Browse builds

Evaluation framework for detecting AI hallucinations and instruction-following failures with Jev.

Connector for integrating TypeSafe Jev decisions into application workflows.

Local Paseo plugin that exposes Jev evaluations through MCP.

Adds jev(), jev_prob, jev_choice, and jev_score to vanilla PostgreSQL queries through a psql-shaped CLI and Go, TypeScript, and Python SDKs.

JSON-in, typed-decisions-out CLI for the TypeSafe System One API.

A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model.

Pi extension: verbatim context compaction with TypeSafe Jev decisions.

Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.

AI workspace whose approval review uses Jev to gate workspace actions with typed decisions.

Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.

Typed System One decisions, ranking, verification, and an opt-in Hermes tool gate using TypeSafe Jev.

Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter.

Prompt-injection and dangerous-action guard for coding agents (Claude Code, Codex, pi, ACP), powered by Jev.

Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

A claude code plugin for jev.

Command-line tool for TypeSafe's Jev AI model.

Grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.

Scans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it.

Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell.

Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into Compozy.

MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client.

Proof of concept MCP for Typesafe's new Jev AI model.

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

A staged code-review workflow and local dashboard built with TypeSafe Jev.

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.

Jev adapter to Mellea.

Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes.

Home Assistant integration for TypeSafe Jev. Ask a question about your house and get a probability, a choice or a score as an entity.

Fish-style zsh history autosuggestions ranked by Jev (TypeSafe).

Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.

Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.

Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results.

Open, Jev-compatible System One decision server on DiffusionGemma.

An integration with jev by typesafe.ai in Rust.

Rust client for the TypeSafe System One API (Jev).

PHP & Laravel SDK for TypeSafe AI's JEV Model series.

Unofficial Go client for TypeSafe's System One API and its model, Jev.

Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.

Go client for TypeSafe AI's System One API (Jev), with optional Langfuse instrumentation.

Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers.