feat: agent node

README.md

@@ -95,5 +95,38 @@ For self-hosting (e.g. Tailscale/HTTPS): set `CORS_ORIGIN` to your frontend URL;
 | PUT    | `/api/todos/:id` | Update. |
 | DELETE | `/api/todos/:id` | Delete. |
 | GET    | `/health`        | Health check (e.g. for Docker). |
+| POST   | `/api/agent`     | Run AI agent; body `{ "prompt", "context?", "contextNodes?" }` → `{ "markdown" }`. |
 
 Data is in-memory (resets on restart). Add a JSON file or DB later if needed.
+
+---
+
+## Agent node (local LLM or OpenAI)
+
+The **Agent** node uses an OpenAI-compatible API. You can use:
+
+**1. Local LLM (e.g. LM Studio)**
+
+1. Install [LM Studio](https://lmstudio.ai/) and load a model.
+2. Start the local server: in LM Studio open the **Developer** tab and run the **Local Server** (default: `http://localhost:1234`).
+3. In the project root or `backend/`, set:
+
+   ```bash
+   export AI_BASE_URL=http://localhost:1234/v1
+   # Optional: set to the model name shown in LM Studio (e.g. the loaded model id). Default is "local-model".
+   export AI_MODEL=your-model-name
+   ```
+
+4. Start the backend (`cd backend && npm run dev`). The Agent node will use your local model.
+
+**2. OpenAI**
+
+Set `OPENAI_API_KEY` to your API key. The backend will use `gpt-4o-mini` unless you set `AI_MODEL`.
+
+**Env summary (backend)**
+
+| Variable | When to use | Description |
+|----------|--------------|-------------|
+| `AI_BASE_URL` | Local LLM (LM Studio, Ollama, etc.) | OpenAI-compatible base URL, e.g. `http://localhost:1234/v1`. |
+| `AI_MODEL` | Optional | Model id (for local: use the name shown in LM Studio; for OpenAI: e.g. `gpt-4o-mini`). |
+| `OPENAI_API_KEY` | OpenAI only | Your OpenAI API key. Not required when using `AI_BASE_URL` only. |