An actually robust browser agent powered by local LLM?

<!-- SC_OFF --><div class="md"><p>What's your favorites for local computer automations tools/models? Specifically involving clicking in the browser. Are you able to run them at

<!-- SC_OFF --><div class="md"><p>I've been thinking about this as local models get better at </p> <p>tool use — shell access, file system, HTTP requests, MCP. </p> <p>If a prompt

<!-- SC_OFF --><div class="md"><p>I've been thinking about why local-first AI agent architectures are getting serious enterprise traction in 2026, beyond the obvious &quot;keep

<!-- SC_OFF --><div class="md"><p>Been using ClaudeCode CLI with Opus 4.6 and many MCP's and honestly its addicting. </p> <p>Just tell it what to build and it does everything —

<!-- SC_OFF --><div class="md"><p>vision based computer use systems seem to be quite bad at the moment, succeeding only 33% of the time</p> <p><a

<!-- SC_OFF --><div class="md"><p>Im looking to setup a local offline llm for a business i work for, just need it to run on our shared server and be able to do admin type stuff on

<!-- SC_OFF --><div class="md"><p>I have to download 1000 PDFs</p> <p>Site is dynamic</p> <p>I used a few agents but they take screenshot at every step</p> <p>if I load a local

<!-- SC_OFF --><div class="md"><p>Sorry if this is a dumb question, I searched a lot online and am having a hard time finding recommendations due to what I'm specifically wanting