Skip to content

Ollaya

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.

Category
Models & Reimplementations
Format
—
Published by
Community
Author
ollaya-dev
Added
2026-09-28
Last verified
2026-09-28

Highlights

  • POST /v1/systemone and GET /v1/models match TypeSafe when TYPESAFE_BASE_URL is http://localhost:11435.
  • Publishes small ONNX graphs and reads author weights from Hugging Face, pinned and checked by sha256.
  • winnow:e4b is listed at 0.722 on typed decisions against Jev's 0.738, and 89 ms for five questions on an RTX 4090.
  • fp32 exports matched the PyTorch reference on 100% of 2,383 questions per checkpoint.
  • ollaya mcp exposes the same models to Claude Code, Claude Desktop, and Cursor.

Quickstart

bash
curl -fsSL https://ollaya.dev/install.sh | sh
ollaya run laya "Third time this year you've double-charged me."

Watch out

Apache-2.0, and each model keeps its own license. Not affiliated with Ollama or TypeSafe. GGUF models need llama.cpp; CPU users are pointed at laya.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

Related terms

Glossary definitions related to this entry.

More like this

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
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
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

From the guides

Original write-ups that draw on this entry.

A base URL is the whole client change. What still works when Ollaya, Lichen, verdict, Rizzo Flow, or jevos answers POST /v1/systemone on your machine.
Models & Reimplementations#open-models#local#api
Read article
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

LLM-as-a-judge, sped up

Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)

Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Reply

Instant compaction with Jev

A Claude session from 1M to 86K tokens

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be  Show more

Image
Image
tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Reply

Vercel's fx safety reviewer, 18x faster

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply

Jev lands on OpenRouter

700 leads scored for $0.09