Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
-
Updated
Sep 20, 2026 - Python
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.
Super fast Jev like server, model agnostic, working with any OpenAI compatible endpoint
OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI.
Local multimodal decisions on your Mac. Jev-compatible typed probabilities with Qwen, llama.cpp and Metal.
Local multimodal decisions on your Mac. Jev-compatible typed probabilities with Qwen, llama.cpp and Metal.
MCP server exposing TypeSafe's Jev through the public OpenJEV API. Send one shared context and several independent questions; get typed judgments and probabilities back — choice, score, or yes/no — not prose. Built for DeepSeek Harness; runs unchanged in any MCP client.
Sub-10ms calibrated semantic decision engine & runtime for edge, embodied control, agent simulation, and typed dynamic workflows.
Open-source Jev harness for TypeSafe, OpenJev, LocalJev, Ollama, vLLM, LM Studio, llama.cpp. Typed decisions, calibration, verification, abstention, CI gates.
Bounded semantic routing with Jev and Poise. Rust, single-server, alpha.
Typed, probabilistic decisions (Choice / Score / Noul) for System One tasks, powered by TypeSafe Jev, with OpenAI and Anthropic as alternative engines
Adding SystemOne APIs like Typesafe Jev to home assistant
A pre-execution gate for AI agent actions, powered by TypeSafe's Jev (System One) model.
A bounded Jev System-1 browser tool for Pi, OpenCode V2, Amp, and MCP, powered by agent-browser
Jev 决策的 Record / Replay 工具:CLI + 本地代理 + JSON 磁带,回放彻底离线。
Claude Code plugin that scores how well you prompt a coding agent, and shows whether your habits are improving. Runs on TypeSafe's Jev model. Zero added latency.
To associate your repository with the openjev topic, visit your repo's landing page and select "manage topics."