Ollaya
by Ollaya
Pulls and serves open decision models from a local daemon, Ollama-style, returning calibrated typed answers via a CLI, a TypeSafe-compatible HTTP API, or an MCP server.
Skills
Pull and Run Models
Pulls decision models by name and runs them with ollaya run, pull, list, ps, and related commands.
TypeSafe-Compatible API
Serves POST /v1/systemone, /v1/decisions, and GET /v1/models wire-identical to TypeSafe.
Native Decide API
Returns decisions with routing information and timings from /api/decide.
MCP Server
Serves the models to Claude Code, Claude Desktop, Cursor, and other MCP clients via ollaya mcp.
Modelfiles
Bakes a question set into a custom model with ollaya create.
Related Agents
Jev
Answers typed Choice, Score, and yes/no (Noul) questions about your app state with calibrated probabilities and confide…
Laya
Answers typed choice, score, and yes/no questions about text in 100+ languages in one forward pass, via Python, CLI, a…
AgentOps for Apify Builders Bundle
Apify actor bundle for agent builders: normalize run traces for QA, control costs, and guard tool calls with a firewall…
Alibaba Cloud Model Studio
Serves Qwen and third-party models through DashScope and OpenAI-compatible APIs on Alibaba Cloud, covering text, vision…