Guozhen AIGlobal AI field notes and model intelligence

Realtime AI News

Tencent open-sources BrowserSkill, a browser automation tool that gives AI agents hands of their own

Tencent has open-sourced BrowserSkill, a new browser automation tool that lets AI agents operate a browser directly and complete real tasks on web pages. The open-source release puts this execution capability into the community's hands and could lower the barrier to building agents that actually do work.

Published
腾讯开源浏览器自动化工具BrowserSkill,让AI智能体拥有独立干活的双手
Image source: tencent.com

Tencent has open-sourced a new browser automation tool called BrowserSkill, designed to give AI agents hands of their own so they can operate a browser directly and complete real tasks on web pages. The news spread widely on August 11 via Chinese media reports.

Browser automation sits at a critical point in the current AI agent boom: large models are good at understanding instructions and making plans, but actually executing — performing real operations on live web pages — has been the bottleneck between conversation and real-world impact. BrowserSkill targets exactly that gap.

By open-sourcing the tool, Tencent is putting the capability directly into developers' hands. Any team can pick it up, integrate it into its own agent systems, and give agents the ability to act on web pages rather than merely offering suggestions.

In industry context, teaching agents to use browsers and web tools has become a crowded race among major vendors. The browser is the most universal gateway between agents and the digital world, and whoever makes this step smoother is more likely to build agents that genuinely get work done.

Tencent's open-source release means BrowserSkill will not remain an internal corporate tool: it becomes a community component that can be freely used and extended, potentially lowering the barrier for building executable agents across the industry.

What to watch next: how quickly BrowserSkill is adopted by the community, how well it integrates with mainstream agent frameworks, and whether Tencent builds a fuller open-source agent toolchain around it.

Why it matters

By open-sourcing browser automation, Tencent fills a key execution gap for AI agents and could accelerate the spread of usable agent toolchains across the developer community.

TencentOpen SourceAgent
Back to realtime news

Nearby Updates

All

08/11, 10:53

Anthropic signs $9.1B AI compute deal with bitcoin miner Riot Platforms

Anthropic has signed a 20-year compute supply agreement worth $9.1 billion with bitcoin miner Riot Platforms, which will provide 191 megawatts of capacity from its Rockdale, Texas data center campus. With two five-year renewal options the deal could be worth up to $16.1 billion, and Riot shares jumped about 25% after hours.

08/11, 09:01

Open-source LangAlpha launches as the Claude Code of finance for natural-language investment research

Open-source project LangAlpha has officially launched, positioned as the Claude Code of finance for driving investment research workflows with natural language, per InfoQ. The Apache-2.0 project on GitHub offers persistent workspaces, parallel research subagents, and multi-tier financial data access.

08/11, 08:46

Five universities release first benchmark results for robot three-view world models

Five universities have released the first evaluation results for robot three-view world models, with a leaderboard that will be updated continuously, QbitAI reports. The benchmark focuses on how consistently the models perform across robot tasks, giving the emerging field its first public point of comparison.

08/11, 08:03

OpenAI reportedly completes $7 billion employee tender offer

OpenAI has reportedly completed a $7 billion employee tender offer, according to TechCrunch, giving staff and early shareholders a chance to sell company stock. The deal has not been officially confirmed, and details such as valuation and participants remain undisclosed.