Skip to content
JevDirectory.orgTraffic count loading. View site trafficSponsor Us
Ecosystem

Local decision server

A process on your machine that answers typed questions from local weights, so the state does not leave the host.

All 132 terms
Category
Ecosystem
Also known as
—
Related terms
4
Directory entries
6
Docs
—
Added
2026-09-28

Definition

Local servers trade the hosted API's operations for a model you run. Ollaya pulls several open checkpoints. Rizzo Flow downloads a fine-tuned Spark model. Lichen and verdict read a GGUF through llama.cpp. jevos is a yes/no model aimed at a laptop CPU.

The state stays on the machine only if nothing else forwards it. Jeview is the opposite pattern: a local proxy that still calls TypeSafe. A local server also drops hosted rate limits and picks up your GPU, RAM, and license constraints.

Tagslocalopen-models

Related terms

Definitions that connect to this one.

Wire-compatible endpointA local server that accepts POST /v1/systemone and returns Choice, Score, or Noul answers in the documented JSON shape.EcosystemBase URLThe host a Jev client calls. Point it at a local System One server and the rest of the request stays the same.EcosystemLogit readoutReading the next-token probability of each declared label, then renormalising, so no answer text is generated.PatternsNoul-only modelA local decision model that answers yes/no questions and rejects Choice and Score instead of guessing a shape.API & Models

From the directory

Ollaya
702GitHub stars
A local daemon that pulls open decision models and serves them on TypeSafe's /v1/systemone, so a Jev client switches hosts with TYPESAFE_BASE_URL.
Models & Reimplementations#community#rust#open-models
Communityollaya-dev/ollayaRust
Rizzo Flow
689GitHub stars
A local server that reads next-token probabilities from a fine-tuned Spark model and returns Choice, Score, and Noul answers with zero generated tokens.
Models & Reimplementations#community#python#open-models
CommunityRizzo-AI-Academy/rizzo-flowPython
Lichen
39GitHub stars
A local /v1/systemone server that reads label probabilities from a GGUF chat model, with prompt repetition and a confidence shrink toward uniform.
Models & Reimplementations#community#python#open-models
CommunityMushroom-Systems/lichenPython
jevos
1.1kGitHub stars
A local yes/no decision model that speaks Jev's wire format on a laptop CPU, refusing Choice and Score until those question types ship.
Models & Reimplementations#community#python#open-models
Communityfeder-cr/jevPython
Jeview
59GitHub stars
A local gateway that forwards /v1/systemone to TypeSafe, stores each call in SQLite, and draws the calls on a live map.
Tools & CLIs#community#javascript#local
Communityandududu/jeviewJavaScript
verdict
7GitHub stars
A Python server in front of llama-server that reads one-token label probabilities and exposes them as POST /v1/systemone.
Models & Reimplementations#community#python#open-models
Communitykhimaros/verdictPython

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Arbitrary classification as a primitive

cocktail peanut
cocktail peanut
@cocktailpeanut
·

Jev is cool not because it re-invented classification, but because it makes ARBITRARY classification into a type-safe programmable primitive. A general purpose zero shot decision model whose native interface is RUNTIME-DEFINED typed decisions, optimized for that exact interface

Image
cocktail peanut
cocktail peanut
@cocktailpeanut

If you called Yann LeCun an idiot for saying we need to move beyond LLMs and build something new, you are banned from using Jev.

Reply
Read 13 replies

How Jev makes agents faster and cheaper

500 emails for 3.5 cents

Headless Chromium agent

Custom Jev-style models for agent workflows

Scott Williams
Scott Williams
@swill1ams
·

Prediction: millionaires will be made using custom Jev style models (parallel constrained decoding) to make the agent systems companies already run more token efficient. Let me explain with a scenario: Imagine a company already has an agent workflow running where an llm reviews Show more

Harsha Gundala
Harsha Gundala
@harshagundal

They were building in stealth for 2 years, I was building in stealth for 2 hours… Happy to open source Qwen-2.5-1B-RLCD, 5x faster on-device inference for JSON workloads that need to be type-safe. ⚡️Demo below on a M4 MacBook⚡️ every LLM has the ability to efficiently batch

Watch on X
Reply
Read 35 replies

Live viral post analyzer