Better Agents
Scaffold agent projects with testing, evaluation, prompt versioning, observability, and MCP-ready development conventions.
- Source repo
- langwatch/better-agents
- Stars
- ★ 1.6k
- Last updated
- 6mo ago
- License
- MIT
- Primary language
- TypeScript
- FA score
- 44/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformClaude Code
- Cost
- Free software; you pay for model usage
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A developer starting an Agno project with Claude Code who wants Scenario end-to-end tests and versioned prompts from the first iteration.
- Not a fit if
- Teams wanting a ready runtime: it only scaffolds projects
- Teams avoiding a LangWatch cloud account and API key
- Developers not using Claude Code, Cursor, Antigravity, or Kilocode
- Maintenance
- No commits for 6+ monthslast commit 2026-05-11latest release v0.1.23 (2026-02-22)
- Source review
- 44/100 · Major gaps 1 safety controls not found
What does this agent do, and when should you use it?
Better Agents is a CLI and set of development standards for initializing new agent projects. It is designed to work alongside a selected agent framework, including Agno, Mastra, and LangGraph, and supported coding assistants such as Claude Code, Cursor, Antigravity, and Kilocode CLI. Its generated project layout includes application code, Scenario end-to-end tests, evaluation notebooks, versioned prompts, a prompt registry, MCP configuration, and AGENTS.md guidance. The product produces and standardizes a local project foundation; it is not documented as a hosted agent runtime. It fits teams that want testing, prompt collaboration, evaluation, and observability conventions in place from project creation.
Running better-agents init . or better-agents init my-awesome-agent starts an interactive CLI flow for selecting a programming language, agent framework, coding assistant, LLM provider, and API keys. It creates project assets including app/ or src/, tests/scenarios/, tests/evaluations/, prompts/, prompts.json, .mcp.json, AGENTS.md, .env, and .gitignore. tests/scenarios/ is for Scenario end-to-end conversational tests, while tests/evaluations/ holds datasets and notebooks for evaluating pipeline tasks such as RAG and classification. Prompts are stored as versioned YAML files under prompts/ and controlled through prompts.json; .mcp.json configures MCP servers for the selected coding assistant.
- A developer starting an Agno project with Claude Code who wants Scenario end-to-end tests and versioned prompts from the first iteration.
- A Mastra team that needs YAML prompt files and
prompts.jsonto coordinate prompt work across collaborators. - An engineering team building a LangGraph workflow with RAG or classification steps that needs a place for evaluation datasets and notebooks.
- A technical lead standardizing new agent repositories around MCP configuration, observability, tests, and project conventions.
- A Cursor, Antigravity, or Kilocode CLI user who wants a consistent starting structure for a new agent codebase.
Key setup facts
Pulled from the install and usage notes below. The project README has the current values.
- Install / run
npm install -g @langwatch/better-agentsnpx @langwatch/better-agents init my-agent-project
- Runtime
- Node.js 22+
How do you install or deploy this agent?
Requirements are Node.js 22+, npm or pnpm, a supported coding assistant, a LangWatch API key, and an API key for the selected LLM provider. Install globally with npm install -g @langwatch/better-agents. Or run without a global installation: npx @langwatch/better-agents init my-agent-project.
How do you use this agent?
Initialize the current directory with better-agents init ., or create and initialize a new directory with better-agents init my-awesome-agent. Follow the CLI prompts to select the language, framework, coding assistant, LLM provider, and required API keys. Anonymous usage telemetry is enabled by default; set BETTER_AGENTS_TELEMETRY=0 to opt out.
What are this agent's strengths and limitations?
- Scaffolds Scenario end-to-end testing, evaluation notebooks, versioned prompts, and a prompt registry together rather than only creating application folders.
- Includes
.mcp.jsonso MCP configuration for the chosen framework and Scenario testing can be part of the new project. - The initialization flow supports choices of language, agent framework, coding assistant, and LLM provider.
- Separates behavioral tests, offline evaluation work, and prompt assets into explicit
tests/scenarios/,tests/evaluations/, andprompts/locations.
- Requires Node.js 22+ and npm or pnpm.
- Adoption requires both a LangWatch API key and an API key for the chosen LLM provider.
- The documented coding-assistant choices are limited to Claude Code, Cursor, Antigravity, and Kilocode CLI.
- It establishes project structure and guidance rather than supplying a deployed runtime; the actual framework implementation remains the project’s responsibility.
How does this agent compare with similar options?
Better Agents is complementary to Agno, Mastra, and LangGraph: those frameworks hold the agent implementation, while Better Agents scaffolds the surrounding testing, evaluation, prompt, and MCP conventions. It also works with, rather than replaces, coding assistants including Claude Code, Cursor, Antigravity, and Kilocode CLI.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Better Agents This agent | 44 · Major gaps | CLIFree + model costs | ★ 1.6k | 6mo ago | TypeScript | Claude Code |
| RocketRide | 84 · Good | — | ★ 20k | today | Python | — |
| Hypha | 55 · Major gaps | Self-hosted serviceFree + model costs | ★ 452 | 5d ago | TypeScript | OpenAI API |
| Rulesync | 71 · Some gaps | CLIFree | ★ 1.6k | 1d ago | TypeScript | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The CLI requires API keys through environment variables and documents an opt-out for anonymous telemetry, reducing the risk of exposing keys in arguments. Telemetry is enabled by default, however, and the sample does not describe event fields or retention, so least privilege, data-flow transparency, and external-effects controls are only partial. Initialization automatically launches the selected coding assistant; confirmation and rollback for generated files or external actions are not documented. The MIT license is clear and the author field names LangWatch, but publisher identity is unverified and does not establish maintenance ownership.
The repository configures CI for type checking, build, lint, unit tests, and end-to-end tests; that shows a validation process exists, not its results. Node requirements conflict across sources (README says 22+, quick start says 18+, and package.json says >=18), as do some assistant and framework lists. Failure behavior is only lightly documented, including initialization and telemetry errors.
The documentation targets developers building Python or TypeScript agents with coding assistants and names several frameworks, model providers, and setup modes. CLI options constrain language, framework, and goal, but supported combinations, capability boundaries, and environment compatibility are not fully documented; automatic assistant launch also limits workflow flexibility.
README, quick start, usage guide, license, and changelog entry provide a usable information structure, install commands, and concrete examples. The MIT text is complete and a package version is present, but requirements and feature lists conflict across documents, known limitations are not covered, and maintenance responsibility is not clearly established. A contributing guide is linked but its contents are not included.
The product offers a project structure for agent code, tests and evaluations, prompt management, and coding-assistant context, giving new projects a potentially useful starting point. The sample supports these benefits mainly through feature descriptions; it does not show generated output details or cost evidence. Default telemetry and API-key setup add configuration overhead.
Operational claims about installation, options, and environment variables are partly represented in both CLI code and documentation, while stronger claims such as production readiness and ensuring best practices lack outcome evidence in this sample. README, quick start, and package.json disagree on Node requirements and supported options. This is a static sample, so behavior and test outcomes remain unverified.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Node.js requirements and some assistant/framework lists differ across the README, quick start, usage guide, and package.json; check the actual CLI options before relying on a documented combination.
- Telemetry is enabled by default. The sample gives an opt-out variable but does not describe collected fields, destination details, or retention.
- The selected coding assistant is automatically launched after setup; the sample does not describe overwrite confirmation or recovery for generated files.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
[0.1.23](https://github.com/langwatch/better-agents/compare/v0.1.22...v0.1.23) (2026-02-22) Features * pass LANGWATCH_API_KEY to MCP server config ([#84](https://github.com/langwatch/better-agents/issues/84)) ([8ab576e](https://github.com/langwatch/better-agents/commit/8ab576ecc12eca6d1da3526983f04212d857ca6a))View on GitHub ↗ -
Release notes excerpt
[0.1.20](https://github.com/langwatch/better-agents/compare/v0.1.20...v0.1.20) (2025-12-11) Features * add non-interactive mode with CLI options ([#77](https://github.com/langwatch/better-agents/issues/77)) ([0ff5bd1](https://github.com/langwatch/better-agents/commit/0ff5bd1c74782ba6b808ac415906e666cf368552)) Miscellaneous * release v0.1.20 ([c799e6c](https://github.com/langwatch/better-agents/commit/c799e6cfc81120bf1f43848b44d272587967a7be))View on GitHub ↗ -
Release notes excerpt
[0.1.20](https://github.com/langwatch/better-agents/compare/v0.1.19...v0.1.20) (2025-12-09) Features * cursor-agent(mac) ([#59](https://github.com/langwatch/better-agents/issues/59)) ([75f51f7](https://github.com/langwatch/better-agents/commit/75f51f760346e35758348cafec4d6aac0a04f7da)) * vercel-ai ([#70](https://github.com/langwatch/better-agents/issues/70)) ([8aa9b11](https://github.com/langwatch/better-agents/commit/8aa9b11b98f8c16b6cfa2a2a61aa54793a4d9b09)) …View on GitHub ↗
FAQ
Does it deploy or run an agent for me?
app/ or src/.Which credentials are required?
Can telemetry be disabled?
BETTER_AGENTS_TELEMETRY=0; anonymous usage telemetry is enabled by default.Which coding assistants are explicitly supported?
Is Better Agents free?
Is Better Agents open source?
Is Better Agents safe to use?
Is Better Agents still maintained?
Who makes Better Agents?
Thanks — we use this to improve the page.