@jakevin7: None of the current AI browsers feel great for personal use, so I built one myself called Kaze, which means "wind" in Japanese. The built-in AI operates as smooth as the wind & won't get in your way. Github: https://github.com/jackwener/Kaze — Welc

X AI KOLs Timeline Products

Summary

Developer jackwener has open-sourced Kaze, an AI browser for macOS. Its built-in agent executes tasks in a separate tab group, supports connecting external agents like Claude Code and Codex, and allows handing the browser over to your own agent via MCP.

None of the current AI browsers feel great for personal use, so I built one myself called Kaze, which means "wind" in Japanese. The built-in AI operates as smooth as the wind & won't get in your way. Github: https://github.com/jackwener/Kaze — star and follow the project. Report issues via GitHub issues. Project homepage: https://kaze.build Core plugin of the project has been open-sourced: https://github.com/jackwener/BrowserMCP The browser source code is still being organized and will be open-sourced in the future. The biggest highlight is that its browser operations are extremely smooth, especially when running double DeepSeek. While the agent is working, it opens a separate group of tabs in the background, named by task. The browser itself can be used as an MCP server with your own agent, or you can use the browser's built-in agent directly. Continuous improvements are planned. Github: https://github.com/jackwener/Kaze
Original Article
View Cached Full Text

Cached at: 10/28/26, 07:42 PM

Today’s AI browsers don’t feel great to use personally, so I built my own — it’s called Kaze, meaning “wind” in Japanese. The embedded AI operates as smooth as the wind and never gets in your way.

GitHub: https://github.com/jackwener/Kaze — feel free to star the repo and report issues.

Project homepage: https://kaze.build — The core plugin is already open source: https://github.com/jackwener/BrowserMCP. The browser itself is still being cleaned up and will be open-sourced in the future.

The biggest highlight is how smooth the browser operations feel, especially with double DeepSeek. When the agent is working, it opens a separate set of background tabs, named by task. The browser itself can serve as an MCP server for your own agents, or you can directly use the agent embedded in the browser. More improvements are coming.

GitHub: https://github.com/jackwener/Kaze

Similar Articles

@CycleDecoded: Guys doing automation and scraping can throw away their previous solutions. An open-source project called Index (built by the AI developer platform Laminar team) suddenly went viral on GitHub, turning the web browser directly into a callable API. In essence, it's an ultra-smooth “AI browser Agen…

X AI KOLs Timeline

Index is an open-source AI browser Agent developed by the Laminar team that turns any website into a callable API, supports vision models such as Claude and Gemini, and achieves 92% accuracy on WebVoyager.

@GitHub_Daily: AI agents automating browser operations or scraping data often get blocked by anti-scraping mechanisms, and get stuck when encountering captchas or human verification. Recently, the BrowserAct team open-sourced a Skill, a browser automation command-line tool designed specifically for AI agents. It provides three layers of anti-blocking mechanisms, from…

X AI KOLs Timeline

The BrowserAct team open-sourced a browser automation command-line tool designed specifically for AI agents, providing three layers of anti-blocking mechanisms (fingerprint spoofing, captcha cracking, human takeover), supports multi-browser parallelism and account isolation, and optimizes output format to save tokens.

@geekbb: A macOS terminal designed for AI coding, integrating workspace management, split-screen, and AI agent startup workflows. Supports horizontal and vertical split screens, one-click launch of seven AI agents like Claude Code, Codex, Gemini CLI, and more. Right-click selected content to directly submit to...

X AI KOLs Timeline

kooky is a macOS terminal designed for AI coding, integrating workspace management, split-screen, and AI agent startup workflows. It supports one-click launch of multiple AI agents and right-click content submission.