### kickoffAssistant

Source: https://github.com/langwatch/better-agents/blob/main/src/assistant-kickoff/README.md

Builds and displays initial instructions for starting the coding assistant. This function constructs the AI prompt, formats and displays setup instructions, and prepares command-line instructions.

```APIDOC
## kickoffAssistant(projectPath, config)

### Description
Builds and displays initial instructions for starting the coding assistant. This function constructs the AI prompt, formats and displays setup instructions, and prepares command-line instructions.

### Method
`kickoffAssistant`

### Parameters
#### Path Parameters
- **projectPath** (string) - Required - The path to the project.
- **config** (ProjectConfig) - Required - The configuration object for the project.

### Response
#### Success Response
- Returns a Promise that resolves when the kickoff process is complete.

### Request Example
```javascript
kickoffAssistant('/path/to/your/project', { /* ProjectConfig object */ })
```
```

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

### Initialize a New Agent

Source: https://github.com/langwatch/better-agents/blob/main/docs/GETTING-STARTED.md

Initialize a new agent project using the globally installed CLI. This command will guide you through a series of prompts to set up your agent.

```bash
better-agents init my-agent
```

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

### Agent Project Setup Confirmation

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

This output confirms the successful setup of your agent project and provides the initial prompt for your coding assistant. It outlines first steps and best practices.

```bash
✔ Setting up your agent project...
✨ Your agent project is ready!

Project location: /path/to/my-stock-agent

🤖 Starting your coding assistant...

Initial prompt:
"You are an expert AI agent developer. This project has been set up with Better Agents best practices.

First steps:
1. Read and understand the AGENTS.md file - it contains all the guidelines for this project
2. Update the AGENTS.md with specific details about what this project does
3. Create a comprehensive README.md explaining the project, setup, and usage
4. Set up the Python environment (requirements.txt)
5. Use the Agno MCP to learn about Agno best practices
6. Use the LangWatch MCP to learn about prompt management and testing
7. Start implementing the core agent functionality

Remember:
- ALWAYS use LangWatch Prompt CLI for prompts (ask the MCP how)
- ALWAYS write Scenario tests for new features (ask the MCP how)
- Follow the Agent Testing Pyramid methodology
- Test everything before considering it done

Project Goal: Build an agent that can analyze stock prices and provide trading recommendations"

To start Claude Code with this prompt, run:
  cd /path/to/my-stock-agent
  claude "You are an expert AI agent developer..."

Happy coding! 🚀
```

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

### Example Prompt File

Source: https://github.com/langwatch/better-agents/blob/main/docs/STRUCTURE.md

Demonstrates the file naming convention for versioned prompt files, typically stored in YAML format.

```text
prompts/sample_prompt.yaml
```

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

### Install Project Dependencies

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Install all necessary project dependencies using pnpm.

```bash
pnpm install
```

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

### Initialize Better Agents in New Directory

Source: https://github.com/langwatch/better-agents/blob/main/README.md

Initialize Better Agents in a new directory, creating the project structure and configuration files. The CLI guides through setup choices.

```bash
better-agents init my-awesome-agent
```

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

### Navigate and Launch Agent

Source: https://github.com/langwatch/better-agents/blob/main/docs/GETTING-STARTED.md

After initializing your agent, navigate into the project directory and launch your coding assistant. The assistant is typically auto-launched after the initial setup.

```bash
cd my-agent
# Launch your coding assistant (it will be auto-launched after setup)
```

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

### Clone and Install Dependencies

Source: https://github.com/langwatch/better-agents/blob/main/docs/USAGE.md

Clone the repository and install project dependencies using pnpm.

```bash
git clone https://github.com/langwatch/better-agents
cd better-agents
pnpm install
```

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

### Environment Setup: requirements.txt

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

This file lists the Python dependencies required for the agent, including Agno, LangWatch, and python-dotenv.

```python
# requirements.txt
agno>=0.1.0
langwatch>=0.1.0
python-dotenv>=1.0.0
```

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

### Initialize a New Agent with npx

Source: https://github.com/langwatch/better-agents/blob/main/docs/GETTING-STARTED.md

Initialize a new agent project without global installation using npx. Follow the interactive prompts to configure your agent's language, framework, coding assistant, LLM provider, API keys, and project goal.

```bash
npx @langwatch/better-agents init my-agent
```

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

### Initialize Better Agents Project

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

Initialize a new agent project named 'my-stock-agent'. This command will guide you through configuration questions.

```bash
better-agents init my-stock-agent
```

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

### Agent Project Structure Example

Source: https://github.com/langwatch/better-agents/blob/main/docs/PHILOSOPHY.md

Illustrates a recommended directory structure for an agent project, including sections for agent code, tests (evaluations and scenarios), prompts, and configuration files.

```tree
my-agent-project/
├── app/ (or src/)           # The actual agent code, structured according to the chosen framework
├── tests/
│   ├── evaluations/         # Jupyter notebooks for evaluations
│   │   └── example_eval.ipynb
│   └── scenarios/           # End-to-end scenario tests
│       └── example_scenario.test.{py,ts}
├── prompts/                 # Versioned prompt files for team collaboration
│   └── sample_prompt.yaml
├── prompts.json             # Prompt registry
├── .mcp.json                # MCP server configuration (universal)
├── .cursor/mcp.json         # Symlink to .mcp.json for Cursor
├── AGENTS.md                # Development guidelines
├── CLAUDE.md                # References AGENTS.md for Claude Code
├── .env                     # Environment variables
└── .gitignore
```

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

### Start Developing with Claude Code

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

Initiate agent development by providing a natural language prompt to Claude Code. Claude Code will handle environment setup, learning from best practices, and prompt management.

```bash
claude "Build an agent that can analyze stock prices and provide trading recommendations"
```

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

### Clone the Better Agents Repository

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Clone the repository and navigate into the project directory to begin development setup.

```bash
git clone https://github.com/langwatch/better-agents
cd better-agents
```

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

### Example Evaluation Notebook

Source: https://github.com/langwatch/better-agents/blob/main/docs/STRUCTURE.md

Shows the file naming convention for Jupyter notebooks used for evaluating specific agent pipeline components.

```text
tests/evaluations/example_eval.ipynb
```

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

### generateAgentsGuide

Source: https://github.com/langwatch/better-agents/blob/main/src/documentation/README.md

Generates the AGENTS.md guide file with best practices and guidelines.

```APIDOC
## generateAgentsGuide(projectPath, config)

### Description
Generates the AGENTS.md guide file with best practices and guidelines for agent development.

### Method Signature
`generateAgentsGuide(projectPath, config)`

### Parameters
- **projectPath** (string) - Required - The path to the project for which the guide is being generated.
- **config** (object) - Required - Configuration object for the guide generation process.

### Returns
- `Promise<void>` - A promise that resolves when the guide generation is complete.
```

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

### Install Better Agents CLI

Source: https://github.com/langwatch/better-agents/blob/main/docs/GETTING-STARTED.md

Install the Better Agents command-line interface globally using npm.

```bash
npm install -g @langwatch/better-agents
```

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

### Example Scenario Test File

Source: https://github.com/langwatch/better-agents/blob/main/docs/STRUCTURE.md

Illustrates the file naming convention for end-to-end scenario tests. These tests simulate conversations with the agent.

```text
tests/scenarios/example_scenario.test.{py,ts}
```

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

### Initialize Better Agents Project with npx

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

Initialize a new agent project without global installation using npx. This is a convenient way to run the CLI tool for one-off tasks or testing.

```bash
npx @langwatch/better-agents init my-stock-agent
```

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

### Create a New Agent Framework Provider

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Implement a FrameworkProvider for a new agent framework, including its ID, language, display name, setup logic, and optional MCP configuration.

```typescript
// src/providers/frameworks/your-framework/index.ts
export const YourFrameworkProvider: FrameworkProvider = {
  id: 'your-framework',
  language: 'python', // or 'typescript'
  displayName: 'Your Framework',
  async setup({ projectPath }) {
    // Framework-specific setup
  },
  getMCPConfig() {
    return { command: 'npx', args: [...] }; // optional
  },
  getAgentsGuidelines() {
    return '## Your Framework Guidelines
...';
  },
};
```

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

### Build the Project

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Compile and build the project using pnpm.

```bash
pnpm build
```

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

### setupAgnoTools

Source: https://github.com/langwatch/better-agents/blob/main/src/tool-setup/README.md

Configures framework-specific tools for Agno.

```APIDOC
## setupAgnoTools(projectPath)

### Description
Configures framework-specific tools for Agno.

### Parameters
#### Path Parameters
- **projectPath** (string) - Required - The path to the project directory.

### Returns
- `Promise<void>` - A promise that resolves when the setup is complete.
```

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

### setupMCPServers

Source: https://github.com/langwatch/better-agents/blob/main/src/tool-setup/README.md

Configures MCP (Model Context Protocol) servers for the project.

```APIDOC
## setupMCPServers(projectPath, config)

### Description
Sets up MCP (Model Context Protocol) servers for the agent project.

### Parameters
#### Path Parameters
- **projectPath** (string) - Required - The path to the project directory.
- **config** (object) - Required - Configuration object for MCP servers.

### Returns
- `Promise<void>` - A promise that resolves when the setup is complete.
```

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

### Initialize Agent with AWS Bedrock (Interactive)

Source: https://github.com/langwatch/better-agents/blob/main/docs/USAGE.md

Use this command to interactively set up an agent using AWS Bedrock. The CLI will prompt for language, framework, coding assistant, and goal.

```bash
LANGWATCH_API_KEY="sk-lw-..." \
AWS_ACCESS_KEY_ID="AKIA..." \
AWS_SECRET_ACCESS_KEY="..." \
AWS_REGION="us-east-1" \
better-agents init my-agent
# CLI will prompt for: language, framework, coding assistant, goal
```

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

### Test the CLI Initialization

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Initialize a test project using the CLI to verify its functionality.

```bash
pnpm dev init test-project
```

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

### Initialize Python Agent with Agno (Interactive)

Source: https://github.com/langwatch/better-agents/blob/main/docs/USAGE.md

Use this command to interactively set up a Python agent with Agno and OpenAI. The CLI will prompt for language, framework, coding assistant, and goal.

```bash
LANGWATCH_API_KEY="sk-lw-..." OPENAI_API_KEY="sk-..." better-agents init trading-agent
# CLI will prompt for: language, framework, coding assistant, goal
```

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

### Architectural Overview Diagram

Source: https://github.com/langwatch/better-agents/blob/main/src/builders/README.md

This diagram illustrates the architecture of the builders, showing how 'init.ts' orchestrates the calls to 'buildMCPConfig', 'setupEditorConfigs', and 'buildAgentsGuide' to generate project artifacts like '.mcp.json', '.cursor/mcp.json', and 'CLAUDE.md'.

```text
                    ┌─────────────────┐
                    │   init.ts       │
                    └────────┬────────┘
                             │
        ┌────────────────────┼────────────────────┐
        │                    │                    │
        ▼                    ▼                    ▼
┌───────────────┐  ┌─────────────────┐  ┌─────────────────────┐
│ buildMCPConfig│  │ setupEditorConfigs│ │ buildAgentsGuide    │
│ (returns obj) │──│ (writes files)    │ │ (writes AGENTS.md)  │
└───────────────┘  └─────────────────┘  └─────────────────────┘
                            │
        ┌───────────────────┼───────────────────┐
        │                   │                   │
        ▼                   ▼                   ▼
   .mcp.json         .cursor/mcp.json      CLAUDE.md
                      (symlink)           
```

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

### Complete Python Project with Agno (Non-Interactive)

Source: https://github.com/langwatch/better-agents/blob/main/docs/USAGE.md

Use this command to non-interactively initialize a Python project with Agno, specifying all parameters via command-line arguments.

```bash
LANGWATCH_API_KEY="sk-lw-..." OPENAI_API_KEY="sk-..." better-agents init trading-agent \
  --language python \
  --framework agno \
  --llm-provider openai \
  --coding-assistant cursor \
  --goal "Build an agent that can analyze stock prices and provide trading recommendations"
```

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

### Navigate to Project Directory

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

Use this command to change your current directory to the newly created agent project folder.

```bash
cd my-stock-agent
```

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

### List Project Files

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

This command lists all files and directories within your agent project, showing the generated project structure.

```bash
ls -la
```

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

### Manage Prompts

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

List available prompts and push local prompt files to the LangWatch platform.

```bash
langwatch prompts list
```

```bash
langwatch prompts push prompts/stock_analysis.yaml
```

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

### Initialize Better Agents in Current Directory

Source: https://github.com/langwatch/better-agents/blob/main/README.md

Initialize Better Agents within the current directory. The CLI will prompt for project configuration details.

```bash
better-agents init .
```

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

### Run Project Tests

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Execute the project's test suite using pnpm.

```bash
pnpm test
```

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

### Development Guidelines File

Source: https://github.com/langwatch/better-agents/blob/main/docs/STRUCTURE.md

Contains development guidelines for ensuring features are tested, evaluated, and prompts are versioned.

```text
AGENTS.md
```

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

### Prompt Registry File

Source: https://github.com/langwatch/better-agents/blob/main/docs/STRUCTURE.md

The standard file for registering and managing prompts within the project.

```text
prompts.json
```

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

### Initialize Agent with AWS Bedrock (Non-Interactive)

Source: https://github.com/langwatch/better-agents/blob/main/docs/USAGE.md

Use this command to non-interactively initialize an agent using AWS Bedrock, specifying all parameters via command-line arguments.

```bash
LANGWATCH_API_KEY="sk-lw-..." \
AWS_ACCESS_KEY_ID="AKIA..." \
AWS_SECRET_ACCESS_KEY="..." \
better-agents init my-agent \
  --language typescript \
  --framework vercel-ai \
  --llm-provider bedrock \
  --aws-region us-west-2 \
  --coding-assistant cursor \
  --goal "Build a content generation agent"
```

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

### Initialize TypeScript Agent with Mastra (Interactive)

Source: https://github.com/langwatch/better-agents/blob/main/docs/USAGE.md

Use this command to interactively set up a TypeScript agent with Mastra and Anthropic. The CLI will prompt for language, framework, coding assistant, and goal.

```bash
LANGWATCH_API_KEY="sk-lw-..." ANTHROPIC_API_KEY="sk-ant-..." better-agents init customer-support
# CLI will prompt for: language, framework, coding assistant, goal
```

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

### Run Agent

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

Execute the main Python script to run your agent.

```bash
python app/main.py
```

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

### Agent Implementation: app/main.py

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

The main Python file for the agent, importing necessary libraries like Agent from 'agno' and 'langwatch'.

```python
# app/main.py
from agno import Agent
import langwatch

# Agent code following Agno patterns...
```

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

### Read AGENTS.md

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

Use the 'cat' command to display the contents of the AGENTS.md file, which contains project guidelines and best practices.

```bash
cat AGENTS.md
```

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

### Agent Project Structure Overview

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

This visual representation details the standard directory and file structure generated for a Better Agents project, including directories for application code, prompts, tests, and configuration files.

```bash
my-stock-agent/
├── app/                          # Main application code
│   └── main.py
├── prompts/                      # Versioned prompt files
│   └── sample_prompt.yaml
├── tests/                        # Scenario tests
│   ├── evaluations/             # Jupyter notebooks for evaluations
│   │   └── example_eval.ipynb
│   └── scenarios/               # Scenario tests
│       └── example_scenario.test.py
├── .mcp.json                    # MCP server configuration (universal)
├── .cursor/
│   └── mcp.json                 # Symlink to ../.mcp.json for Cursor
├── AGENTS.md                    # Development guidelines
├── CLAUDE.md                    # References AGENTS.md for Claude Code
├── .env                         # Your API keys (DO NOT COMMIT!)
├── .env.example                 # Template for API keys
├── .gitignore
└── prompts.json                 # Prompt registry
```

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

### Prompt Creation: prompts/stock_analysis.yaml

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

Defines the configuration for the stock analysis prompt, including the model to use, temperature, and system message.

```yaml
# prompts/stock_analysis.yaml
model: gpt-4o
temperature: 0.7
messages:
  - role: system
    content: |
      You are a stock analysis expert...
```

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

### Initialize a New Agent (Non-Interactive Mode)

Source: https://github.com/langwatch/better-agents/blob/main/docs/USAGE.md

Configure and initialize a new agent project non-interactively by providing all necessary details as CLI arguments and environment variables. This is useful for scripting and automation.

```bash
LANGWATCH_API_KEY="sk-lw-..." ANTHROPIC_API_KEY="sk-ant-..." better-agents init my-agent \
  --language python --framework agno --llm-provider anthropic \
  --coding-assistant cursor --goal "Build a trading agent"
```

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

### Create a New Language Provider

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Implement a LanguageProvider for a new programming language, specifying its ID, display name, source directory, and test file extension.

```typescript
export const YourLanguageProvider: LanguageProvider = {
  id: 'your-language',
  displayName: 'Your Language',
  sourceDir: 'src', // or 'app'
  testFileExtension: '.test.yourlang',
  // Add language-specific configuration
};
```

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

### Initialize LangGraph Python Agent with Gemini (Non-Interactive)

Source: https://github.com/langwatch/better-agents/blob/main/docs/USAGE.md

Use this command to non-interactively initialize a Python agent using LangGraph and Gemini, specifying all parameters via command-line arguments.

```bash
LANGWATCH_API_KEY="sk-lw-..." GOOGLE_API_KEY="..." better-agents init research-agent \
  --language python \
  --framework langgraph-py \
  --llm-provider gemini \
  --coding-assistant cursor \
  --goal "Build a research agent that can gather and summarize information from multiple sources"
```

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

### Create a New Coding Assistant Provider

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Implement a CodingAssistantProvider for a new assistant, including its ID, display name, command, availability check, and launch logic.

```typescript
// src/providers/coding-assistants/your-assistant/index.ts
export const YourAssistantProvider: CodingAssistantProvider = {
  id: 'your-assistant',
  displayName: 'Your Assistant',
  command: 'your-cli-command',
  async isAvailable() {
    // Check if the assistant CLI is installed
    return { installed: true, installCommand: 'npm install -g your-cli' };
  },
  async launch({ projectPath, prompt }) {
    // Launch the assistant with the initial prompt
  },
};
```

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

### Environment Variables File

Source: https://github.com/langwatch/better-agents/blob/main/docs/STRUCTURE.md

Standard file for storing environment variables for the project.

```text
.env
```

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

### MCP Server Configuration File

Source: https://github.com/langwatch/better-agents/blob/main/docs/STRUCTURE.md

Configuration file for the MCP server, providing framework expertise and tool access to the coding assistant.

```text
.mcp.json
```

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

### Initialize TypeScript Agent with Mastra and Claude (Non-Interactive)

Source: https://github.com/langwatch/better-agents/blob/main/docs/USAGE.md

Use this command to non-interactively initialize a TypeScript agent with Mastra and Claude, specifying all parameters via command-line arguments.

```bash
LANGWATCH_API_KEY="sk-lw-..." ANTHROPIC_API_KEY="sk-ant-..." better-agents init customer-support \
  --language typescript \
  --framework mastra \
  --llm-provider anthropic \
  --coding-assistant claude-code \
  --goal "Build a customer support agent that can handle common queries and escalate complex issues"
```

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

### Cursor IDE MCP Configuration Symlink

Source: https://github.com/langwatch/better-agents/blob/main/docs/STRUCTURE.md

A symlink to the main .mcp.json file, specifically for compatibility with the Cursor IDE.

```text
.cursor/mcp.json
```

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

### Run Tests

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

Execute scenario tests using pytest.

```bash
pytest tests/scenarios/
```

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

### Scenario Tests: tests/scenarios/stock_analysis.test.py

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

A Python test file for defining and running scenario tests for the stock analysis agent using LangWatch Scenario.

```python
# tests/scenarios/stock_analysis.test.py
"""Test stock analysis agent scenarios"""

def test_analyze_stock():
    # Scenario test using LangWatch Scenario
    pass
```

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

### Create a New Feature Branch

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Create a new branch for your feature development using Git.

```bash
git checkout -b feature/your-feature-name
```

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

### Test CLI Interactions with CLITestRunner

Source: https://github.com/langwatch/better-agents/blob/main/src/__tests__/utils/README.md

Use CLITestRunner to simulate user interactions with the CLI, including command execution, prompt responses, and output/file assertions. Remember to call cleanup() after tests.

```typescript
import { CLITestRunner } from "./utils/cli-test-runner.js";

it("creates a project", async () => {
  const runner = new CLITestRunner();

  await runner
    .command('init', 'my-project')
    .expectPrompt('What programming language')
    .input('typescript')
    .expectPrompt('What agent framework')
    .input('agno')
    .expectOutput('Project setup complete')
    .expectFile('src/main.ts')
    .expectFileToMatchInlineSnapshot('package.json')
    .run();

  await runner.cleanup();
});
```

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

### Claude Code Compatibility File

Source: https://github.com/langwatch/better-agents/blob/main/docs/STRUCTURE.md

References AGENTS.md for Claude Code compatibility, ensuring project works with AI coding editors.

```text
CLAUDE.md
```

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

### Evaluations: tests/evaluations/stock_eval.ipynb

Source: https://github.com/langwatch/better-agents/blob/main/docs/WALKTHROUGH.md

A Jupyter notebook used for evaluating the performance of the stock analysis agent, focusing on accuracy, response quality, and tool usage.

```python
# tests/evaluations/stock_eval.ipynb
# Jupyter notebook evaluating:
# - Accuracy of stock recommendations
# - Response quality
# - Tool usage effectiveness
```

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

### Git Ignore File

Source: https://github.com/langwatch/better-agents/blob/main/docs/STRUCTURE.md

Standard Git ignore file to specify intentionally untracked files that Git should ignore.

```text
.gitignore
```

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

### Opt-out of Telemetry

Source: https://github.com/langwatch/better-agents/blob/main/README.md

Disable anonymous usage telemetry for Better Agents by setting the BETTER_AGENTS_TELEMETRY environment variable to 0. Telemetry is enabled by default.

```bash
BETTER_AGENTS_TELEMETRY=0
```

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

### Update Agent Framework Types

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Add a new agent framework to the AgentFramework type definition in src/types.ts.

```typescript
export type AgentFramework = 'agno' | 'mastra' | 'your-framework';
```

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

### Update Coding Assistant Types

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Add a new coding assistant to the CodingAssistant type definition in src/types.ts.

```typescript
export type CodingAssistant = 'claude-code' | 'cursor' | 'kilocode' | 'your-assistant' | 'none';
```

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

### Update Programming Language Types

Source: https://github.com/langwatch/better-agents/blob/main/docs/CONTRIBUTING.md

Add a new programming language to the ProgrammingLanguage type definition in src/types.ts.

```typescript
export type ProgrammingLanguage = 'python' | 'typescript' | 'your-language';
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.