Extension vs. Browser: The Core Debate
The central debate revolves around whether the project's core functionality (agent-driven browser automation) is better suited for a dedicated browser fork or a Chrome extension.
- The initial question: "Why a browser, and not a fantastic chrome extension?" – anilgulecha
- A major suggested advantage of a browser is bypassing security features, but this is viewed skeptically: "The only reason to use a browser over a chrome extension is to bypass security features" -- dataviz1000. dataviz1000 further argues these limitations are in place "for very, very good reasons and should not be bypassed."
- dataviz1000 also points out the existing reach of Chrome: "There are 3,500,000,000 Chrome users on Earth. Getting them to install a Chrome extension is much, much easier than getting them to install a new browser.".
- The developers admit accessibility is one use case, but that forking the browser opens up possibilities like "Ship a small LLM along with browser" and "MCP store built in" – felarof
Security and Risk Mitigation
Concerns are raised about the security implications of an agentic browser, particularly the potential for exposing sensitive data and the risk of prompt injection attacks.
- The major concern is around sending potentially sensitive material to third-party servers: "there are much larger security issues using a agentic browser which is sending entire contents of a bank website or health records in a hospital patient portal to a third party server." - dataviz1000
- dataviz1000 suggests mitigation strategies: "The first step in mitigating these security vulnerabilities is preventing the automation from doing anything a Chrome extension can't already do. The second is blacklisting or opt in only allowing the agents to read and especially to write (fill in form is a write) any webpage without explicit permission."
Productivity Claims and Skepticism
The claim of a "10x productivity boost" is met with skepticism and criticism.
- "The 10x line made me lose all interest I had on this." – iammrpayments
- gtsop mocks the claim considering the project's timeline: "Are we still tossing around the 10x productivity boost? Please make this stop. I see first commit on April 28 so by 10x productivity its like you've been working on this for almost 2.5 years, and there is still a waiting list on the website."
- However, other users acknowledge demonstrable productivity gains from related tools such as Cursor: "But cursor for sure has improved productivity by a huge multiplicative factor, especially for simpler stuff (like building chrome extension)." – felarof
Practical Functionality and User Experience
Users raise questions about how the browser interacts with web pages, handles errors, and allows for user intervention.
- lxe inquires about page content extraction and event dispatch: "how do you pass the page content, and the locations of interactive components to the LLM? And how do you dispatch events to interact with the page?"
- b0a04gl asks about error handling and undo functionality: "so agents can control tabs, forms, clicks—like a real user would. so what about undo. if an agent clicks the wrong thing, how do you roll that back without reloading the world?" Response: "There is a big red button to always stop the agent." - felarof
- deepdarkforest critiques the stop button as insufficient, suggesting a need for more granular human-in-the-loop control: "if i have to supervise constantly for non reversible actions, then im no more efficient(actually less i would argue) than just doing the task myself. A human in the loop- pause just before a non reversible action asking for approval maybe?"
Platform Support: Focus on Mac, Calls for Linux and More
The initial focus on macOS is noted, with users requesting builds for other platforms.
- "What is with Mac users forking Chromium and then only making releases for Mac?" - jklinger410
- The developers respond that it was easier to build for macOS first and that Linux is on their radar: "Haha, was easier to build and we were the first users :) have linux next on our radar. What build do you want?" - felarof
- Specific requests for Linux distributions (deb) and other operating systems (FreeBSD, Haiku, Amiga) are made.
Licensing (AGPL) and its Implications
The choice of the AGPL license is discussed, particularly in relation to commercial viability.
- The AGPL license is viewed as potentially problematic for commercial applications: "Also the fact that it's AGPL means this project is very copyleft and not compatible with business models." - ilaksh
- mattigames summarizes: "The short answer is that it means that businesses need to publicly share whatever change they do to the code, and that alone is enough deterrent to use it."
Branding and Naming
The project's name and icon are questioned due to their association with Firefox/Netscape while being a Chromium fork.
- "Name derived from Netscape (Firefox's great-grandfather), icon is a red fox, but based on Chrome? Was this originally designed as a Firefox fork or what happened there" - wongarsu
- ilaksh agrees that: "it seems misleading to use that icon with a Chromium fork."