Ollaya logo

Ollaya

Expose locally hosted open decision models to MCP clients for routing, triage, guardrails, and tool approval.

Install Ollaya

Run the project’s own setup commands, in order.

Setup steps from the project

ollaya installs with its own commands rather than a config we can generate, so these are copied as-is. Run them in order in a terminal. Source: github.com

  1. 1. Install
    curl -fsSL https://ollaya.dev/install.sh | sh
    

Overview

ollaya MCP server exposes open decision models running on local hardware or a self-hosted machine to Claude Code, Claude Desktop, Cursor, and other MCP clients. It runs through the `ollaya mcp` command and lets agents obtain typed, calibrated decisions instead of generated text. Models can answer questions over messages, tickets, emails, JSON, and supported images. Reach for it when an agent needs fast local classification, routing, safety checks, or tool-approval decisions without sending data to a hosted service.

Use cases

  • Route incoming requests to the appropriate team
  • Triage support tickets locally
  • Apply guardrails before an agent takes action
  • Approve or reject tool calls with typed decisions
  • Classify multilingual messages without a hosted LLM call

Key features

  • MCP access to local open decision models
  • Typed choices, scores, and calibrated probabilities
  • CPU, CUDA, Metal, Vulkan, and ROCm/HIP runtime paths
  • Language-aware Laya routing
  • Custom Modelfiles and question sets
  • Jev-compatible TypeSafe API

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1.5kStargazers on the source repository.
Last commitTodayMost recent push to the default branch.

How Ollaya works

What ollaya does

ollaya runs open decision models locally and makes their outputs available through MCP. These models inspect a state—such as a message, ticket, email, JSON object, or, for supported models, an image—and answer typed questions. Supported question types include choices, scores, and yes-or-no-style decisions. Results are calibrated probabilities returned in a single forward pass rather than generated prose.

The MCP interface is intended for agents that need a decision layer for routing, guardrails, triage, and tool approval. Running locally keeps the input on the machine or self-hosted server. The project includes multiple model families, including Laya, Winnow, Kev, Decider, NLI classifiers, GLiClass, and Qwen3Guard.

How it works

Start the Ollaya daemon and expose it to an MCP client with:

sh
ollaya mcp

The client launches the command as an MCP process, while Ollaya loads and serves the selected local model. Models are downloaded by name and can be managed with the Ollaya CLI. The daemon can also start automatically when a CLI command needs it.

Ollaya models use small ONNX graphs that reference the original weight files hosted by their authors. Model sources are pinned to commits and checked with SHA-256 verification. Some families, including Winnow, JevK5, and Jeb, run author-published GGUF files through llama.cpp instead.

The runtime supports CPU execution through ONNX Runtime, CUDA for NVIDIA GPUs, and several llama.cpp backends for GGUF models, including CPU, AMD ROCm/HIP, Windows Vulkan, NVIDIA CUDA, and Apple Metal. laya can select an English or multilingual model based on the request language.

Setup and configuration

Install the Ollaya binary using the project installer, then download a model and start the MCP process. A typical local setup is:

Terminal
curl -fsSL https://ollaya.dev/install.sh | sh
ollaya pull winnow:e4b
ollaya mcp

Configure Claude Code or another MCP client to run ollaya mcp. Cursor provides an installation option, and the project documents the equivalent MCP command for other clients.

The CLI also supports run, pull, list, ps, show, rm, cp, stop, and create. A Modelfile can package a question set into a named model. For example, a model can be built from a base model and a local QUESTIONS file, then started with ollaya create and ollaya run.

Tools and capabilities

  • Serve local open decision models through MCP.
  • Answer typed choice, score, and yes-or-no-style questions.
  • Process text states and supported image inputs with compatible models.
  • Route requests between English and multilingual Laya variants.
  • Run safety, intent, triage, and classification decisions locally.
  • Calibrate a model on labelled JSONL examples and write calibration settings for a Modelfile.
  • Expose a Jev-compatible HTTP API at /v1/systemone, /v1/decisions, and /v1/models for TypeSafe SDKs and existing Jev clients.
  • Provide native HTTP endpoints such as /api/decide, /api/pull, /api/tags, /api/show, and /api/ps.

Limitations and notes

Ollaya models do not generate text; they return decisions and probabilities. Model capabilities vary: for example, multilingual support, image handling, context length, and question behavior depend on the selected model. The recommended Winnow model is a 4B-class model that benefits from an NVIDIA GPU, while laya:multilingual is intended for CPU use.

Ollaya does not re-host model weights. It retrieves the required author-provided files from their Hugging Face repositories, while publishing the small model graphs needed to run them. Model performance and calibration can differ by model, device, quantization, and media type.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Ollaya

ollaya is an MCP server that connects MCP clients to open decision models running on your own machine or server. Its main capability is exposing those models for typed decisions such as routing, guardrails, triage, and tool approval, with calibrated answers returned without an LLM text-generation call.

Install Ollaya with `curl -fsSL https://ollaya.dev/install.sh | sh`, then configure your MCP client to run `ollaya mcp`. You can pull a model first with `ollaya pull MODEL`; the daemon can also start automatically when a CLI command needs it.

Yes, ollaya works with Cursor through its MCP server command. Configure Cursor to launch `ollaya mcp`, or use the project’s Cursor installation link to add the server.

Yes, Ollaya supports CPU execution. ONNX models use CPU inference, and the project recommends `laya:multilingual` as a CPU-friendly option; GGUF models can also run through llama.cpp on CPU.

Yes, Ollaya provides a Jev-compatible API. Set `TYPESAFE_BASE_URL` to the local Ollaya address, provide any non-empty `TYPESAFE_API_KEY`, and choose an open model with `TYPESAFE_DEFAULT_MODEL`.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewOllaya AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/ollaya?style=directory)](https://allmcps.com/mcp/ollaya)
HTML Embed
<a href="https://allmcps.com/mcp/ollaya"><img src="https://allmcps.com/api/badge/ollaya?style=directory" alt="Ollaya on AllMCPs" /></a>