Better Agents

Better Agents is a CLI tool and a set of standards for agent building.

It supercharges your coding assistant (Kilocode, Claude Code, Cursor, etc), making it an expert in any agent framework you choose (Agno, Mastra, etc) and all their best practices.

It's the best way to start any new agent project.

The Better Agent Structure and generated AGENTS.md ensures industry best practices, making your agent ready for production:

• Scenario agent tests written for every feature to ensure agent behaviour
• Versioning of the prompts for collaboration
• Evaluation notebooks for measuring specific prompts performance
• Already instrumented for full observability
• Standardization of structure for better project maintainability

The Better Agent Structure

my-agent-project/
├── app/ (or src/)           # The actual agent code, 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
├── AGENTS.md                # Development guidelines
├── .env                     # Environment variables
└── .gitignore

The structure and guidelines on AGENTS.md ensure every new feature required for the coding assistant is properly tested, evaluated, and that the prompts are versioned.

The .mcp.json comes with all the right MCPs set up so you coding assistant becomes an expert in your framework of choice and know where to find new tools.

scenarios/ tests guarantee the agent behaves as expected, which simulates a conversation with the agent making sure it does what expected.

evaluations/ notebooks holds dataset and notebooks for evaluating pieces of your agent pipeline such as a RAG or classification tasks it must do

Finally, prompts/ hold all your versioned prompts in yaml format, synced and controlled by prompts.json, to allow for playground and team collaboration.

Getting Started

Installation

npm install -g @langwatch/better-agents

Or use with npx:

npx @langwatch/better-agents init my-agent-project

Initialize a new project

# In current directory
better-agents init .

# In a new directory
better-agents init my-awesome-agent

The CLI will guide you through selecting your programming language, agent framework, coding assistant, LLM provider, and API keys.

Documentation

• Getting Started - Quick start guide (2 minutes)
• Walkthrough - Detailed step-by-step guide
• Project Structure - Understanding the Better Agent structure
• Features - Key features and capabilities
• Usage - CLI usage and examples
• Philosophy - Agent Testing Pyramid approach
• Contributing - How to contribute to Better Agents
• Changelog - Version history

Requirements

• Node.js 22+
• npm or pnpm
• A coding assistant (one of the following):
  • Claude Code (claude CLI)
  • Cursor
  • Kilocode CLI (kilocode)
• API Keys:
  • Your chosen LLM Provider API key
  • LangWatch API key (get one at https://app.langwatch.ai/authorize)
  • Smithery API key (optional - for MCP tool auto-discovery, get one at https://smithery.ai/account/api-keys)

Resources

• LangWatch
• Scenario Documentation
• Agent Testing Pyramid
• Agno
• Mastra

License

MIT

---

Built with ❤️ by the LangWatch team