# Integrations

- [Connect API Providers & Model Servers to Unsloth](https://unsloth.ai/docs/integrations/connections.md): Guide to connect OpenAI, Anthropic, Ollama, llama.cpp, vLLM and other providers to Unsloth. Add API keys or model server URLs, load models, and use external models in chat.
- [Connect OpenAI to Unsloth: Run GPT Models in Local Chat](https://unsloth.ai/docs/integrations/connections/openai.md)
- [Connect Anthropic to Unsloth: Run Claude Models in Local Chat](https://unsloth.ai/docs/integrations/connections/anthropic-claude.md)
- [Connect llama.cpp to Unsloth: Run GGUFs with llama-server](https://unsloth.ai/docs/integrations/connections/connect-llama.cpp-to-unsloth-run-ggufs-with-llama-server.md)
- [Connect vLLM to Unsloth for Local Chat Inference](https://unsloth.ai/docs/integrations/connections/vllm.md)
- [How to Connect Ollama to Unsloth](https://unsloth.ai/docs/integrations/connections/ollama.md)
- [How to Connect OpenRouter to Unsloth: API Key & Model Setup](https://unsloth.ai/docs/integrations/connections/openrouter.md)
- [How to Run Local AI Models with OpenClaw](https://unsloth.ai/docs/integrations/openclaw.md): Guide to running local LLMs with OpenClaw.
- [How to Run Local AI Models with OpenCode](https://unsloth.ai/docs/integrations/openclaw/opencode.md): Guide to connect open LLMs with OpenCode on your local device.
- [How to Run Local AI Models with Hermes Agent](https://unsloth.ai/docs/integrations/hermes-agent.md): Guide on using open LLMs with Hermes Agent locally.
- [Connect Python SDK to Unsloth](https://unsloth.ai/docs/integrations/connect-python-sdk-to-unsloth.md): Guide to calling Unsloth's local API from Python using the official OpenAI or Anthropic SDKs including streaming, vision, function calling, and Unsloth's built-in server-side tools.
- [Connect Curl & HTTP to Unsloth](https://unsloth.ai/docs/integrations/connect-curl-and-http-to-unsloth.md): Guide to hitting Unsloth's API with curl (or any HTTP client), complete with copy-pasteable recipes for every endpoint and feature..


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://unsloth.ai/docs/integrations.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.