aihawk_mcp_server vs browser-use
browser-use is much bigger: 118.8k stars against 32.2k. Over the days we have tracked them aihawk_mcp_server moved +1.8% and browser-use +11.4%, so browser-use is growing faster right now.
browser-use leads on customization and model freedom. aihawk_mcp_server does not take any axis by a clear margin.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
An anti-detect, human-like web-browsing agent that runs locally and drives pages (pointer movement, keystrokes) to avoid captchas and blocks while exposing an MCP server.
- Stars
- 32.2k
- Tracked growth
- +1.8%
- Maturity
- ●●●●●
- Last commit
- 16h ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Your OpenRouter key
An open-source browser agent that runs locally and is extensible with custom tools and provider‑prefixed models, enabling reproducible, privacy-friendly web automation.
- Stars
- 118.8k
- Tracked growth
- +11.4%
- Maturity
- ●●●●●
- Last commit
- 2d ago
- Language
- Python
- License
- MIT
- Cost to run
- Your LLM API key (or run free local models).
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | aihawk_mcp_server | browser-use |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Diff only | ●●●●● Diff only |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● None mentioned | ●●●●● None mentioned |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Config flags & .env | ●●●●● Custom tools & prompts |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hosted run | ●●●●● Fully local capable |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● OpenRouter + MCP | ●●●●● Bring-your-own / local |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One command + key | ●●●●● API key + install |
Which one to pick
Pick aihawk_mcp_server if…
Run locally — when you need a controllable, anti-detect browser agent that simulates human interaction and can be plugged into assistants or a local web UI.
Pick browser-use if…
Open-source & flexible — pick any LLM (including local models), add custom tools, and run browser automation on your machine.
- Customization: Custom tools & prompts (5/5 against 3/5)
- Model freedom: Bring-your-own / local (5/5 against 3/5)
What people want from each one
feder-cr/aihawk_mcp_server
browser-use/browser-use
Hacker News: Launch HN: Browser Use (YC W25) – open-source web agents drew 259 points and 100 comments.
Questions people ask
Is aihawk_mcp_server better than browser-use?
browser-use leads on customization and model freedom. aihawk_mcp_server does not take any axis by a clear margin. aihawk_mcp_server is worth picking when run locally — when you need a controllable, anti-detect browser agent that simulates human interaction and can be plugged into assistants or a local web UI.
Which of aihawk_mcp_server and browser-use keeps my code private?
aihawk_mcp_server: Self-hosted run (4/5). browser-use: Fully local capable (5/5).
What does each one cost to run?
aihawk_mcp_server: Your OpenRouter key. browser-use: Your LLM API key (or run free local models)..
Full profiles: feder-cr/aihawk_mcp_server and browser-use/browser-use. Everything else in Browser agents.