### Install Dependencies and Start Dev Server

Source: https://github.com/nanogpt-community/nanocode/blob/dev/CONTRIBUTING.md

Install project dependencies and start the development server from the repository root. Requires Bun 1.3+.

```bash
bun install
bun dev
```

--------------------------------

### Install Mintlify CLI and Start Dev Server

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/docs/quickstart.mdx

Install the Mintlify CLI globally and then run the development server in your docs directory. Changes are reflected live.

```bash
npm i -g mint
mint dev
```

--------------------------------

### Install Dependencies and Start Development Server

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/desktop/README.md

Installs project dependencies and then starts the Tauri development server for the desktop app. Ensure you are in the repo root.

```bash
bun install
bun run --cwd packages/desktop tauri dev
```

--------------------------------

### Start SolidStart Development Server

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/console/app/README.md

After installing dependencies, run `npm run dev` to start the development server. Use the `-- --open` flag to automatically open the application in your browser.

```bash
npm run dev

# or start the server and open the app in a new browser tab
npm run dev -- --open
```

--------------------------------

### Install NanoCode CLI

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/github.mdx

Run this command in a GitHub repository to start the NanoCode installation process, which includes setting up the GitHub app and workflow.

```bash
nanocode github install
```

--------------------------------

### Start OpenCode Web Backend and Attach TUI

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/cli.mdx

This example demonstrates starting the OpenCode backend server for web/mobile access on a specific port and hostname, and then attaching the TUI to this running backend from another terminal.

```bash
# Start the backend server for web/mobile access
opencode web --port 4096 --hostname 0.0.0.0

# In another terminal, attach the TUI to the running backend
opencode attach http://10.20.30.40:4096
```

--------------------------------

### Card Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/docs/ai-tools/cursor.mdx

Shows how to use Card components for highlighting specific information or links. Ideal for getting started guides or feature summaries.

```jsx
<Card title="Getting started guide" icon="rocket" href="@nanogpt/quickstart">
Complete walkthrough from installation to your first API call in under 10 minutes.
</Card>
```

--------------------------------

### Install nanogpt-client via npm

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Install the nanogpt-client package using npm.

```bash
npm install nanogpt-client
```

--------------------------------

### Install nanocode SDK

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/sdk.mdx

Install the nanocode SDK using npm. This is the first step to using the SDK in your project.

```bash
npm install @nanogpt/sdk
```

--------------------------------

### Setup Virtual Framebuffer for Headless Linux

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/troubleshooting.mdx

In headless Linux environments, use `xvfb` to simulate a display for clipboard functionality. This command installs `xvfb` and sets up a virtual display.

```bash
apt install -y xvfb
# and run:
Xvfb :99 -screen 0 1024x768x24 > /dev/null 2>&1 &
export DISPLAY=:99.0
```

--------------------------------

### Install NanoCode with Bun

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/index.mdx

Install NanoCode globally using Bun. This is an alternative package manager installation method.

```bash
bun install -g nanocode
```

--------------------------------

### Start Web Server

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/web.mdx

Run this command to start the local NanoCode web server. It automatically opens in your default browser.

```bash
nanocode web
```

--------------------------------

### Install NanoGPTJS

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Install the NanoGPTJS library using npm.

```bash
npm install nanogptjs
```

--------------------------------

### Start Headless Web Server

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/cli.mdx

Starts a headless OpenCode server with a web interface. Set OPENCODE_SERVER_PASSWORD for basic auth.

```bash
opencode web
```

--------------------------------

### TUI Configuration Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/tui.mdx

Example tui.json file demonstrating various customization options for the TUI, including theme, keybinds, and scrolling behavior.

```json
{
  "$schema": "https://opencode.ai/tui.json",
  "theme": "opencode",
  "keybinds": {
    "leader": "ctrl+x"
  },
  "scroll_speed": 3,
  "scroll_acceleration": {
    "enabled": true
  },
  "diff_style": "auto"
}
```

--------------------------------

### TEE Verification Example (Python)

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Python script for TEE Attestation & Signature Verification. Requires installation of 'eth-account'.

```python
#!/usr/bin/env python3
"""
TEE Attestation & Signature Verification Example for NanoGPT.
"""
import requests
import json
import hashlib
from cryptography import x509
from cryptography.hazmat.primitives import serialization
from cryptography.hazmat.backends import default_backend
import base64
try:
 from eth_account.messages import encode_defunct
 from eth_account.account import Account
except ImportError:
 raise ImportError("Please install eth_account: pip install eth-account")
import os
from cryptography.x509.oid import ObjectIdentifier # if needed

```

--------------------------------

### Install Dependencies

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/app/README.md

Install project dependencies using npm, pnpm, or yarn.

```bash
$ npm install # or pnpm install or yarn install
```

--------------------------------

### Chat Example with NanoGPTJS

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Example of how to perform a chat completion using the NanoGPTJS library.

```javascript
async function chatExample() {
 try {
 const response = await nanogpt.chat({
 model: 'chatgpt-4o-latest',
 messages: [
 { role: 'system', content: 'You are a helpful assistant.' },
 { role: 'user', content: 'What is the capital of France?' }
 ]
 });

 console.log(response);
 } catch (error) {
 console.error('Error:', error);
 }
 }

chatExample();
```

--------------------------------

### Install Clipboard Utilities on Linux (Wayland)

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/troubleshooting.mdx

For copy/paste functionality on Wayland systems, install `wl-clipboard` using apt.

```bash
apt install -y wl-clipboard
```

--------------------------------

### Install Clipboard Utilities on Linux (X11)

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/troubleshooting.mdx

For copy/paste functionality on X11 systems, install `xclip` or `xsel` using apt.

```bash
apt install -y xclip
# or
apt install -y xsel
```

--------------------------------

### Start Headless OpenCode Server

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/cli.mdx

Starts a headless OpenCode server for API access. This server can be attached to by other `opencode run` commands.

```bash
opencode serve
```

--------------------------------

### Install Opencode GitHub Action via CLI

Source: https://github.com/nanogpt-community/nanocode/blob/dev/github/README.md

Run this command in your GitHub repo's terminal to install the GitHub app, create the workflow, and set up secrets.

```bash
opencode github install
```

--------------------------------

### Install Mintlify CLI

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/docs/README.md

Install the Mintlify CLI globally using npm. This tool is required for local development and previewing documentation changes.

```bash
npm i -g mint
```

--------------------------------

### Model Naming Convention Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/troubleshooting.mdx

Models should be referenced using the format `<providerId>/<modelId>`. This example shows correct formatting for different providers.

```bash
openai/gpt-4.1
openrouter/google/gemini-2.5-flash
nanocode/kimi-k2
```

--------------------------------

### Example AGENTS.md Content

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/rules.mdx

This markdown file provides an example of custom instructions for a monorepo project, including project structure, code standards, and conventions.

```markdown
# SST v3 Monorepo Project

This is an SST v3 monorepo with TypeScript. The project uses bun workspaces for package management.

## Project Structure

- `packages/` - Contains all workspace packages (functions, core, web, etc.)
- `infra/` - Infrastructure definitions split by service (storage.ts, api.ts, web.ts)
- `sst.config.ts` - Main SST configuration with dynamic imports

## Code Standards

- Use TypeScript with strict mode enabled
- Shared code goes in `packages/core/` with proper exports configuration
- Functions go in `packages/functions/`
- Infrastructure should be split into logical files in `infra/`

## Monorepo Conventions

- Import shared modules using workspace names: `@my-app/core/example`
```

--------------------------------

### Run Desktop App Development

Source: https://github.com/nanogpt-community/nanocode/blob/dev/CONTRIBUTING.md

Start the native desktop application for development using Tauri. This command also starts the web dev server. Additional Tauri prerequisites are required.

```bash
bun run --cwd packages/desktop tauri dev
```

```bash
bun run --cwd packages/desktop dev
```

--------------------------------

### Binary Response Headers Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

OpenAI models return audio data directly as binary. This example shows the expected Content-Type and Content-Length headers.

```text
Content-Type: audio/mp3
Content-Length: 123456
[Binary audio data]
```

--------------------------------

### Start Local Development Server

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/docs/README.md

Run the Mintlify development server from the root of your documentation project. Ensure your 'docs.json' file is present. The preview will be available at http://localhost:3000.

```bash
mint dev
```

--------------------------------

### Start Web Development Server Only

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/desktop-electron/README.md

Starts only the Vite web development server without launching the native Tauri shell. Useful for focusing on web-related development.

```bash
bun run --cwd packages/desktop dev
```

--------------------------------

### Mintlify Request/Response Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/docs/ai-tools/cursor.mdx

Illustrates how to document API requests and their corresponding responses.

```bash
curl -X POST 'https://api.example.com/users' \
  -H 'Content-Type: application/json' \
  -d '{"name": "John Doe", "email": "john@example.com"}'
```

--------------------------------

### Initialize New Project

Source: https://github.com/nanogpt-community/nanocode/blob/dev/specs/project.md

Initializes a new project.

```http
POST /project/init -> Project
```

--------------------------------

### Accordion Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/docs/ai-tools/cursor.mdx

Demonstrates how to use AccordionGroup and Accordion components for collapsible content sections. Useful for organizing FAQs or troubleshooting guides.

```jsx
<AccordionGroup>
  <Accordion title="Troubleshooting connection issues">
    - **Firewall blocking**: Ensure ports 80 and 443 are open
    - **Proxy configuration**: Set HTTP_PROXY environment variable
    - **DNS resolution**: Try using 8.8.8.8 as DNS server
  </Accordion>

  <Accordion title="Advanced configuration">
    ```javascript
    const config = {
      performance: { cache: true, timeout: 30000 },
      security: { encryption: 'AES-256' }
    };
    ```
  </Accordion>
</AccordionGroup>
```

--------------------------------

### Documentation Agent Configuration

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/agents.mdx

Example configuration for a 'docs-writer' subagent, specifying its description, mode, and available tools. The system prompt guides its behavior as a technical writer.

```markdown
---
description: Writes and maintains project documentation
mode: subagent
tools:
  bash: false
---

You are a technical writer. Create clear, comprehensive documentation.

Focus on:

- Clear explanations
- Proper structure
- Code examples
- User-friendly language
```

--------------------------------

### Build the Desktop Application

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/desktop/README.md

Builds the release version of the desktop application. Run this command from the repository root.

```bash
bun run --cwd packages/desktop tauri build
```

--------------------------------

### Quick Start: Create Embedding with NanoGPT

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Initialize the OpenAI client to point to the NanoGPT API and create an embedding for a given text. This example demonstrates the basic usage for generating embeddings.

```python
from openai import OpenAI

# Initialize client pointing to NanoGPT
client = OpenAI(
 api_key="YOUR_NANOGPT_API_KEY",
 base_url="https://nano-gpt.com/api/v1"
)

# Create embedding
response = client.embeddings.create(
 input="Your text to embed",
 model="text-embedding-3-small"
)

embedding = response.data[0].embedding
print(f"Embedding has {len(embedding)} dimensions")
```

--------------------------------

### Verify Agents SDK Installation

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/opencode/test/fixture/skills/agents-sdk/SKILL.md

Check if the agents package is installed in your project. If not, install it using npm.

```bash
npm ls agents  # Should show agents package
```

```bash
npm install agents
```

--------------------------------

### Install NanoCode with pnpm

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/index.mdx

Install NanoCode globally using pnpm. This is another package manager option for installation.

```bash
pnpm install -g nanocode
```

--------------------------------

### Create Client (with server)

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/sdk.mdx

Create an instance of nanocode, which starts both a server and a client. You can optionally provide configuration options.

```javascript
import { createOpencode } from "@nanogpt/sdk"

const { client } = await createOpencode()

// Optional configuration:
// const nanocode = await createOpencode({
//   hostname: "127.0.0.1",
//   port: 4096,
//   config: {
//     model: "anthropic/claude-3-5-sonnet-20241022",
//   },
// })

// console.log(`Server running at ${nanocode.server.url}`)
// nanocode.server.close()
```

--------------------------------

### Navigate to project directory

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/index.mdx

Before initializing NanoCode, navigate to the root directory of the project you want to work on.

```bash
cd /path/to/project
```

--------------------------------

### Install Droid CLI

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Install the Droid command-line interface using curl. This command fetches and executes the installation script.

```bash
curl -fsSL https://app.factory.ai/cli | sh
```

--------------------------------

### Install NanoCode via curl

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/index.mdx

Use this command to install NanoCode using the provided script. Ensure you have curl installed.

```bash
curl -fsSL https://nanocode.ai/install | bash
```

--------------------------------

### Use Grep by Vercel MCP Server in Prompt

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/mcp-servers.mdx

Example prompt demonstrating how to use the Grep by Vercel MCP server to find information on setting custom domains in an Astro component.

```text
What's the right way to set a custom domain in an SST Astro component? use the gh_grep tool
```

--------------------------------

### Search for Configuration Files

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/opencode/src/session/prompt/gemini.txt

Demonstrates how to find all instances of a specific configuration file across the project using a glob pattern. It then offers to read the content of the found files.

```text
user: Where are all the 'app.config' files in this project? I need to check their settings.
model:
[tool_call: glob for pattern '**/app.config']
(Assuming GlobTool returns a list of paths like ['/path/to/moduleA/app.config', '/path/to/moduleB/app.config'])
I found the following 'app.config' files:
- /path/to/moduleA/app.config
- /path/to/moduleB/app.config
To help you check their settings, I can read their contents. Which one would you like to start with, or should I read all of them?
```

--------------------------------

### Install Dependencies with Bun

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/opencode/README.md

Installs project dependencies using the Bun package manager. Ensure Bun is installed on your system.

```bash
bun install
```

--------------------------------

### Print 'Hello World' in Python

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/opencode/src/tool/todowrite.txt

Use this for simple, single-line code execution. The todo list is not needed for trivial tasks.

```python
print("Hello World")
```

--------------------------------

### Initialize NanoCode for a project

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/index.mdx

Run this command in your project's root directory to initialize NanoCode. It will analyze the project and create an AGENTS.md file.

```bash
/init
```

--------------------------------

### Install Nanocode CLI

Source: https://github.com/nanogpt-community/nanocode/blob/dev/README.md

Installs the latest version of the Nanocode CLI globally.

```bash
bun i -g nanocode@latest
```

--------------------------------

### Run Backend Development Server

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/app/AGENTS.md

Starts the backend development server for local UI changes. Ensure you are in the 'packages/opencode' directory.

```shell
bun run --conditions=browser ./src/index.ts serve --port 4096
```

--------------------------------

### Text-to-Speech API Parameter Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Example of the text parameter for text-to-speech generation.

```string
"Hello! This is a test of the text-to-speech API."
```

--------------------------------

### Configure Local MCP Server with Command and Environment Variables

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/mcp-servers.mdx

Set up a local MCP server by specifying 'type: "local"' and providing the 'command' to execute it. Environment variables can be passed using the 'environment' object.

```jsonc
{
  "$schema": "https://nanocode.ai/config.json",
  "mcp": {
    "my-local-mcp-server": {
      "type": "local",
      // Or ["bun", "x", "my-mcp-command"]
      "command": ["npx", "-y", "my-mcp-command"],
      "enabled": true,
      "environment": {
        "MY_ENV_VAR": "my_env_var_value"
      }
    }
  }
}
```

--------------------------------

### Create a New SolidStart Project

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/console/app/README.md

Use `npm init solid@latest` to create a new SolidStart project. You can initialize it in the current directory or specify a new directory name.

```bash
npm init solid@latest

# create a new project in my-app
npm init solid@latest my-app
```

--------------------------------

### Install Playwright Browsers

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/app/README.md

Installs the necessary Playwright browser binaries for end-to-end testing.

```bash
bunx playwright install
```

--------------------------------

### Development vs. Production CLI Commands

Source: https://github.com/nanogpt-community/nanocode/blob/dev/CONTRIBUTING.md

Compares the command-line interface commands for development using 'bun dev' and production using 'opencode'. Shows how to display help, start servers, and run the TUI in a specific directory.

```bash
# Development (from project root)
bun dev --help           # Show all available commands
bun dev serve            # Start headless API server
bun dev web              # Start server + open web interface
bun dev <directory>      # Start TUI in specific directory

# Production
opencode --help          # Show all available commands
opencode serve           # Start headless API server
opencode web             # Start server + open web interface
opencode <directory>     # Start TUI in specific directory
```

--------------------------------

### Bearer Authentication Header Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Example of the Authorization header for Bearer token authentication.

```http
Authorization: Bearer YOUR_API_KEY
```

--------------------------------

### Command Line Interface for Connecting to Providers

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/providers.mdx

Use the /connect command to initiate the connection process with various AI providers.

```txt
/connect
```

```txt
/models
```

--------------------------------

### Polling Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

An example JavaScript function demonstrating how to poll for video generation status.

```APIDOC
## Polling Example

An example JavaScript function demonstrating how to poll for video generation status.

```javascript
async function pollVideoStatus(runId, model) {
 const maxAttempts = 120; // ~10 minutes total
 const delayMs = 5000; // 5 seconds (max ~10 minutes)
 
 for (let i = 0; i < maxAttempts; i++) {
 const response = await fetch(
 `/api/generate-video/status?runId=${runId}&model=${model}`
 );
 const result = await response.json();
 
 if (result.data.status === 'COMPLETED') {
 return result.data.output.video.url;
 } else if (result.data.status === 'FAILED') {
 throw new Error(result.data.error || 'Video generation failed');
 }
 
 // Wait before next poll
 await new Promise((resolve) => setTimeout(resolve, delayMs));
 }
 
 throw new Error('Video generation timed out');
 }
 ```
```

--------------------------------

### Create a video

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Example of creating a video using the client, specifying prompt, framework, and target length in words.

```typescript
const video = await client.videos.create({
  prompt: 'A short animation of code being written',
  framework: 'emotional_story',
  targetLengthInWords: 70
});
```

--------------------------------

### Mintlify Success Response Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/docs/ai-tools/cursor.mdx

Provides an example of a successful API response structure.

```json
{
  "id": "user_123",
  "name": "John Doe", 
  "email": "john@example.com",
  "created_at": "2024-01-15T10:30:00Z"
}
```

--------------------------------

### Use Context7 MCP Server in Prompt

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/mcp-servers.mdx

Example prompt demonstrating how to use the Context7 MCP server to configure a Cloudflare Worker script.

```text
Configure a Cloudflare Worker script to cache JSON API responses for five minutes. use context7
```

--------------------------------

### Execute npm install command

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/opencode/src/tool/todowrite.txt

This snippet demonstrates a single command execution. The todo list is unnecessary for tasks with immediate, single-step results.

```bash
npm install
```

--------------------------------

### API Key Authentication Header Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Example of the x-api-key header for API key authentication.

```http
x-api-key: YOUR_API_KEY
```

--------------------------------

### TEE Signature Response Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Example JSON response structure for a TEE signature request.

```json
{
 "signature": "<string>"
 }
```

--------------------------------

### Run Web App Development Server

Source: https://github.com/nanogpt-community/nanocode/blob/dev/CONTRIBUTING.md

Start the web app development server to test UI changes. Requires the OpenCode server to be running first. The output will show the local development URL.

```bash
bun run --cwd packages/app dev
```

--------------------------------

### Install Claude Code CLI

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/docs/ai-tools/claude-code.mdx

Install the Claude Code CLI tool globally using npm.

```bash
npm install -g @anthropic-ai/claude-code
```

--------------------------------

### Mintlify Steps for Procedures

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/docs/ai-tools/cursor.mdx

Demonstrates structuring documentation as a series of steps with verification and warnings.

```Steps
<Steps>
<Step title="Install dependencies">
  Run `npm install` to install required packages.
  
  <Check>
  Verify installation by running `npm list`.
  </Check>
</Step>

<Step title="Configure environment">
  Create a `.env` file with your API credentials.
  
  ```bash
  API_KEY=your_api_key_here
  ```
  
  <Warning>
  Never commit API keys to version control.
  </Warning>
</Step>
</Steps>
```

--------------------------------

### Error Handling Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Example of how to catch and log API response errors, including status and message.

```javascript
try {
 const response = await nanogpt.chat({
 model: 'chatgpt-4o-latest',
 messages: [
 { role: 'user', content: 'Hello!' }
 ]
 });
} catch (error) {
 console.error('Status:', error.status);
 console.error('Message:', error.message);
}
```

--------------------------------

### Run Slack Bot

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/slack/README.md

Start the Slack bot development server. Ensure your .env file is configured with Slack app credentials.

```bash
# Edit .env with your Slack app credentials
bun dev
```

--------------------------------

### Install NanoCode with Yarn

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/index.mdx

Install NanoCode globally using Yarn. This is a common package manager for JavaScript projects.

```bash
yarn global add nanocode
```

--------------------------------

### Set Up Proxy Environment Variables

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/network.mdx

Configure proxy settings for NanoCode by exporting standard environment variables. Ensure to bypass the proxy for local connections.

```bash
export HTTPS_PROXY=https://proxy.example.com:8080

export HTTP_PROXY=http://proxy.example.com:8080

export NO_PROXY=localhost,127.0.0.1
```

--------------------------------

### Install NanoCode with npm

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/index.mdx

Install NanoCode globally using npm. This is one of the package manager options available.

```bash
npm install -g nanocode
```

--------------------------------

### session.init({ path, body })

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/sdk.mdx

Analyzes an application and creates an AGENTS.md file for a given session path. Returns a boolean indicating success.

```APIDOC
## session.init({ path, body })

### Description
Analyzes an app and creates `AGENTS.md` for a session.

### Method
N/A (SDK Method)

### Parameters
#### Path Parameters
- **path** (string) - Required - The path identifier of the session.
#### Request Body
- **body** (object) - Required - An object containing details for the analysis (e.g., app path).

### Response
#### Success Response
- **success** (boolean) - True if the initialization was successful, false otherwise.

### Response Example
```json
true
```
```

--------------------------------

### OpenHands Custom Model Prefix Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Example showing the required 'openai/' prefix for custom models in OpenHands.

```text
Custom Model: openai/claude-3-5-sonnet-20241022
```

--------------------------------

### Use Sentry MCP Server in Prompt

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/web/src/content/docs/mcp-servers.mdx

Example prompt demonstrating how to use the authenticated Sentry MCP server to query for unresolved issues.

```text
Show me the latest unresolved issues in my project. use sentry
```

--------------------------------

### Error Response Example

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

This is an example of an error response that might be returned by the API, indicating a content policy violation.

```json
{
 "status": "error",
 "code": "CONTENT_POLICY_VIOLATION",
 "error": "Content rejected by provider. Please modify your prompt and try again."
 }
```

--------------------------------

### OpenAPI Configuration Examples

Source: https://github.com/nanogpt-community/nanocode/blob/dev/packages/docs/essentials/settings.mdx

Configure OpenAPI file paths. Supports absolute URLs, relative paths, and multiple OpenAPI files.

```json
"openapi": "https://example.com/openapi.json"
```

```json
"openapi": "@nanogpt/openapi.json"
```

```json
"openapi": ["https://example.com/openapi1.json", "@nanogpt/openapi2.json", "@nanogpt/openapi3.json"]
```

--------------------------------

### Text Completion Model Examples

Source: https://github.com/nanogpt-community/nanocode/blob/dev/nanogpt.md

Examples of model identifiers for text completion, including options for web search.

```string
"chatgpt-4o-latest"
```

```string
"chatgpt-4o-latest:online"
```

```string
"chatgpt-4o-latest:online/linkup-deep"
```

```string
"claude-3-5-sonnet-20241022:online"
```