Decision Model Python Packages

laya-mlx

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

von-sdk

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

opendecider

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVIDIA, Apple Silicon, LM Studio, Ollama and vLLM.

laya-coreml

Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.

anyjev

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

edgejev

离线可用的本地类型化决策：4 核 CPU 单题 15.6ms。Local & offline Jev / System One inference on CPU — ONNX + INT8, no torch at runtime. 支持 laya / kev / PlayJev

jev-browser-pilot

A bounded decision layer for browser and desktop automation: a decision-only model picks one next step; the code owns perception, content, actuation and verification.

pydecide

One client for every decision model: Choice, Score and Noul over Jev, OpenRouter, laya, MLX, CrossEncoders and LLM fallback

laya-mcp

MCP server for Laya typed decisions (noul / choice / score): warm model sidecar, token-budget preflight, persisted calibration, honest confidence.

decision-tune

DecisionTune 1.0: a 395M decision model. Pick an option or get P(yes) with one encoder pass. PyTorch, MLX, ONNX. Apache-2.0.

jev-style

Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.

typecastlm

Use TypeCastLM decision models: ask questions about your material, get calibrated probabilities — locally, via llama.cpp, or as a Jev-API server. pip install typecastlm

tinyjev

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.

opendecider-client

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVIDIA, Apple Silicon, LM Studio, Ollama and vLLM.

oev

An 184M-parameter decision engine delivering calibrated distributions from one 22ms forward pass while matching models 2.3x its size.

wev-ai

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisions and browser-agent steps.

simthinkd

A tiny decision model (265k parameters) that picks one action in about 2 ms on one CPU core, inside real-time loops.

ruhui

Multilingual, non-autoregressive System 1 decision model.

ollajev

Run System One decision models from Hugging Face locally behind the Jev / System One API, Ollama style

rev-decision

A fast, local decision engine. No decoding loop, no free-text parsing, just calibrated choices.

clef-router

Route prompts between cheap and frontier LLMs with Cloudflare's Clef decision model. OpenAI-compatible proxy + library.

toolhunch

Your agent has too many tools. Hybrid search + a fast decision model (Jev, Laya) or an LLM pick the right one, or say "none". Pydantic AI integration and a ToolRet benchmark.

sokudan

Japanese System One decision model (Jev-style): typed answers and probabilities in one forward pass, no text generation. Includes bench_ja/bench_en and a Laya position-bias repro.

unee

Unee: a small open AI model that decides and chats, on your own hardware or in the browser.