AaabolfazlBenchmarks & research

typesafe-local

Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.

Explore repository

How it uses Jev

TypeSafe shipped a model that returns typed decisions instead of prose, and the idea was interesting enough that I wanted to know how much of it comes from the model and how much from the way it is served. So I built one, on top of an off-the-shelf local model, and measured it.

Getting started

The model ( 1.1 GB) downloads on first run into .hf cache/ inside this folder . ./cleanup.sh --yes removes everything; nothing is written elsewhere.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to typesafe-local

Browse all
jevmlx project preview

jevmlx

Benchmarks & research
Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.
BMade bybnsd5560
jev-visual project preview

jev-visual

Benchmarks & research
An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.
HMade byhr98w271
open-jev (daseinlabs) project preview

open-jev (daseinlabs)

Jev alternatives & open source
One-pass option scoring with a local Gemma 3 4B on Apple silicon via MLX, inspired by jevlike, with a Doom demo.
DMade bydaseinlabs107
agent-jev project preview

agent-jev

Benchmarks & research
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.
MMade bymalevrigns286
system-one (mpuig) project preview

system-one (mpuig)

Jev alternatives & open source
An open-source System One decision model — Kahneman's term for the fast, automatic judgment faculty. Calibrated choice/score/noul probabilities in one forward pass on small fine-tuned open models. Local on Apple Silicon (MLX), Jev-compatible API, audited experiment log.
MMade bympuig1
system-one-gemma project preview

system-one-gemma

Jev alternatives & open source
Open-source Jev-style System One decision model. Gemma 3 270M with a scoring head — fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev.
AMade byakash-kamat4
TypeSafe.Jev project preview

TypeSafe.Jev

SDKs & clients
Typed AI decisions for .NET: ask Jev (TypeSafe AI System One) yes/no, choice and score questions and get a C# enum with calibrated probabilities back.
RMade byRavenValentin1
SystemOneDotNet project preview

SystemOneDotNet

SDKs & clients
.NET client for TypeSafe System One (Jev) — typed questions in, typed answers with probabilities and confidence out. No prompt engineering, no output parsing.
JMade byJabbaKadabra3
A home that understands project preview

A home that understands

Integrations
Turn the state of your home into typed decisions, sensors, and smarter automations.
AMade byAboveColin58