All decision model projects

P(DOOM) Protocol: co-op browser platform shooter where TypeSafe Jev plays alongside the user.

Experiment testing how well Jev predicts financial markets; the author reports it does not do well, like most LLMs.

Side-by-side comparison of Jev and DeepSeek-flash on speed, tokens, cost and accuracy for extraction, classification and reranking.

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

herdr plugin that lets a decision model play Caves of Qud, and later any Steam game, from inside a herdr pane.

Drives ego-browser pages with Jev: code builds the allowed actions, Jev picks one, and code acts and re-checks.

Go event bus whose optional routing layer asks Jev a Choice to pick an event projection only for ambiguous cache misses.

Repository titled System One Models and Jev, with no README available to describe its contents.

Xano template for an agent tool-call guardrail in which Jev decides and Xano enforces.

Android chat copilot: Jev judges intent, needs and risk in visible chats, then ranks drafted replies to fill, never send.

Repository on a direct approach to Jev-style models using Reinforcement Learning for Calibrated Decisions (RLCD).

AI decision reliability control plane that evaluates autonomous agent actions with Jev before they run.

Drives a phone with Jev choosing each action while the phone-use runtime executes it on iOS and Android.

Single-tool MCP server that acts as a code-review gate powered by TypeSafe Jev.

Repository and Rust crate search tool that asks Jev to score and select retrieved candidates for a request.

Claude Code and Codex skills powered by Jev, published with a calibration curve measured on 4,995 real agent decisions.

Minecraft mod in which Jev tries to finish the game from scratch without a scripted route.

Project premised on offloading cheap routing decisions from an LLM to a decision model while the LLM writes, tests and revises.

High-frequency trading bot in Rust that uses Jev as its decision maker, per its one-line description.

Vercel AI SDK for TypeScript, whose TypeSafe provider lets apps call Jev through a shared evaluate interface.

TypeSafe's official Jev documentation: concepts, primitives, HTTP API, patterns, cookbooks and SDK references.

Netlify AI Gateway support for TypeSafe Jev: call @typesafe-ai/sdk from Netlify Functions with Netlify handling keys and billing.

Vercel AI Gateway model page hosting Jev as typesafe-ai/jev for AI SDK evaluate calls, with no TypeSafe waitlist.

OpenRouter's catalogue of decision models from several publishers behind its alpha Decisions API, with an agent-skill usage guide.

Official Vercel AI SDK provider @ai-sdk/typesafe-ai for calling Jev as an evaluation model with experimental_evaluate.

TypeSafe AI's GitHub Pages repository; no description or README was published.

Dependency-free TypeScript SDK that turns Jev answers into named decisions with hysteresis thresholds, journaling and replay.

Educational site with six bounded recipes and a custom builder for AI SDK Choice, Score and Boolean evaluations, exportable as TypeScript.

Python trust middleware for the Jev API that logs decisions, measures calibration from your recorded outcomes and signs the evidence.

TypeSafe SDK for the Godot 4.7 game engine, described as at parity with the Python SDK and HTTP API.