> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.privategpt.dev/api-reference/sdks/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.privategpt.dev/_mcp/server.

# Client libraries

> Use the Anthropic SDK or LangChain to talk to PrivateGPT.

PrivateGPT follows the Claude API model, so any client that speaks that protocol works against it — point it at your local PrivateGPT URL instead of Anthropic's servers.

---

## Anthropic SDK

#### Python

```bash
pip install anthropic
```

```python
import anthropic

client = anthropic.Anthropic(
    base_url="http://localhost:8080",
    api_key="any",  # required by the client but not validated by default
)

message = client.messages.create(
    model="qwen3.5:35b",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
print(message.content[0].text)
```

#### TypeScript

```bash
npm install @anthropic-ai/sdk
```

```typescript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  baseURL: "http://localhost:8080",
  apiKey: "any",
});

const message = await client.messages.create({
  model: "qwen3.5:35b",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(message.content[0].text);
```

---

## LangChain

#### Python

```bash
pip install langchain-anthropic
```

```python
from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(
    model="qwen3.5:35b",
    anthropic_api_url="http://localhost:8080",
    anthropic_api_key="any",
)

response = llm.invoke("Hello!")
print(response.content)
```

> Use the Anthropic SDK or LangChain to talk to PrivateGPT.