jev-model

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)

A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.

Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync

Self-hosted Enterprise and Personal AI + agent runtime in .NET (NativeAOT-friendly)

Awesome list of TypeSafe AI Jev use cases: 74 demos ranked by likes, 150+ GitHub repos, limits, cost and API examples. CC0

AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.

Deep research tool for local knowledge base.

GoEventBus — high-performance event bus with a decision layer.

Open infrastructure for training, evaluating, and deploying System 1 decision models across language and multimodal backbones.

Open-source platform for creating, distributing and running sovereign EU-compliant LLMs. Verticalize any model for your domain, language and brand. AI Act ready.

A Bangla-focused adaptation of Laya for typed decisions, classification, and routing.

Filter your X.com feed with Jev or any LLM

A tiny jev-like model that answers Choice, Score and Noul questions in one forward pass and returns calibrated probabilities. MLX or PyTorch, fully offline, System One compatible.

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it tells you. Deterministic-first, tool-agnostic.

When Jev meets LLM -- Pair a small local LLM (System 2) with Jev model (System 1) to make small model more faster and accurate — OpenAI-compatible, private, and almost free to run in Kilo code and Cline.

Run Laya locally with Bun: native ONNX inference, a TypeSafe-compatible API, and a bilingual decision playground.

Cut LLM context and Claude Code sessions 40–80% without rewriting a byte. Offline, verbatim, with an audit receipt for every block dropped. CLI, MCP server and Claude Code/Open AI Plugin. MIT.

Curated Jev showcases from X, organized by category with media previews and direct source links.

Live TopstepX bot trading on futures, AI-graded entries (Chronos+XGBoost) with a PPO-learned trailing-stop exit.

Natural-language constraints for JEPA world-model planning, judged by a decision model instead of an LLM.