Jev solved local harness/model routing I use a combination of Claude Code, Codex and Opencode as my local agentic stack and routing to other harnesses was always enforced in the system prompt/rules With a deterministic hook that Claude Code can decide before delegation, Jev Show more
Patterns
Logit readout
Reading the next-token probability of each declared label, then renormalising, so no answer text is generated.
- Category
- Patterns
- Also known as
- —
- Related terms
- 4
- Directory entries
- 3
- Docs
- —
- Added
- 2026-09-28
Definition
Lichen, verdict, and Rizzo Flow all answer by scoring label tokens in one forward pass. Lichen lists options twice in rotated order and shrinks confidence when the two readings disagree. Verdict keeps the probability mass that landed on the labels before renormalising, because a tiny mass can still rank options after it is scaled to 1.
The mechanism is not Jev's. These projects say so. Output tokens in their sample responses are zero. Accuracy and calibration still depend on the GGUF you loaded and on any temperature or shrink you fitted.
Tagspatternsopen-models
Related terms
Definitions that connect to this one.
Local decision serverA process on your machine that answers typed questions from local weights, so the state does not leave the host.EcosystemWire-compatible endpointA local server that accepts POST /v1/systemone and returns Choice, Score, or Noul answers in the documented JSON shape.EcosystemProbability distributionThe floats summing to 1 across your options or levels that every Choice and Score answer returns under probabilities.Answers & ConfidenceGeneration limitationJev is not trained to generate text; forcing it by chaining choices is slow and unreliable, so extraction becomes a Choice instead.Evaluation & Training
From the directory
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
Community
Mushroom-Systems/lichenPython
Mushroom-Systems/lichenPython7GitHub 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
Community
khimaros/verdictPython
khimaros/verdictPython689GitHub 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
Community
Rizzo-AI-Academy/rizzo-flowPython
Rizzo-AI-Academy/rizzo-flowPythonFrom the community
Posts from builders shipping with Jev right now.
How Jev makes agents faster and cheaper
500 emails for 3.5 cents
Yeah Jev by @typesafeai is very cool. It classified 500 emails in seconds. And it costed 3.5 cents.
Headless Chromium agent
Acabo de terminar la implementación de @typesafeai + Chromium Headless para que mis agentes puedan navegar por internet a una buena velocidad! En este ejemplo le pido al agente que entre a la página del término "Café" en Wikipedia y navegue por los hipervínculos hasta terminar Show more
Tremendo esto!! Voy a trabajar en una implementacion propia.
Custom Jev-style models for agent workflows
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
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
Live viral post analyzer
Just created this with Jev by @typesafeai. A live viral post analyzer. As soon as you stop typing for .5 seconds it analyzes the viral potential. Going to try and actually make this good, will need to scrape a lot of twitter data... Notice how it also categorizes the tweet Show more
Jev plays Tetris: 134 lines in two minutes
Puse a Jev, la nueva IA de @typesafeai, a jugar al Tetris en modo súper difícil. Decidió cada jugada en unos 0,3 segundos. Acomodó 357 piezas e hizo 134 líneas en solo 2 minutos. Increíble.