Launches on September 18, 2026

Experimental Pi extension using TypeSafe Jev for auditable tool-history compaction

TypeSafe Jev (System One judgments) for Pi: zero-dependency jev_ask tool with question linting, model discovery, and budget caps

High-concurrency Elixir actor runtime for large-scale semantic graphs, search swarms, and batched model evaluation.

Natural-language PostgreSQL predicates with TypeSafe Jev. A simple search playground with randomly generated databases.

Ask the Potpie docs a question, get the exact paragraph that answers it. Extractive search powered by Jev (TypeSafe System One) — no LLM, no embeddings, nothing generated.

Vite demo: TypeSafe Jev checks whether text contains profanity

An MIT-licensed public-radio assignment desk using NPR CDS MCP and TypeSafe Jev for editorial discovery, review, and audio workflows.

Black-box QA of saucedemo.com, judged three ways: TypeSafe Jev, GPT-5.6 with screenshots, and a confidence-gated hybrid.

Built a new SALT RSS pipeline that can do tellurics and such.

Synthetic smoking-history extraction benchmark comparing TypeSafe Jev and OpenAI structured outputs, with reproducible accuracy, cost, and latency results.

Natural-language speculation gates for speculative programmatic tool calling (spec-ptc), judged by TypeSafe Jev

Rust client for the TypeSafe AI systemone API

A Minecraft agent with no LLM in the loop: code owns the plan, TypeSafe's Jev decision model supplies per-tick judgment

Mine quotable user praise from Gmail with TypeSafe's Jev: one typed request per email, verbatim quotes, thresholds in code

Watch TypeSafe Jev play Tetris. Live API vs offline heuristic, with recorded demos and reproducible runs.

Deterministic transcript cleanup and compaction support using TypeSafe's Jev.

Typesafe switch, score, and bool primitives for Python, powered by TypeSafe AI

Pure Go 1.27 SDK for TypeSafe AI: typed decisions, context-aware retries, and zero dependencies.

Jev (TypeSafe's decision model) plays Super Mario Bros, Contra, and Mega Man through stable-retro. Typed judgments in, buttons out; every decision logged.

Automation Anywhere custom package wrapping the TypeSafe (Jev) API for typed yes/no, categorical, and scored-scale text evaluation.

Community SDK for Typesafe.ai in Go

Go client for the TypeSafe AI API. Ask typed questions, get calibrated probabilities your code can act on — with a fake server to test against.

Idiomatic, strongly-typed Go client SDK for the TypeSafe AI System One API (v0.6.0)

A typesafe.ai client written in golang

Demo pública: mensaje → juicios TypeSafe (Choice/Noul/Score) vs decisión en código. Spec: Notion TypeSafe triage.

UiPath bring-your-own-guardrail connector backed by the TypeSafe Jev System One model: plain-language agent policies enforced as calibrated probabilities.

Universal TypeSafe Jev Runtime Plugin & MCP Server for Coding Agents

ocaml sdk for typesafe.ai's jev model

Werewolf against seven villagers whose suspicions are calibrated probabilities from TypeSafe Jev