<Enter something smart here and make sure you replace this with something smart>
0.1.18
- With this we support now gemini, qwen and other models like llama and granite3.1
0.1.17
- model can now output multiple steps at the same time which leads to 10x improvements in form filling etc - much more robust css selectors - include more attributes - better handling of multiple browsers
0.1.16
- improved DOM processing - spin up multiple contexts per browser - parallelize as many agents as you want - save traces and replays
Breaking changes - detached controller from browser state - browser service split into browser and context
0.1.15
0.1.12
- Main goal: Do a task once with LLM, re-run it without LLM as often as you want. Even if DOM tree changes, we find the element on the screen. - Implemented saving and reloading of browser history. - Improved agent rerun capabilities, ensuring reliable execution.