Docs
CommunityJev Guides & Articles
Ollaya Documentation
Ollaya's documentation index for its local decision-model runtime: quickstart, the full CLI reference from run to mcp, native and TypeSafe-compatible API endpoints, Modelfiles, and MCP plus agent-skill guidance.
- Format
- Docs
- Reading time
- 2 min
- Published by
- Community
- Last verified
- Oct 2026
- Capabilities
- Self-hostedRuns locally
Highlights
- Documents the CLI surface: run, pull, serve, list, ps, show, stop, rm, cp, create, preset, update, and mcp.
- Covers native /api endpoints and TypeSafe-compatible /v1 endpoints, including errors, streaming, and limits.
- Modelfile bakes a question set, calibration, precision, and license into a model you can run by name.
- The TypeSafe compatibility page runs the official SDK against local, open models by changing environment variables.
- An MCP server targets Claude Code, Claude Desktop, and Cursor, with an agent skill teaching when and how to use it.
Watch out
Grounded in the documentation index page captured on 2026-10-15; the individual docs pages behind it were not captured, so this entry describes the documentation map rather than exact commands, and runtime licensing and model sources are covered on pages not reviewed here.
Questions about this entry
Short answers drawn from the linked project or page.
It downloads and serves open decision models locally: a model reads a state such as text, an email, a ticket, or JSON plus typed questions, and returns typed answers with calibrated probabilities in a single forward pass, never generating text.
A quickstart, a CLI reference, a native API reference, TypeSafe compatibility, Modelfile documentation, an agents section for MCP and skills, and an FAQ about Ollama, hardware, privacy, weights, and licensing.
Yes. The TypeSafe compatibility page says you can use the official TypeSafe SDK and existing code with local, open models by changing environment variables, so current calls keep working against the local server.
Run, pull, serve, list, ps, show, stop, rm, cp, create, preset, update, and mcp, covering pulling models, serving them, managing instances and presets, copying and removing models, and starting the MCP server.
A file that bakes a question set, calibration, precision, and license into a model you can then run by name, so a recurring decision task becomes a locally callable model rather than an ad-hoc request.
Yes: the docs describe an Ollaya MCP server for Claude Code, Claude Desktop, Cursor and other clients, plus an agent skill that teaches the agent when and how to use local typed decisions.
The FAQ covers where weights come from and how licensing works, but those pages were not part of the capture, so this entry does not state the sources. The docs index only promises an explanation.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev in front of the HeyGen MCP
X: Playwright CLI + Jev vs Playwright MCP
X: A local MCP server that cuts computer use from 23s to 0.8s. Cartwright built Cortex, a local MCP server where…
X: A side panel that drives any site's WebMCP tools
More Jev resources like this
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.
Jev Models & Reimplementations#community#rust#open-models
Community
ollaya-dev/ollayaRust
ollaya-dev/ollayaRustA desktop app for dictation, audio-file transcription and meeting notes on Windows, macOS and Linux, using local Whisper models or the OpenAI API, with an opt-in MCP server and local history API so agents can search saved transcripts.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
knuckles92/openwhisperPython
knuckles92/openwhisperPythonA local, open-source personal AI assistant for your job: mail, chats and tickets become tasks, agents you already use such as Claude Code, Codex and Gemini do the work, and nothing is sent until you approve. The current release is v0.3.8.3.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
ldbumble/taskuaryPython
ldbumble/taskuaryPythonA 144.3M-parameter bilingual typed decision model fine-tuned from jhu-clsp/mmBERT-small: it answers noul, choice, and score questions in one forward pass with calibrated confidence and zero output tokens, and it runs on CPU.
Jev Models & Reimplementations#community#catalog-import#cobanov
A native Swift implementation of OpenJev, the Jev-compatible typed-decision server: send a state and typed questions over a Jev-compatible HTTP API and read every answer from model probabilities, on Apple silicon Macs or inside iPhone and Mac apps.
Jev Repos & SDKs#community#catalog-import#cobanov
Community
algorythm-canada/openjevswiftSwift
algorythm-canada/openjevswiftSwiftThe Go server, agent CLI and MCP for Laya - open horizontal System 1 decision models that score structured features and return ranked pattern probabilities instead of text. It ships a JEV compatibility API and a migration guide.
Jev Repos & SDKs#community#catalog-import#madewithjev
Community
neko233-com/laya-goGo
neko233-com/laya-goGoFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.