Launches on September 19, 2026

Near-instant generative UI for Telegram bots, powered by JEV.

very first hands on jev, foundation models by typesafe

Use Jev to quickly search your old hard drives and identify anything of value.

Haskell client for TypeSafe's System One (Jev) decision API — typed, batched Choice/Score/Noul over http-client

INSTRUCT_JEV - TypeSafe AI Jev / System One instruction corpus (choice/noul/score), compiled by DeckerGUI. 119 rows. Mirrored on HuggingFace.

JEB: a System One-compatible decision model API. State + typed questions in, calibrated probabilities out, one forward pass.

Mini benchmark of TypeSafe's jev-1.13 structured decision model (OpenRouter Decisions API) on labeled support-triage: noul/choice/score, consistency, cost, lessons learned

Reproducible evaluation of TypeSafe Jev on all 58,492 BBQ questions: accuracy, stereotype bias, uncertainty, cost and latency.

Claude Code plugin: a 3-cent bouncer for your agent's shell. Jev typed probabilities auto-allow routine commands, deny destructive ones, and flag prompt injection in tool results.

Give any MCP-capable LLM harness an on-demand real-browser search tool (TypeSafe Jev) with per-run timing and cost tracking.

CI example using Jev to classify failed PR checks and return structured decisions with probabilities.

Local, contract-compatible System One decision server (typed questions -> calibrated probabilities, zero generation). Independent reimplementation; not affiliated with TypeSafe.

Context compaction and safety gating for AI agents via TypeSafe Jev: keeps messages verbatim, no summarization. OpenAI, Anthropic, LangChain, CLI, MCP.

Jev learns your repo's decision norms, then adversarially judges past decisions against them. Unix-style primitives (seed, expand, judge, verify, report, norms) with per-node typed judgments from typesafe-ai/jev.

Real-time hawk-or-dove analysis of Fed press conferences with TypeSafe's Jev vs chat models. Live at fedspeech.pages.dev

Recursive FOLIO document classification with TypeSafe Jev

TypeSafe Jev 1.13 vs Claude Fable 5.1, GPT-6 Astra, Kimi K3, MiniMax M3 and DeepSeek V4.1 Flash on 200 typed decisions: accuracy, calibration, agreement with 100 human annotators, latency and cost

TypeSafe Jev arcade

TypeSafe.ai Jev Go SDK

A safety boundary for AI-assisted Home Assistant decisions, with explicit policy checks and deterministic state verification.

MCP server exposing TypeSafe's Jev as a judge tool: typed judgments with calibrated probabilities, for any MCP client.

Hands-on research lab for TypeSafe's Jev (System One model): reproducible benchmarks of Noul/Choice/Score primitives, confidence gating, fan-out latency, agent control — plus a living audit of the Jev ecosystem.

A hands-on lab for Jev, TypeSafe's System One model — AI decision trees, guardrails and routing with typed answers instead of text

Never confidently wrong: a TLA+-verified consensus kernel around TypeSafe's Jev, run through 1,680 chaos-tested pharmacy decisions with zero wrong verdicts. Film, code, and every captured call.

Give your Jev language, i'm not finish now

Jev decides whether a batch of logs is worth acting on. Typed questions, confidence gates, nothing executed.

AI defect code suggestions for Non-Conformance Reports, powered by TypeSafe AI's Jev model

A vocabulary-driven TypeScript runtime for safe, stateful applications powered by TypeSafe AI Jev.

Does ORDER BY over a Jev probability put rows in a defensible order? Independent ranking, calibration and invariant measurements of TypeSafe AI's Jev: passes six pre-registered gates on 360 labeled rows, fails four of six on graded product relevance.

Evidence-gated registry of Jev question packs — curated questions, golden cases and measured evidence for Jev-compatible decision endpoints

Chrome extension that asks Jev whether the page you are on is selling something or reporting first-hand experience, and marks Google results with verdicts it already has or snippet-only estimates, leaving low-confidence ones undecided.

Score every file in a pull request with Jev (TypeSafe System One) and decide in code whether it can merge itself. Shadow mode: comments, never merges.

A WebGL demo where you play the card game Speed against a CPU whose brain is TypeSafe AI's Jev. The whole point of the app is to measure and show Jev's decision speed and decision accuracy in real time.

7 projects built with TypeSafe Jev — dev tools and games

Ingress LLM firewall: a reverse proxy that screens each request with one batched TypeSafe Jev System One call for jailbreaks, indirect injections, and data exfiltration before an expensive model runs

Jev (TypeSafe AI) 可复现实测：算术、计数、日期、零幻觉、把握度校准，中英对照

Is this Jev question safe to build on? A swamp extension that measures repeatability, framing sensitivity, resolution and answerability of TypeSafe System One questions — with the preregistered study and raw data that produced it.

TypeSafe Jev (System One) 简历-JD 匹配度初筛：判据模板 + 正/负/陷阱三类样本测试档案，判据 v1→v3 迭代全程可复现 / Resume-JD screening with TypeSafe Jev: atomic questions, calibrated criteria v1→v3, full reproducible test archive

Per-prompt model routing for Pi, driven by Jev (TypeSafe System One)

Test bench for TypeSafe's Jev

Pre-registered benchmark: can a 2B local model (Gemma 4 E2B) answer web questions without making things up when a decision model (TypeSafe Jev) makes every call? SearXNG for search, MemPalace for verbatim memory, seven arms including open local judges. Spec and thresholds fixed before any run.

A 3D town where 50 AI citizens each decide how to react to your broadcast, in parallel, in under a second - powered by TypeSafe's Jev decision model.

Unofficial developer notes & examples for Jev, TypeSafe AI's System One model. Try it free: jevtypesafeai.com

Jevaluate: evaluate before you trust. Field notes, runnable scripts and an agent skill for TypeSafe Jev: gated evals, a browser loop, a product walk with DeepSeek vision, a UI text judge and a first-click tree test. Co-authored with Claude Fable 5.1.

One MCP tool that returns the files a coding agent should read.

AI detection in research papers with Jev

Instant semantic code search: local ripgrep shortlist, meaning-ranked by TypeSafe Jev via OpenRouter.

Jev-like model inference engine + Jev-compatible API

Run Flutter integration tests using natural language with TypeSafe.ai's Jev

Computer use with TypeSafe Jev: control your PC, browser, games and Android phone with a prompt