DEV.co
AI Frameworks · langwatch

better-agents

Better Agents is a CLI tool and standards framework for building AI agents across multiple frameworks (Agno, Mastra, LangGraph, etc.). It provides project scaffolding, prompt versioning, scenario-based testing, and evaluation notebooks to accelerate agent development with coding assistants.

Source: GitHub — github.com/langwatch/better-agents
1.5k
GitHub stars
154
Forks
TypeScript
Primary language
MIT
License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

FieldValue
Repositorylangwatch/better-agents
Ownerlangwatch
Primary languageTypeScript
LicenseMIT — OSI-approved
Stars1.5k
Forks154
Open issues15
Latest releasev0.1.23 (2026-02-22)
Last updated2026-06-03
Sourcehttps://github.com/langwatch/better-agents

What better-agents is

TypeScript-based CLI that generates standardized agent project structures with integrated testing infrastructure (Scenario tests for behavior validation, Jupyter notebooks for evaluations), prompt management via YAML with version control, MCP configuration for coding assistants, and LangWatch observability hooks.

Quickstart

Get the better-agents source

Clone the repository and explore it locally.

terminalbash
git clone https://github.com/langwatch/better-agents.gitcd better-agents# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Rapid Agent Prototyping

Teams starting new agent projects can use the CLI to scaffold a complete, best-practices structure in minutes, with all testing and evaluation infrastructure pre-configured and ready to extend.

Multi-Framework Agent Development

Organizations evaluating or supporting multiple agent frameworks (Agno, Mastra, LangGraph) can maintain consistent project structure, testing patterns, and prompt management across all variants.

Prompt Experimentation & Collaboration

Teams can version prompts in YAML, evaluate performance changes via Jupyter notebooks, and iterate safely with full observability—enabling structured prompt engineering workflows rather than ad-hoc changes.

Implementation considerations

  • Requires Node.js 22+; verify target environment supports this version before adoption.
  • Mandatory setup flow includes selecting framework, coding assistant, and LLM provider; ensure team standardizes choices before widespread rollout.
  • LangWatch API key is required for prompt management and observability features; factor in account creation and authentication workflow.
  • Telemetry is enabled by default (opt-out via BETTER_AGENTS_TELEMETRY=0); review org's data practices and inform teams.
  • Scenario tests and evaluation notebooks introduce new testing paradigms; training and documentation review needed for consistent adoption.

When to avoid it — and what to weigh

  • Requires Non-Node.js Agent Runtime — The CLI is Node.js-based and strongly assumes TypeScript/JavaScript agents. Projects needing pure Python or Go agents may find the scaffolding and MCP setup misaligned with their stack.
  • No LangWatch Integration Needed — The framework is heavily integrated with LangWatch for observability and prompt management. Teams already using competing observability platforms or internal prompt stores may see friction and lock-in concerns.
  • Strict Independence from Third-Party Platforms — Setup requires API keys from LangWatch and external LLM providers. Organizations with airgapped environments or policies against external SaaS integrations should avoid this scaffolding approach.
  • Existing Mature Agent Codebases — Projects with established agent architectures and testing patterns may find retrofitting the Better Agents structure costly; the tool is optimized for greenfield projects, not legacy refactoring.

License & commercial use

MIT License (permissive OSI license). Allows commercial use, modification, and distribution with minimal restrictions; only requires retention of copyright and license notice.

MIT license permits commercial use without explicit restriction. However, the tool's integration with external platforms (LangWatch, LLM providers) introduces dependency considerations. Users should review LangWatch's terms of service for production use and clarify any data-use clauses. No special commercial license or support agreement is bundled in the repo.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

SignalAssessment
MaintenanceActive
DocumentationStrong
License clarityClear
Deployment complexityLow
DEV.co fitGood
Assessment confidenceHigh
Security considerations

Security posture not detailed in provided data. Considerations: (1) LangWatch API key and LLM provider credentials must be secured via .env; telemetry opt-out is available but enabled by default. (2) MCP configuration exposes coding assistant integrations; review MCP scope and permissions. (3) Prompt versioning in version control should avoid hardcoding secrets. (4) No mention of input validation, rate limiting, or prompt injection safeguards in the README. Teams should conduct security review before production use and enforce credential rotation policies.

Alternatives to consider

LangChain Hub + LangServe

Offers prompt versioning and deployment tooling but less opinionated structure; requires more manual scaffolding and testing setup. Better Agents provides more standardized templates.

Mastra (native)

If standardizing on Mastra framework only, using Mastra's own templates may reduce external dependencies. Better Agents trades Mastra-only focus for multi-framework flexibility.

Prompt Flow (Azure/Microsoft)

Enterprise-grade orchestration with built-in evaluation and monitoring, but tightly coupled to Azure ecosystem. Better Agents is more framework-agnostic and CLI-driven for local dev.

Software development agency

Build on better-agents with DEV.co software developers

Use Better Agents to scaffold production-ready AI agent projects with integrated testing, prompt management, and observability—in minutes. Start with npm install -g @langwatch/better-agents or npx @langwatch/better-agents init my-agent-project. Review LangWatch integration and team workflow requirements before rollout.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

Related on DEV.co

Explore the category and the services that help you build with it.

better-agents FAQ

Does Better Agents lock us into LangWatch?
The CLI scaffolds projects with LangWatch observability and prompt management built-in. Core functionality (scaffolding, Scenario tests, evaluations) works without LangWatch, but prompt versioning and observability features strongly assume LangWatch. Evaluate carefully if your org uses competing platforms.
Can we use Better Agents with pure Python agents?
The CLI is Node.js/TypeScript. It can scaffold Python agent code (listed in topics), but the testing infrastructure (Scenario tests) and MCP setup are optimized for JavaScript/TypeScript. Python support appears partial; verify in detailed docs before committing.
What if we already have agent projects underway?
Better Agents is designed for greenfield projects. Retrofitting existing codebases to match the Better Agent Structure would require refactoring tests, prompts, and project layout. Consider it for new initiatives, not legacy rework.
How often is Better Agents updated?
Active maintenance with recent commits (June 2026). v0.1.x versioning suggests early-stage; breaking changes are possible. Monitor releases and test updates in non-production first.

Custom software development services

DEV.co helps companies turn open-source tools like better-agents into production software. Our software development services cover the full lifecycle — architecture, web development, integration, and maintenance — delivered by software developers and web developers who ship. Engage our software development agency to implement or customize it for your ai frameworks stack.

Standardize Your Agent Development Today

Use Better Agents to scaffold production-ready AI agent projects with integrated testing, prompt management, and observability—in minutes. Start with npm install -g @langwatch/better-agents or npx @langwatch/better-agents init my-agent-project. Review LangWatch integration and team workflow requirements before rollout.