Local models via Ollama
Use Ollama in your coding tools
Step-by-step setup for Ollama in 11 coding tools: Aider, Claude Code, Cline, Codex CLI, Continue, GitHub Copilot, Goose, Kilo Code, OpenCode, Roo Code and Zed. Every step comes from official docs, read on .
Ollama setup guides
- Documented by AiderUse Ollama in AiderAider connects to Ollama natively: set OLLAMA_API_BASE to the local server and run `aider --model ollama_chat/<model>`.127.0.0.16 steps
- Documented by OllamaUse Ollama in Claude CodeOllama exposes an Anthropic-compatible API, so Claude Code can point at a local Ollama server (or ollama.com cloud) with ANTHROPIC_BASE_URL. Ollama also ships a one-command launcher, `ollama launch claude`.localhost8 steps
- Documented by OllamaUse Ollama in ClineCline has a native Ollama API provider in its settings, and the Cline CLI can be configured with `ollama launch cline` or `cline auth`.localhost8 steps
- Documented by OllamaUse Ollama in Codex CLICodex CLI can run against Ollama with the built-in `--oss` flag, a persistent profile that points a custom model provider at Ollama's OpenAI-compatible /v1 endpoint, or Ollama's `ollama launch codex` helper.localhost9 steps
- Documented by ContinueUse Ollama in ContinueContinue has a native `provider: ollama` model entry in config.yaml; set the model to an Ollama model id and apiBase only if Ollama runs remotely.localhost4 steps
- From Ollama and GitHub Copilot docsUse Ollama in GitHub CopilotGitHub Copilot CLI supports bring-your-own-model providers through COPILOT_PROVIDER_* environment variables, and both GitHub and Ollama document pointing it at a local Ollama server. Ollama also offers `ollama launch copilot`.localhost7 steps
- From Ollama and Goose docsUse Ollama in GooseGoose 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.localhost4 steps
- Documented by Kilo CodeUse Ollama in Kilo CodeKilo Code has a built-in Ollama provider for a local daemon; configure it in Settings > Providers (VS Code) or in kilo.json with baseURL http://localhost:11434/v1 and a model like ollama/qwen3-coder:30b.localhost7 steps
- Documented by OllamaUse Ollama in OpenCodeOpenCode talks to Ollama through the @ai-sdk/openai-compatible provider pointed at http://localhost:11434/v1, or via `ollama launch opencode`, which injects an inline config for the chosen model.localhost6 steps
- From Ollama and Roo Code docsUse Ollama in Roo CodeRoo Code has a native Ollama API provider; set the provider to Ollama, keep the default base URL http://localhost:11434, and enter an Ollama model id.localhost6 steps
- From Ollama and Zed docsUse Ollama in ZedZed has a native Ollama LLM provider that auto-discovers pulled models from http://localhost:11434; optional settings.json control the API URL, model list and context window.localhost5 steps
No verified Ollama guide yet for Cursor. We only publish a pairing once official docs cover it.
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.