langwatch/better-agents

Standards for building agents, better

What it solves

Better Agents provides a standardized project structure and CLI tool to help developers build production-ready AI agents. It eliminates the guesswork of how to organize agentic workflows, prompt versioning, and testing strategies, ensuring that agents are maintainable and reliable up to production standards.

How it works

The tool initializes a new project with a curated directory structure that separates agent code, versioned prompts, and evaluation notebooks. It integrates with coding assistants (like Cursor or Claude Code) via MCP servers to make those assistants experts in specific agent frameworks (such as Agno, Mastra, or LangGraph). It also incorporates a system for writing scenario tests to simulate conversations and verify agent behavior.

Who it’s for

Developers building AI agents who want to move from a prototype to a production-ready system using industry best practices for structure, testing, and observability.

Highlights

  • Standardized Structure: Establishes a clear layout for app code, prompts, and tests.
  • Coding Assistant Integration: Uses .mcp.json to provide context to AI coding tools about the chosen framework and testing standards.
  • Prompt Versioning: Stores prompts in YAML format with a registry to facilitate team collaboration.
  • Testing Pyramid: Implements scenario-based end-to-end tests and Jupyter notebooks for specific pipeline evaluations.
  • Observability: Projects are pre-instrumented for full observability via LangWatch.