AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
better-agents
better-agents logo

better-agents

Active·★ 1.6k·MIT·Updated 2026-06-03

Better Agents is a CLI and a set of standards for starting agent projects. Run `better-agents init my-project` and it walks you through choosing a language, an agent framework (the README names Agno, Mastra and LangGraph), a coding assistant, an LLM provider and API keys. It then generates a project in a fixed layout meant to make the agent production-ready and to make your coding assistant an expert in the chosen framework.

The layout has the agent code in `app/` or `src/`, `tests/scenarios/` for end-to-end Scenario tests that simulate conversations, `tests/evaluations/` for Jupyter notebooks measuring parts like RAG or classification, versioned YAML prompts in `prompts/` with a `prompts.json` registry, a `.mcp.json` with MCP servers for the framework and for writing Scenario tests, and an `AGENTS.md` of guidelines requiring each feature to be tested, evaluated and instrumented for observability. The approach is called the Agent Testing Pyramid.

Requirements are Node.js 22+, one supported coding assistant (Claude Code, Cursor, Antigravity or Kilocode CLI), a LangWatch API key and your LLM provider key. Anonymous usage telemetry is on by default and can be turned off with `BETTER_AGENTS_TELEMETRY=0`. Better Agents comes from LangWatch, so the generated project is wired to their observability and prompt tools. Licence is MIT and the last push was 2026-06-03. This review is based on the README and repository data; we have not run it ourselves.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-22.

License
MIT
Latest release
v0.1.23 · 2026-02-22
Last commit
2026-06-03
Contributors
11
Forks
148
Open issues and PRs
16
First published
2025-04-19
npm package
@langwatch/better-agents 0.1.23 · 11 downloads last week

Source: GitHub, npm and PyPI public APIs.

#CLI#Agent Development#AI Agents#Prompt Management#Testing
$ Install
$ npm install -g @langwatch/better-agents
↗ Visit site★ GitHub
01

Features

01Standardized Agent Project Structure
02End-to-end Agent Scenario Testing
03Versioned Prompt Management
04Performance Evaluation Notebooks
05Built-in Observability
02

Why choose it

+One command sets up tests, evals, versioned prompts and observability in a consistent layout
+Generated AGENTS.md and .mcp.json steer Claude Code, Cursor and others toward the chosen framework
+Supports frameworks such as Agno, Mastra and LangGraph
+MIT license; telemetry can be switched off
03

Trade-offs

!Needs a LangWatch API key, so the generated project leans on one vendor's tooling
!Anonymous telemetry is on by default and has to be turned off with an environment variable
!Opinionated structure that may not fit an existing project, since it is built for new ones
!Needs Node.js 22+ and one of a short list of supported coding assistants
04

Maintenance check

SlowingChecked: 2026-10-18
Last commit
2026-05-11
Commits, last 90 days
0
Releases, last 90 days
0
Latest release
v0.1.23 (2026-02-22)
Open issues
16
Recent issues with at least one comment
4/20
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #71 Agent-Specific CLI Generation with Tool-to-Command Mapping3 comments · 2025-12-08
  • #27 [Feature]: CLI should prompt for target directory and project name when creating a better agent1 comments · 2025-11-20
  • #94 feature request: document optional Parallel web research for Claude Code0 comments · 2026-10-17
  • #88 GNAP: a candidate standard for git-native agent coordination0 comments · 2026-03-15
  • #83 better agents did not recognize the Kilo Code CLI.0 comments · 2026-02-07

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Claude Code
Supported
Verified via docs
Cursor
Supported
Verified via docs
Antigravity
Supported
Verified via docs
Kilocode CLI
Supported
Verified via docs
06

Quick start

1
$ npm install -g @langwatch/better-agents
07

Use cases

↳Kickstarting new AI agent projects with industry best practices.
↳Integrating and leveraging various agent frameworks with coding assistants.
↳Developing and maintaining production-ready, testable, and observable agents.
08

Alternatives

⚡Top VS:
VSCopilotKit★38.2k→VSagents-towards-production★21.7k→VSinspector★11.1k→VSai-agents-from-scratch★4.9k→
CopilotKit logo
CopilotKit★ 38.2k
React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic Frontend.
VSCompare→
agents-towards-production logo
agents-towards-production★ 21.7k
This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for real-world launches.
VSCompare→
inspector logo
inspector★ 11.1k
Visual testing tool for MCP servers
VSCompare→
ai-agents-from-scratch logo
ai-agents-from-scratch★ 4.9k
Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.
VSCompare→
mockserver-monorepo logo
mockserver-monorepo★ 5.0k
MockServer is an HTTP(S) mock server and proxy for testing that lets you mock APIs, inspect and modify live traffic, and inject failures. It supports HTTP/1.1, HTTP/2, gRPC, WebSockets, TCP and more on a single port, with additional support for HTTP/3, message brokers, and AI/LLM APIs.
VSCompare→
nunu logo
nunu★ 2.6k
A CLI tool for building Go applications.
VSCompare→
whodb logo
whodb★ 5.0k
Where data access meets operational intelligence
VSCompare→
skillhub logo
skillhub★ 5.3k
Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
langwatch /
better-agents
↗

MIT CLI that scaffolds agent projects with tests, evals, versioned prompts and an AGENTS.md so your coding assistant follows best practice

1.6k148MIT
Last commit4mo ago
StatusActive
CategoryDev Tooling
Contributors11
Latest releasev0.1.23
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.