Documentation

Ollaya downloads and serves open decision models locally. A decision model reads a state (text, an email, a ticket, JSON) plus typed questions, and returns typed answers with calibrated probabilities in a single forward pass. It never generates text.

• QuickstartInstall Ollaya, run your first decision model and call the local API.
• From the browser to your codeTake the model you tried in your browser to your own code. Pull coba:150m-ternary with Ollaya and call it from curl, Python, TypeScript or a Docker container.
• CLI referenceEvery ollaya command and flag: run, pull, serve, list, ps, show, stop, rm, cp, create, preset, update and mcp.
• API referenceThe native /api endpoints, the TypeSafe-compatible /v1 endpoints, errors, streaming and limits.
• ModelfileBake a question set, calibration, precision and license into a model you can run by name.
• TypeSafe compatibility (Jev-compatible API)Ollaya is a self-hosted, Jev-compatible API server. Use the official TypeSafe SDK and existing Jev code with local, open models by changing environment variables.
• Open-source Jev alternative: which open model on which hardwareReplace TypeSafe's hosted Jev with an open decision model on your own machine, behind the same API. Which model to run on a 4, 8 or 12 GB GPU or a CPU, with measured accuracy, calibration and speed.
• Agents: MCP and skillGive AI agents local, typed decisions: the Ollaya MCP server for Claude Code, Claude Desktop, Cursor and other clients, and an agent skill that teaches when and how to use it.
• Guardrails: prompt injection and jailbreak detectionCheck prompts, tool results and retrieved documents for prompt injection, jailbreaks and harmful content on your own machine, with open guard models and calibrated probabilities.
• Routing: pick the model for each requestRoute each request to the right LLM, tool or team with a local decision model. Difficulty, domain, tool use and sensitivity come back typed and calibrated, in milliseconds.
• Replacing LLM classification calls with a local modelMove the classify, triage and yes/no prompts you send to a hosted LLM onto a local decision model, with typed answers, calibrated probabilities and no per-token cost. Nothing leaves your machine.
• Zero-shot classification on a CPUClassify text into labels you choose per request, on a CPU with no GPU, in under a second. Which open models to run, and how fast and accurate they are, measured.
• FAQHow Ollaya relates to Ollama and TypeSafe, hardware, privacy, where weights come from, and licensing.
• For model authors: Day-0 supportReleasing a decision model? Share it with Ollaya before launch and `ollaya run` works on announcement day, with parity against your code and benchmark numbers you can quote.
• Integrations: LiteLLM, LangChain, AI SDK, DSPy, LlamaIndex, n8n and DifyUse Ollaya from LiteLLM, LangChain, the Vercel AI SDK, DSPy and LlamaIndex through their TypeSafe integrations, with a base URL and nothing else to install, and from n8n and Dify workflows over HTTP.