Setup guide - From Ollama and Goose docs
Use Ollama in Goose
Goose has a built-in Ollama provider (configured by OLLAMA_HOST) in both Desktop and CLI; point it at http://localhost:11434 and pick a tool-capable model.
Last verified 4 steps3 official sources
Steps
- Step 1.
Goose Desktop: open Settings > Configure Provider, find Ollama, click Configure.
- Step 2.
Confirm API Host is
http://localhost:11434and click Submit. - Step 3.
Goose CLI: run the configure flow, select Configure Providers, then Ollama, and enter a model name (e.g. qwen3).
Terminalgoose configure - Step 4.
ollama.com cloud: create an API key at https://ollama.com/settings/keys and save it in your .env, then set API Host (Desktop) or OLLAMA_HOST (CLI) to https://ollama.com.
Caveats
- Goose's provider docs list Ollama with the OLLAMA_HOST variable and say that if no host is provided it defaults to localhost:11434, prepending http:// when no scheme is given.
- Goose's docs say to run an Ollama model that supports tool calling.
- Goose also lists a separate Ollama Cloud provider using OLLAMA_CLOUD_API_KEY; the ollama.com steps above follow Ollama's page instead.
More setup guides
Same tool, other providers
Related reading
- Ollama Decision Models: Run Nimble Locally with --askOllama 0.40.4 runs decision models locally: ollama run nimble --ask answers yes/no, label and score questions with probabilities. Commands and limits.
- Ollama 0.40 on Mac: MLX by Default, Disk Space DoubledOllama 0.40 runs supported models on MLX on Apple Silicon and keeps a backup copy of each model you load. What it costs in disk, what is fixed, and the cleanup.
- GitHub Copilot CLI With Ollama: Local Models and the New SandboxCopilot CLI 1.0.94 finds local Ollama models from /model and ships an OS-level sandbox. Setup, the 4k context trap, and why local is not offline.
- Hermes Agent Guide (2026): What It Is, Local Setup With Ollama, Skills, and Hermes vs OpenClawHermes Agent is Nous Research's open-source, self-improving AI agent. Run it locally with Ollama, see how its skills system works, and compare it with OpenClaw.
- What Is OpenClaw? Setup, Skills, MCP Server, Claude Code, and Ollama (2026 Guide)What is OpenClaw? A self-hosted personal AI agent you reach through chat apps. Install, skills and ClawHub, its MCP server, Claude Code use, and Ollama models.
- GitHub Copilot for JetBrains Gains Persistent Memory and Ollama BYOKGitHub Copilot for JetBrains adds memory across chat sessions, Ollama as a BYOK provider, and enterprise settings for MCP access. What each feature does.
FAQ
How do I use Ollama in Goose?
Goose has a built-in Ollama provider (configured by OLLAMA_HOST) in both Desktop and CLI; point it at http://localhost:11434 and pick a tool-capable model.
Which Ollama model ids work in Goose?
The official docs read for this guide list qwen3. Requests go to http://localhost:11434.
Is this an official Ollama and Goose setup?
The steps draw on both Ollama's and Goose's docs. It was last checked against 3 official pages on October 17, 2026.
Sources
Last verified against 3 official pages.
- docs.ollama.comhttps://docs.ollama.com/integrations/goose
- raw.githubusercontent.comhttps://raw.githubusercontent.com/ollama/ollama/main/docs/integrations/goose.mdx
- raw.githubusercontent.comhttps://raw.githubusercontent.com/aaif-goose/goose/main/documentation/docs/getting-started/providers.md
Newsletter
New models, set up the day they ship
One email per week. New model releases, the coding tools that support them and how to wire them up.