Show HN: Webctl – Browser automation for agents based on CLI instead of MCP

github.com

119 points by cosinusalpha a day ago

Hi HN, I built webctl because I was frustrated by the gap between curl and full browser automation frameworks like Playwright.

I initially built this to solve a personal headache: I wanted an AI agent to handle project management tasks on my company’s intranet. I needed it to persist cookies across sessions (to handle SSO) and then scrape a Kanban board.

Existing AI browser tools (like current MCP implementations) often force unsolicited data into the context window—dumping the full accessibility tree, console logs, and network errors whether you asked for them or not.

webctl is an attempt to solve this with a Unix-style CLI:

- Filter before context: You pipe the output to standard tools. webctl snapshot --interactive-only | head -n 20 means the LLM only sees exactly what I want it to see.

- Daemon Architecture: It runs a persistent background process. The goal is to keep the browser state (cookies/session) alive while you run discrete, stateless CLI commands.

- Semantic targeting: It uses ARIA roles (e.g., role=button name~="Submit") rather than fragile CSS selectors.

Disclaimer: The daemon logic for state persistence is still a bit experimental, but the architecture feels like the right direction for building local, token-efficient agents.

It’s basically "Playwright for the terminal."

binalpatel a day ago

Cool to see lots of people independently come to "CLIs are all you need". I'm still not sure if it's a short-term bandaid because agents are so good at terminal use or if it's part of a longer term trend but it's definitely felt much more seamless to me then MCPs.

(my one of many contribution https://github.com/caesarnine/binsmith)

  • cosinusalpha a day ago

    I am also not sure if MCP will eventually be fixed to allow more control over context, or if the CLI approach really is the future for Agentic AI.

    Nevertheless, I prefer the CLI for other reasons: it is built for humans and is much easier to debug.

  • fudged71 16 hours ago

    Thank you for posting binsmith, I've built something similar over the past few days and you've made some great decisions in here

  • 0x696C6961 a day ago

    MCP let's you hide secrets from the LLM

    • pylotlight a day ago

      you can do same thing with cli via env vars no?

      • verdverm 16 hours ago

        Yes, I'm using Dagger and it has great secret support, obfuscating them even if the agent, for example, cats the contents of a key file, it will never be able to read or print the secret value itself

        tl;Dr there are a lot of ways to keep secret contents away from your agent, some without actually having to keep them "physically" separate

  • desireco42 a day ago

    Hey this looks cool. So each agent or session is one thread. Nice. I like it.

the_mitsuhiko a day ago

At this point I'm fully down the path of the agent just maintaining his own tools. I have a browser skill that continues to evolve as I use it. Beats every alternative I have tried so far.

  • dtkav 21 hours ago

    Same. Claude Opus 4.5 one-shots the basics of chrome debug protocol, and then you can go from there.

    Plus, now it is personal software... just keep asking it to improve the skill based on you usage. Bake in domain knowledge or business logic or whatever you want.

    I'm using this for e2e testing and debugging Obsidian plugins and it is starting to understand Obsidian inside and out.

    • chrisweekly 19 hours ago

      Cool! Have you written more about this? (EDIT: from your profile, is that what https://relay.md is about?)

      • dtkav 14 hours ago

        https://relay.md is a company I'm working on for shared knowledge management/ AI context for teams, and the Obsidian plugin is what i am driving with my live-debug and obsidian-e2e skills.

        I can try to write it up (I am a bit behind this week though...), but I basically opened claude code and said "write a new skill that uses the chrome debug protocol to drive end to end tests in Obsidian" and then whenever it had problems I said "fix the skill to look up the element at the x,y coordinate before clicking" or whatever.

        Skills are just markdown files, sometimes accompanied by scripts, so they work really naturally with Obsidian.

        • chrisweekly 5 hours ago

          Hey FWIW Relay is AWESOME!! The granular sharing of a given dir within a vault (vs the whole thing) finally solves the split-brain problem of personal (private) vault on my own hardware vs mandated use of a company laptop... it's fast, intuitive, and SOLVES this long-time thorn in my side. Thanks for creating it, high five, hope it leads to massive success for you! :)

          • dtkav 2 hours ago

            Thank you for the kind words <3

  • cosinusalpha 8 hours ago

    Do you experience any context pollution with that approach?

  • kinduff a day ago

    whats the name of the skill?

    • lgas 17 hours ago

      why would that matter?

gregpr07 20 hours ago

Creator of Browser Use here, this is cool, really innovative approach with ARIA roles. One idea we have been playing around with a lot is just giving the LLM raw html and a really good way to traverse it - no heuristics, just BS4. Seems to work well, but much more expensive than the current prod ready [index]<div ... notation

  • cosinusalpha 14 hours ago

    Thanks!

    I actually tried a raw HTML when I was exploring solutions. It worked for "one-off" tasks, but I ran into major issues with replayability on modern SPAs.

    In React apps, the raw DOM structure and auto-generated IDs shift so frequently that a script generated from "Raw HTML" often breaks 10 minutes later. I found ARIA/semantics to be the only stable contract that persists across re-renders.

    You mentioned the raw HTML approach is "expensive". Did you feed the full HTML into the context, or did you create a BS4 "tool" for the LLM to query the raw HTML dynamically?

Agent_Builder 17 hours ago

Interesting approach. In our experience, most failures weren’t about which interface agents used, but about how much implicit authority they accumulated across steps. Control boundaries mattered more than the abstraction layer.

  • cosinusalpha 14 hours ago

    I actually think the CLI approach helps with those boundaries. Because webctl commands are discrete and pipeable (e.g. webctl snapshot | llm | webctl click), the "authority" is reset at every step of the pipeline. It feels easier to audit a text stream of commands than a socket connection that might be accumulating invisible context.

TheTaytay 17 hours ago

I really like this idea!

I’d like to see this other browser plugin’s API be exposed via your same CLI, so I don’t have to only control a separate browser instance. https://github.com/remorses/playwriter (I haven’t investigated enough to know how feasible it is, but as I was reading about your tool, I immediately wanted to control existing tabs from my main browser, rather than “just” a debug-driven separate browser instance.)

  • cosinusalpha 14 hours ago

    Thanks! To clarify: webctl allows you to manually interact with the browser window at any time. It even returns "manual interaction" breakpoints to stdout if it detects an SSO/login wall.

    But I agree, attaching to the OS "daily driver" instance specifically would be a nice addition.

philipbjorge a day ago

This looks remarkably similar to https://github.com/vercel-labs/agent-browser

How is it different?

  • cosinusalpha a day ago

    To be honest, I hadn't seen that one yet!

    The main difference is likely the targeting philosophy. webctl relies heavily on ARIA roles/semantics (e.g. role=button name="Save") rather than injected IDs or CSS selectors. I find this makes the automation much more robust to UI changes.

    Also, I went with Python for V1 simply for iteration speed and ecosystem integration. I'd love to rewrite in Rust eventually, but Python was the most efficient way to get a stable tool working for my specific use case.

grigio a day ago

is there a benchmark? there are a lot of scraping agents nowdays..

  • cosinusalpha a day ago

    I don't have an objective benchmark yet. I tried several existing solutions, especially the MCP servers for browser automation, and none of them were able to reproducibly solve my specific task.

    An objective benchmark is a great idea, especially to compare webctl against other similar CLI-based tools. I'll definitely look into how to set that up.

desireco42 a day ago

How are you holding session if every command is issues through cli? I assume this is essential for automation.

  • cosinusalpha a day ago

    A background daemon holds the session state between different CLI calls. This daemon is started automatically on the first webctl call and auto-closes after a timeout period of inactivity to save resources.

    • desireco42 a day ago

      I see, nice. Is there a way to run multiple sessions?

      • cosinusalpha 14 hours ago

        Yes, you can create isolated environments using the "--session NAME" flag.

        It isolates cookies and local storage for that specific run. Since it's a V1 release, there might be some edge cases in the session isolation - if you hit any, please open an issue!