+Start building with open models.
-[Ollama](https://ollama.com) is the easiest way to get up and running with large language models such as gpt-oss, Gemma 4, DeepSeek-R1, Qwen3 and more.
+Follow the [quickstart](/quickstart), then choose a model, integration, or API.
+
+## Models
+
+Run models locally or use larger models in Ollama's cloud.
1. Install Claude Code
2. Set the environment variables
```shell export ANTHROPIC_AUTH_TOKEN=ollama @@ -120,7 +179,7 @@ export ANTHROPIC_API_KEY="" export ANTHROPIC_BASE_URL=http://localhost:11434 ``` -2. Run Claude Code with an Ollama model: +3. Run Claude Code
```shell claude --model qwen3.5 @@ -129,8 +188,5 @@ claude --model qwen3.5 Or run with environment variables inline: ```shell -ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 ANTHROPIC_API_KEY="" claude --model glm-5:cloud +ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 ANTHROPIC_API_KEY="" claude --model kimi-k2.7-code:cloud ``` - -**Note:** Claude Code requires a large context window. We recommend at least 64k tokens. See the [context length documentation](/context-length) for how to adjust context length in Ollama. - diff --git a/docs/integrations/hermes.mdx b/docs/integrations/hermes.mdx index fc0921f..99dda32 100644 --- a/docs/integrations/hermes.mdx +++ b/docs/integrations/hermes.mdx @@ -56,7 +56,7 @@ hermes setup If you'd rather drive Hermes's own wizard instead of `ollama launch hermes`, install it directly: ```bash -curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash +curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash ``` Hermes launches the setup wizard automatically. Choose **Quick setup**: diff --git a/docs/integrations/index.mdx b/docs/integrations/index.mdx index 32951d1..8cc5499 100644 --- a/docs/integrations/index.mdx +++ b/docs/integrations/index.mdx @@ -2,57 +2,43 @@ title: Overview --- -Ollama integrates with a wide range of tools. +Use Ollama from coding agents, personal assistants, and editors. -## Coding Agents +Run `ollama launch` to see the latest integrations you can run from the terminal. -Coding assistants that can read, modify, and execute code in your projects. +## Code in the terminal -- [Claude Code](/integrations/claude-code) -- [Codex App](/integrations/codex-app) -- [Codex CLI](/integrations/codex) -- [Copilot CLI](/integrations/copilot-cli) -- [Cline CLI](/integrations/cline-cli) -- [OpenCode](/integrations/opencode) -- [Droid](/integrations/droid) -- [Goose](/integrations/goose) -- [Oh My Pi](/integrations/oh-my-pi) -- [Pi](/integrations/pi) -- [Pool](/integrations/pool) -## Assistants +1. Install OpenCode
+ +2. Configure Ollama as a provider
+ +Add an Ollama provider to `opencode.json`: + +```json +{ + "$schema": "https://opencode.ai/config.json", + "provider": { + "ollama": { + "npm": "@ai-sdk/openai-compatible", + "name": "Ollama", + "options": { + "baseURL": "http://localhost:11434/v1" + }, + "models": { + "qwen3.5": { + "name": "qwen3.5" + } + } + } + } +} +``` + +3. Run OpenCode
+ +```shell +opencode +``` + +To configure OpenCode with Ollama without starting an interactive session: ```shell ollama launch opencode --config ``` -