Get started with Better Agents in 2 minutes! 🚀
npm install -g @langwatch/better-agentsOr use npx (no installation):
npx @langwatch/better-agents init my-agentbetter-agents init my-agentFollow the prompts:
- Language: Python or TypeScript
- Framework: Agno (Python) or Mastra (TypeScript)
- Coding Assistant: Claude Code, Cursor, Antigravity, Kilocode CLI, or None
- LLM Provider: OpenAI, Anthropic, Gemini, Bedrock, OpenRouter, or Grok
- API Keys: Your chosen LLM Provider API key and LangWatch API key
- Project Goal: Describe what you want to build
my-agent/
├── app/ (or src/) # Your agent code
├── prompts/ # Versioned prompts
├── tests/
│ ├── evaluations/ # Performance evaluation notebooks
│ └── scenarios/ # End-to-end scenario tests
├── AGENTS.md # Development guidelines
├── CLAUDE.md # References AGENTS.md for Claude Code
├── .mcp.json # MCP server configuration (universal)
└── .cursor/mcp.json # Symlink to .mcp.json for Cursor
cd my-agent
# Launch your coding assistant (it will be auto-launched after setup)Your coding assistant is now an expert in:
- Your chosen framework (Agno/Mastra)
- LangWatch best practices
- Prompt management
- Agent testing
✅ Agent Testing Pyramid - Unit tests + Evals + Simulations ✅ Prompt Management - Version controlled prompts ✅ MCP Integration - Expert guidance built-in ✅ Production Ready - Best practices from day one
- Node.js 18+
- npm or pnpm
- A coding assistant (one of the following):
- Claude Code (
claudeCLI) - Cursor
- Antigravity (
agy) - Kilocode CLI (
kilocode)
- Claude Code (
- API Keys:
- Your chosen LLM Provider API key
- LangWatch API key (get one at https://app.langwatch.ai/authorize)
- Full Walkthrough: Walkthrough Guide
- Dashboard: https://app.langwatch.ai/
- Scenario Docs: https://scenario.langwatch.ai/
Questions? Open an issue on GitHub!