System One 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.

shad0wllm

System 0 for your LLM: learns the fixed-choice answers your LLM gives (intents, routing, moderation) and serves the repeats in microseconds from a small CPU table, at most 5% disagreement, certified. Zero-code proxy for the OpenAI Decisions API, System One and chat models.

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.

decision-circuits

Decision circuits: typed questions to a System One model, calibrated probabilities back, gates in code. Zero-dependency Python SDK with LangChain, OpenAI Agents, and Claude Agent SDK integrations.

semantic-operators

An abstraction for System One models, currently supporting TypeSafe's Jev and Laya. Typed questions, probabilities, and "don't know" instead of a guess, from Python, the command line, or MCP

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

l2s1-sdk

jev-style adaptor for llama.cpp interface

pydecide

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

jev-mcp-server

MCP server for Jev (TypeSafe System One): the three official question types — choice, score, noul — plus batch classify. Calibrated probabilities, ~0.5s, <$0.001/call.

laya-mcp

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

stuntd

Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

opendxp

NoulXP (formerly OpenDXP): the open standard for System One models. Package an AI decision model once, prove it, calibrate it, run it anywhere over HTTP or MCP.

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.

system-one

Vendor-neutral SDK for typed decision-making (yes/no, choice, score) — hosted and local

jevlint

A linting tool combining static analysis and Jev queries to help improve... Jev queries

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.

fastjev

SDK-first, independently maintained SemIf fork for fast, self-hosted semantic decisions.

makoto-decision

Decision like hanuma makoto

laya-finetune

Fine-tune Laya, the open System One decision model, for any typed-decision task: synthetic data, RLCD, calibration and long context.

thinkthen

ThinkThen: code that knows what you mean

jevshield

Sub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev (System-1) decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready.