browser-use

AIMIT

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Latest 0.13.10 · by browser-useWritten in PythonWebsitebrowser-use/browser-useRSS

Release activity

Release activity — 13 releases across 11 days since May 23, 2026. Each cell is one day; darker means more releases that day. Nothing is recorded before May 23, 2026. Older weeks are hidden at this screen width.
JunJulAugSep
SundayNo releases on May 24, 2026No releases on May 31, 2026No releases on Jun 7, 2026No releases on Jun 14, 2026No releases on Jun 21, 2026No releases on Jun 28, 2026No releases on Jul 5, 2026No releases on Jul 12, 2026No releases on Jul 19, 2026No releases on Jul 26, 2026No releases on Aug 2, 2026No releases on Aug 9, 20261 release on Aug 16, 2026No releases on Aug 23, 2026No releases on Aug 30, 2026No releases on Sep 6, 2026
MondayNo releases on May 25, 2026No releases on Jun 1, 20261 release on Jun 8, 2026No releases on Jun 15, 2026No releases on Jun 22, 2026No releases on Jun 29, 2026No releases on Jul 6, 2026No releases on Jul 13, 2026No releases on Jul 20, 20261 release on Jul 27, 2026No releases on Aug 3, 2026No releases on Aug 10, 2026No releases on Aug 17, 2026No releases on Aug 24, 2026No releases on Aug 31, 2026No releases on Sep 7, 2026
Tuesday1 release on May 26, 2026No releases on Jun 2, 2026No releases on Jun 9, 2026No releases on Jun 16, 2026No releases on Jun 23, 2026No releases on Jun 30, 2026No releases on Jul 7, 2026No releases on Jul 14, 2026No releases on Jul 21, 2026No releases on Jul 28, 2026No releases on Aug 4, 2026No releases on Aug 11, 2026No releases on Aug 18, 2026No releases on Aug 25, 2026No releases on Sep 1, 2026No releases on Sep 8, 2026
WednesdayNo releases on May 27, 2026No releases on Jun 3, 20261 release on Jun 10, 2026No releases on Jun 17, 2026No releases on Jun 24, 20261 release on Jul 1, 2026No releases on Jul 8, 2026No releases on Jul 15, 2026No releases on Jul 22, 2026No releases on Jul 29, 2026No releases on Aug 5, 2026No releases on Aug 12, 2026No releases on Aug 19, 2026No releases on Aug 26, 2026No releases on Sep 2, 2026No releases on Sep 9, 2026
ThursdayNo releases on May 28, 2026No releases on Jun 4, 2026No releases on Jun 11, 2026No releases on Jun 18, 2026No releases on Jun 25, 2026No releases on Jul 2, 2026No releases on Jul 9, 2026No releases on Jul 16, 2026No releases on Jul 23, 2026No releases on Jul 30, 2026No releases on Aug 6, 2026No releases on Aug 13, 2026No releases on Aug 20, 2026No releases on Aug 27, 2026No releases on Sep 3, 2026No releases on Sep 10, 2026
FridayNo releases on May 29, 2026No releases on Jun 5, 20261 release on Jun 12, 2026No releases on Jun 19, 2026No releases on Jun 26, 2026No releases on Jul 3, 2026No releases on Jul 10, 20262 releases on Jul 17, 2026No releases on Jul 24, 2026No releases on Jul 31, 2026No releases on Aug 7, 2026No releases on Aug 14, 2026No releases on Aug 21, 2026No releases on Aug 28, 20262 releases on Sep 4, 2026No releases on Sep 11, 2026
SaturdayNo releases on May 30, 2026No releases on Jun 6, 2026No releases on Jun 13, 2026No releases on Jun 20, 2026No releases on Jun 27, 2026No releases on Jul 4, 20261 release on Jul 11, 2026No releases on Jul 18, 2026No releases on Jul 25, 2026No releases on Aug 1, 2026No releases on Aug 8, 2026No releases on Aug 15, 2026No releases on Aug 22, 2026No releases on Aug 29, 2026No releases on Sep 5, 2026

13 releases since May 23, 2026, busiest day 2

Changelog

0.13.10

Latest
Added 1
  • Add pydantic-settings 2.15.0 as an explicit runtime dependency
Changed 5
  • Upgrade Browser Harness to 0.1.13
  • Exact-pin all declared runtime, optional, development, and build dependencies
  • Upgrade and migrate to MCP Python SDK 2.1.1
  • Pin Pydantic 2.13.5 and Hatchling 1.32.0
  • Upgrade pypdf to 6.16.2, resolving three current pypdf Dependabot advisories
Fixed 1
  • Report unknown MCP tool calls as application errors instead of successful results

From browser-use

Browser Use 0.13.10
  • Upgrade Browser Harness to 0.1.13.
  • Exact-pin all declared runtime, optional, development, and build dependencies.
  • Upgrade and migrate to MCP Python SDK 2.1.1.
  • Add pydantic-settings 2.15.0 as an explicit runtime dependency.
  • Pin Pydantic 2.13.5 and Hatchling 1.32.0.
  • Upgrade pypdf to 6.16.2, resolving the three current pypdf Dependabot advisories.
  • Report unknown MCP tool calls as application errors instead of successful results.

Validation includes the full GitHub test matrix, model adapters, MCP stdio handshakes, cross-platform wheel installation, focused PDF tests, CodeQL, GitGuardian, and an installed-runtime vulnerability audit.

View originalPermalink
How 0.13.10 went

0.13.9

Added 1
  • Add OrcaRouter as a named LLM provider
Changed 2
  • Require Browser Harness 0.1.10
  • Upgrade datamodel-code-generator to 0.75.1
Fixed 29
  • Make bu-2-0 the ChatBrowserUse default again, keep mini opt-in
  • Report missing target text in replace_file
  • Escape plain text in generated PDFs
  • Update DeepSeek default model to deepseek-v4-flash
  • Stop putting format/stream inside Ollama options
  • Update vulnerable Click, MCP, and pypdf pins

From browser-use

What's Changed
New Contributors

Full Changelog: https://github.com/browser-use/browser-use/compare/0.13.8...0.13.9

View originalPermalink
How 0.13.9 went

0.13.8

Changed 2
  • Update Cerebras model IDs and default
  • Use UTF-8 for agent file writes
Fixed 18
  • Recover Anthropic tool arguments when the model serializes its call as text
  • Guard last_action() against empty action list
  • Guard _inject_budget_warning against ZeroDivisionError
  • Return Path from validate_user_data_dir when creating temp dir
  • Clamp final chunk char_end to len(content) for trailing newline
  • Do not expose domain-restricted actions on an empty URL

From browser-use

What's Changed
New Contributors

Full Changelog: https://github.com/browser-use/browser-use/compare/0.13.7...0.13.8

View originalPermalink
How 0.13.8 went

0.13.7

Changed 2
  • Stop auto-inheriting output_model_schema into per-page extraction
  • Simplify cross-origin iframe minimum size
Fixed 12
  • Do not send default params in gemini genconfig
  • Fix tool name in flash prompts from replace_file_str to replace_file
  • Handle file:// URLs in _extract_start_url
  • Fix clear-to-empty on React controlled inputs using native value setter
  • Gate the skeleton-screen 'still loading?' hint on in-flight network requests
  • Fix nested cross-origin iframe extraction filtering

From browser-use

Ships the latest version of the CLI, which includes bug fixes and better browser management.

What's Changed

Full Changelog: https://github.com/browser-use/browser-use/compare/0.13.6...0.13.7

View originalPermalink
How 0.13.7 went

0.13.5

Added 2
  • Accept bu-qa-1 model alias in ChatBrowserUse
  • Support MCP registry

From browser-use

What's Changed

Full Changelog: https://github.com/browser-use/browser-use/compare/0.13.4...0.13.5

View originalPermalink
How 0.13.5 went

0.13.4

Added 2
  • MCP server for CLI 3.0 with shared MCP runner and max_dim guard
  • Detect LLM output truncation instead of failing with misleading parse errors, with fallback LLM switching on truncation
Changed 3
  • Pin Browser Harness to 0.1.5 for Windows reliability fixes and cloud-browser suggestion
  • CLI polish including shim for legacy CLI commands, hints for unknown commands, and faster startup
  • Restructure README quickstart around the CLI and Python library paths
Fixed 4
  • Navigation readiness detection with per-target lifecycle event storage and handling of same-document navigations without timeout burning
  • Markdown extraction no longer destroys URLs and drops long link lines
  • Keep plain BrowserErrors recoverable and preserve structured error memory through execute_action
  • Visibility check no longer mutates shared snapshot bounds

From browser-use

What's Changed
  • MCP server for CLI 3.0: shared MCP runner, max_dim guard.
  • Fix navigation readiness detection: per-target lifecycle event storage, and handle same-document navigations without burning the readiness timeout.
  • Fix markdown extraction destroying URLs and dropping long link lines.
  • Detect LLM output truncation instead of failing with misleading parse errors, and let truncation errors switch to the fallback LLM.
  • Keep plain BrowserErrors recoverable and preserve structured error memory through execute_action.
  • Fix visibility check mutating shared snapshot bounds.
  • Pin Browser Harness to 0.1.5 (Windows reliability fixes, cloud-browser suggestion).
  • CLI polish: shim for legacy CLI commands, hints for unknown commands, faster startup.
  • Restructure README quickstart around the CLI and Python library paths.

Full Changelog: https://github.com/browser-use/browser-use/compare/0.13.3...0.13.4

View originalPermalink
How 0.13.4 went

0.13.3

Added 2
  • Launch Browser Use CLI 3.0 powered by Browser Harness
  • Add browser-use skill so coding agents can install the Browser Use skill directly
Changed 2
  • Pin Browser Harness to 0.1.4 and ship the Browser Use skill with the package
  • Improve skill install behavior across Claude Code, Codex, Cursor, Gemini, OpenCode, and related agent skill directories

From browser-use

What's Changed
  • Launch Browser Use CLI 3.0 powered by Browser Harness.
  • Add browser-use skill so coding agents can install the Browser Use skill directly.
  • Pin Browser Harness to 0.1.4 and ship the Browser Use skill with the package.
  • Improve skill install behavior across Claude Code, Codex, Cursor, Gemini, OpenCode, and related agent skill directories.

Full Changelog: https://github.com/browser-use/browser-use/compare/0.13.2...0.13.3

View originalPermalink
How 0.13.3 went

0.13.2

Added 1
  • Add BU3 browser use models
Changed 2
  • Accept provider-prefixed models in ChatBrowserUse
  • Default beta example to openai/gpt-5.5
Removed 1
  • Remove bu-3 and bu-3-max models

From browser-use

What's Changed

Full Changelog: https://github.com/browser-use/browser-use/compare/0.13.1...0.13.2

View originalPermalink
How 0.13.2 went

0.13.1

Added 1
  • Support Claude Fable 5 model
Changed 1
  • Anthropic tool choice set to auto when thinking (cannot force it)
Fixed 1
  • Fix packaged agent tools environment

From browser-use

What's Changed

Full Changelog: https://github.com/browser-use/browser-use/compare/0.13.0...0.13.1

View originalPermalink
How 0.13.1 went
0.13.0

0.13.0 - Rebuilt in Rust [beta]

Added 3
  • Introduce a new Rust-backed beta agent that provides modern models a more direct browser control loop guided by robust helpers
  • Add x402 skill
  • Add browser-use-core binary discovery
Changed 1
  • Clean up Rust SDK server implementation
Fixed 2
  • Fix prerelease version upgrade check
  • Close beta SDK browser resources properly

From browser-use

Browser Use 0.13.0 introduces a new Rust-backed beta agent.

It gives modern models a more direct browser control loop, guided by robust helpers instead of brittle browser abstractions.

uv add "browser-use[core]"

from browser_use.beta import Agent

The existing Python agent remains unchanged.

What's Changed

Full Changelog: https://github.com/browser-use/browser-use/compare/0.12.9...0.13.0

View originalPermalink
How 0.13.0 went

0.12.9

Changed 1
  • Pass session id to judge LLM calls
Fixed 1
  • Skip screenshots on new tab pages

From browser-use

What's Changed

Full Changelog: https://github.com/browser-use/browser-use/compare/0.12.8...0.12.9

View originalPermalink
How 0.12.9 went

0.12.8

Added 2
  • Add client header to GoogleChat
  • Add OpenRouter pricing fallback for token costs
Changed 5
  • Default ChatBrowserUse to bu-2-0
  • Recommend gemini-3-flash-preview in examples and tests
  • Freeze HistoryItem and lock byte-prefix property
  • Move per-step metadata out of agent_state into a tail block
  • Move user request before agent history
Fixed 2
  • Restrict unix socket file to owner-only access in daemon
  • Refuse evaluate() on restricted browser profiles

From browser-use

What's Changed
New Contributors

Full Changelog: https://github.com/browser-use/browser-use/compare/0.12.7...0.12.8

View originalPermalink
How 0.12.8 went

More in AI

View all
Codex

OpenAI's coding agent, running locally in the terminal.

OpenAI
Ollama

Get up and running with large language models locally.

Ollama
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

openclaw
tensorflow

An Open Source Machine Learning Framework for Everyone

tensorflow
superpowers

An agentic skills framework & software development methodology that works.

obra
skills

Skills for Real Engineers. Straight from my .agents directory.

mattpocock

Discussion

If you publish browser-use, you can claim this product by proving you administer its repository.