mastra vs browser-use
Two of the top projects in Agent frameworks and SDKs, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
mastra
TypeScript framework for building AI agents, workflows and MCP servers
browser-use
Python library that lets an LLM agent control a web browser
Verdict
mastra ranks higher, 91 to 90. Of the 4 score parts we measure for both, mastra leads on 2, browser-use on 1 and 1 is even.
- Adoptionbrowser-use leads by 17 points, 98 to 81: a wide gap.
- FreshnessEven at 100.
- Maintenancemastra leads by 17 points, 94 to 77: a wide gap.
- Agent-readymastra leads by 15 points, 85 to 70: a wide gap.
Pick mastra if you are
TypeScript developers building production agents and workflows
- Graph workflow engine with .then(), .branch() and .parallel() control flow
- Suspend and resume agents or workflows, with execution state kept in storage
Pick browser-use if you are
Developers building LLM agents that automate web tasks in Python
- Works with several LLM providers, plus local models through Ollama
- Custom actions can be registered with the Tools decorator
| What we compare | mastra | browser-use |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 81, widely used | 98, widely used |
| Momentum | Not scored for this kind | Not scored for this kind |
| Freshness | 100, active | 100, active |
| Maintenance | 94, healthy | 77, fair |
| Agent-ready | 85, ready | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 29.5k | 120.7k |
| License | custom license (read the license) | MIT (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | Nov 2026 |
| Language | TypeScript | Python |
| Docker | No | Yes |
| GPU | Not needed | Optional |
| arm64 or Apple Silicon | Not stated | Not stated |
mastra
Mastra is a TypeScript framework for building agents and graph-based workflows, with model routing across 40+ providers. It adds suspend/resume with stored state, memory, RAG, evals and observability, and runs inside React, Next.js or Node apps or as a standalone server. A local Studio on port 4111 is used to build and test agents, workflows and tools.
Who it is for: TypeScript developers building production agents and workflows
Strengths
- Graph workflow engine with .then(), .branch() and .parallel() control flow
- Suspend and resume agents or workflows, with execution state kept in storage
- Built-in evals, observability, memory and RAG alongside agents
- Can author MCP servers exposing agents and tools
Weaknesses
- TypeScript only; no other language SDKs mentioned
- Code in ee/ directories needs an enterprise license for production use
- Pull requests limited to collaborators
- No Docker or compose files in the repo
- no GPU
- Needs Node.js, LLM provider API key
- Models: OpenAI, Anthropic, Gemini, xAI, 40+ providers via model router
- port 4111
browser-use
Browser Use is a Python library where an Agent takes a natural-language task and drives a local or cloud browser to complete it. It works with OpenAI, Anthropic, Google and Ollama models, or the project's own BU2 model via an API key. The README also describes a CLI skill for coding agents and a paid hosted cloud with stealth browsers.
Who it is for: Developers building LLM agents that automate web tasks in Python
Strengths
- Works with several LLM providers, plus local models through Ollama
- Custom actions can be registered with the Tools decorator
- Can reuse a local Chrome profile for authenticated sessions
- Same agent code runs on a local browser or a cloud browser
Weaknesses
- Stealth, CAPTCHA solving and residential proxies require paid Browser Use Cloud
- BU2 model needs a Browser Use API key and is not local
- Cloud profile sync transfers cookies only, not local storage or extensions
- Local-model quality and hardware needs are unspecified in the README
- GPU optional
- Docker
- Needs Chrome or Chromium, LLM provider API key, Browser Use API key (optional)
- Models: OpenAI, Anthropic, Google, Ollama, BU2 (ChatBrowserUse)
More in Agent frameworks and SDKs
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.