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.

Related

  • Project
    HKUDS/CLI-Anything

    CLI‑Anything is an open‑source Python framework that automatically generates agent‑friendly command‑line wrappers for any software. It ships a package manager (`cli‑anything‑hub`) that indexes dozens of community‑built CLIs (GIMP, Blender, Zoom, GIS tools, etc.) and lets agents discover, install, and invoke them via structured JSON output. Developers can use a 7‑phase generator to create new CLIs for any application, and AI agents (Claude Code, Cursor, Pi, OpenClaw, …) can install the meta‑skill to browse the registry autonomously. The project is actively maintained, well‑tested (2 461 passing tests), and Apache‑2.0 licensed.

  • Project
    vercel-labs/skills

    A CLI that discovers, installs, updates, and runs reusable prompt bundles (“skills”) for many AI coding assistants (Claude Code, Cursor, OpenCode, etc.), pulling them from any Git repository or direct URL.

  • Project
    google/agents-cli

    agents‑cli is a Google‑maintained CLI (and skill bundle for AI coding assistants) that streamlines the entire lifecycle of Gemini‑based AI agents—from project scaffolding and local evaluation to cloud deployment, CI/CD, and observability.

  • Project
    NVIDIA/NeMo-Agent-Toolkit

    NVIDIA NeMo Agent Toolkit (NAT) is an open‑source Python SDK that adds enterprise‑grade instrumentation, profiling, and optimisation to LLM‑based AI agents. It works with popular frameworks (LangChain, CrewAI, Semantic Kernel, etc.) and provides a CLI (`nat`), a UI, protocol support (MCP, A2A), and experimental runtime intelligence (Dynamo). Install via `pip install nvidia-nat` and define agent workflows in YAML to run, evaluate, or serve them.

  • Project
    alibaba/open-code-review

    An AI-powered code review CLI tool that combines deterministic engineering with an AI agent to provide high-precision, token-efficient reviews of Git diffs and full files.