yes/no checks, classification, scoring, multi-question evaluation and health, with bounded retries, validated answers and local diagnostics.

MCP server and Claude Code plugin that files each captured note, link or meeting line with one Jev request: kind, project, action and duplicate questions answered in parallel. Routes to a project only at 0.45 or above, marks a duplicate only at 0.70 with a matching item, and stores text verbatim in append-only JSONL.

MIT-licensed Python tool router for coding agents that keeps obvious calls on a fast path, asks Jev (default typesafe/jev-1.13 via OpenRouter) for genuinely ambiguous choices, and can run bounded MCTS when multi-step consequences matter. Ships a CLI, MCP server and hook integrations.

MCP server that lets Claude Code, Cursor and other clients drive Chrome over the DevTools Protocol, exposing an accessibility-tree menu of stable refs. Its example Jev loop has Jev pick browser actions from that menu, and the README reports about a third fewer tokens and a quarter fewer tool calls in a blind benchmark.

Local code search for coding agents: ripgrep and BM25 shortlist function-level chunks, Jev Noul relevance questions run across parallel requests, and accepted excerpts return to Codex, Claude Code, OpenCode or Pi through MCP or the `oko ask` command.

Chrome MV3 extension plus a local MCP server exposing 50 browser tools; its chrome_act_toward_goal micro-loop uses TypeSafe Jev System One or a local decider to pick the next action on an 85%+ pruned, Shadow-DOM-pierced DOM tree, dispatching trusted CDP events in logged-in Chrome without stealing focus.

Evaluation scripts, MCP tools, and a skill router built to measure where jev-1.13.0 fits in agent harnesses, with raw results under eval/.

A local daemon that pulls open decision models and serves them on TypeSafe's /v1/systemone, so a Jev client switches hosts with TYPESAFE_BASE_URL.

A single-binary MCP tool named evaluate that sends Noul, Choice, and Score questions to hosted Jev or a local System One server.

Five typed tools — classify, check, score, rank, and ask — plus a skill, wired into Claude Code, Codex, Pi, and OpenCode in one setup command.

An MCP proxy and hooks adapter that screens an agent's tool calls before they run and the tool results before the agent reads them, with thresholds in a policy file.

A Python toolkit that puts Jev, Laya, or Cua-S1 at the center of browser, computer-use, robotics, and game agents, with a CLI and an MCP server.

Say the moment and get reaction GIFs: Jev picks a reaction and literal subjects, then scores a KLIPY shortlist of up to 30 candidates from titles and tags.

A git host for agents where every push and pull request gets a typed Jev review, every branch move a signed certificate, and sites deploy from a repo.

An MCP server for Antigravity IDE, Cursor, and Claude Code that uses Jev (jev-latest) to locate code semantically and audit git diffs, replacing broad grep sweeps of entire files.

Claude Code, Codex, and pi plugin plus MCP server and npm library that hands steps needing no text output to Jev: one batched call answers typed questions about a state, and an opt-in PreToolUse gate can only deny or ask.

Python MCP server that exposes classify, score, check, match, and screen tools to MCP-compatible agents, returning typed judgments over a closed answer set with token usage and latency. Ships generic triage and routing question examples.

A local-first MCP server that gives Claude Code, Codex, Cursor, and OpenCode structured quality scores from Jev across correctness, complexity, tests, security, and other dimensions while the agent writes code.

A Rust CLI and MCP server that reranks live DuckDuckGo SERPs with Jev and audits SEO/GEO readiness (schema, robots.txt, sitemaps, llms.txt) with a fifty-rule engine, no paid SEO subscriptions, and a local SQLite history.

Unofficial browser automation where the calling LLM states the outcome and Jev decides each element, action, and value from a Playwright page snapshot. Ships as a library, CLI, and MCP server.

A Rust CLI and stdio MCP server that grounds repository and crate discovery in live GitHub and crates.io metadata, then lets Jev score candidates so only verified, installable packages are returned.

A self-hosted, versioned skills library for AI agents with HTTP MCP, scoped client keys, and opt-in Jev recommendations that rank skills for a task using your own OpenRouter, TypeSafe, or Vercel key.

An unofficial Python CLI and stdio MCP server for Jev: send text or JSON state with typed questions and get machine-readable noul, choice, or score answers from the official API, OpenRouter, Vercel, or a proxy.

A hosted and self-hostable pull-request reviewer where Jev answers a Clean Code question set for each changed file and Luna writes the review from those answers; also exposed as a stateless Streamable HTTP MCP server.

A tool-call gate for Claude Code, Codex, Cursor, and other harnesses backed by Jev: deterministic rules and a read-only allowlist run first, then one request answers allow, ask, or deny in about 400 ms.

An ACP and MCP adapter that bridges TypeSafe Jev with any LLM: native Jev when TYPESAFE_API_KEY is set, or Codex, Claude, Grok, OpenCode, and OpenAI-compatible endpoints standing in as System One when it is not.

A self-hosted AI trading platform that can put Jev in front of strategy and Quick Trade entry orders as an auditable PASS/REJECT gate, with LLM fallback and deterministic bypasses for exits and protective orders.

A Python CLI that connects multiple robots under one contract with an optional Jev stepper: Jev picks among permitted discrete calls while an LLM writes poses and prose and the executor enforces safety gates.

A local SQLite memory layer for CLI agents with an opt-in Jev reranker that batches Noul judgments over the top 40 recalled memories and falls back to a local cross-encoder on errors.

Experimental Android sub-agent that gives Jev a bounded list of technically valid UI actions per step, with requirement-driven subgoals, durable SQLite tasks, confidence gates and escalation instead of coordinates.

An SO-101 workbench where an evaluation model or rules baseline picks bounded joint steps from typed candidate actions: decision runs are spend-capped via the Vercel AI Gateway and drive a real LeRobot arm or mock hardware.

A Rust CLI and MCP client for Forma benefit claims that can use optional Jev Choice questions to select from an account's valid benefit/category pairs, falling back to an LLM when Jev finds no match or is not confident.

A chat-shaped command bar where Jev picks the tool, arguments, confirmation, and reply type each turn, and code calls the MCP servers, so no LLM ever writes the reply text.

An open-source, local-first memory layer that captures session history across Claude Code, Cursor, Codex, OpenCode, Cline, and 20+ other harnesses, then has Jev judge bounded, redacted trace projections for reusable lessons a person reviews.

A lightweight, pluggable Java framework for CLI, HTTP, and modular applications that carries Jev, TypeSafe, and MCP-server topics; added from Maven as org.tinystruct:tinystruct and requiring JDK 17 or higher.

An MCP server and agent skill that verifies coding-agent work by driving the real running app and returning pass, fail, or couldn't-tell verdicts with the file:line to fix; its listing frames the approach as Jev-style machine-native runtime perception.

A selective awesome list of Jev projects, integrations, and resources: 241 entries each checked to actually call Jev, admitted at a 10-star bar, and paired with hands-on reviews at mrjev.com.

An open, local-first alternative to Jev that reproduces the Choice, Score, and Noul interface on commodity zero-shot NLI models with temperature scaling and conformal abstention, and runs offline with no API key.

A browser-use agent where Jev picks one action per step from a page's interactive elements. Runs as an MCP server, CLI, or library and returns a step trace, screenshot, and console errors.

An MCP server exposing ten Jev judgment tools, including verify, screen, find, rerank, classify, review, and gate, each returning typed probabilities in roughly 150 to 500 ms.

A single-binary Go MCP server exposing one evaluate tool for noul, choice, and score questions, with one-command registration for Claude Code, Claude Desktop, and Codex.

An MCP server that puts Jev in the coding loop for Cursor, Codex, and other MCP clients: coding-loop checks, ranking, verification, and review tools.

An open Python toolkit with question builders, confidence gates, tiered routing, a concurrent corpus evaluator, calibration tooling, a CLI, and an MCP server, with published benchmarks.