NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #1523 most downloaded on PyPI
Browser agent on Pydantic AI: one persistent Python REPL on raw CDP, cloud or local Chrome
Latest stable
1.0.1
Last release 7 days ago
10 Nov 2026
Ships fairly regularly
a new release about every 3 weeks
Nearly every release is documented
notes for 60 of the last 60 stable releases
2 versions withdrawn
withdrawn after publishing
2 years old
146 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
Added the capability to define initial actions (e.g., navigate to a website, scroll down) before starting interactions with the LLM. Perfect for use c
Added the capability to define initial actions (e.g., navigate to a website, scroll down) before starting interactions with the LLM. Perfect for use cases requiring setup tasks!
Optimized support for cloud-based operations, ensuring smoother deployments and better scalability.
Migrated time.sleep to asyncio.sleep for faster, non-blocking operations and improved performance.
Introduced callbacks for step and done events, enhancing control and monitoring during execution.
Added the ability to exclude specific actions, giving users more flexibility and customization.
Strengthened test cases to ensure the utmost reliability and robustness.
Set viewport_expansion to include up to the entire page into context, default is a little bit more than the viewport
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Fixed langchain-google-genai==2.0.8, because we are not compatible with 2.0.9
Automatically detect which tool-calling method to use
Hotfix: Lang chain changed structured output
Nothing published for this version
Version of package was not found
mark in state what is cut out, so that browser-use knows what it does not know
<Enter something smart here and make sure you replace this with something smart>
With this we support now gemini, qwen and other models like llama and granite3.1
model can now output multiple steps at the same time which leads to 10x improvements in form filling etc
spin up multiple contexts per browser
Nothing published for this version
Nothing published for this version
Nothing published for this version
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.
hydrate cookies on every load page
hydrate cookies on every load page
browser better config
wait for traffic stop loading (much better page load detection)
🤔 “None of us can remember why class Banana extends Weapon exists. It’s staying.”
100x speedup for DOM processing (moved processing into the browser with JS)
Nothing published for this version
everything is now async (agent to DOM)
Playwright makes Browser Use faster and more reliable.
Nothing published for this version
hot fix NoneType error in token calculation
Nothing published for this version
Reverted requirements back to pure pyproject.toml
Reverted requirements back to pure pyproject.toml
add custom function calls to the agent (next to the basic functions of the browser)
Nothing published for this version
One column per month.