Alibaba Cloud platform giving developers API access to Qwen and partner models for text, image, video and speech, billed per token or by subscription.
Paid
BrowserSkill
Open-source CLI and browser extension from Tencent that lets AI agents work in your real, signed-in Chrome or Edge in a separate window.
What is BrowserSkill?
BrowserSkill is a Tencent project that lets an AI agent work inside Chrome or Microsoft Edge with the accounts you are already signed in to. It has two parts, a command-line tool called bsk and a browser extension. With them an agent can read pages, complete forms, navigate a site, take a long screenshot or investigate a failing web request. The work happens in a separate, visible Agent Window, so your own browsing is not interrupted. When a task needs it, an agent can borrow an existing tab and give it back afterwards, and you can step in by hand for login or verification before letting the agent continue. Any shell-capable agent can use it, including Cursor, Claude Code, Codex, OpenClaw and Hermes Agent, and DeepSeek Harness has a dedicated plugin. The code is open source under the MIT license and there is no pricing.
Use cases
- Let an agent use your logged-in browser
- Fill out web forms through an agent
- Investigate a failing website request
- Capture long full-page screenshots
- Hand over login steps and resume the agent
- Give shell-based agents browser access
Who it's for
Why use BrowserSkill
- Because it reuses your real session, an agent does not need separate credentials or a fresh login for each site.
- A separate Agent Window keeps agent activity apart from the tabs you are working in.
- You can take over for login or verification steps and then hand control back to the agent.
- It works with any agent that can run shell commands, so you keep your choice of agent and model.
- The MIT license means free use with no plan to pick.
BrowserSkill features
- bsk command-line tool paired with a browser extension
- Works with Chrome and Microsoft Edge
- Reuses the accounts you are already signed in to
- Separate, visible Agent Window for agent tasks
- Borrow an existing tab and return it when the task ends
- Page reading, clicking, typing, screenshots and file transfer in local mode
- Long screenshot capture
- Evidence-based debugging of failing requests
- Dedicated plugin for DeepSeek Harness
BrowserSkill integrations
How to get started with BrowserSkill
- Install the bsk command-line tool and the browser extension following the project's quick start.
- Connect your shell-capable agent, such as Claude Code or Codex, to BrowserSkill.
- Ask the agent to complete a web task, which runs in the separate Agent Window.
- Step in by hand for login or verification when asked, then let the agent continue.
- Review the results, such as page content, form submissions or screenshots.
BrowserSkill limitations
- Agents act through your signed-in accounts, so the permissions you give them deserve care
- Requires Chrome or Microsoft Edge
BrowserSkill pricing
BrowserSkill is open source, so you can use and self-host it for free.
Prices can change and may vary by country or exclude tax. Check the official pricing page.
BrowserSkill alternatives
The main BrowserSkill alternatives listed on Debuly are Browser Use, Stagehand, Playwright MCP, agent-browser, BrowserOS and Agent Gateway. The table compares pricing and platforms; order is A–Z.
| Tool | Pricing | Starting price | Platforms |
|---|---|---|---|
| BrowserSkill | Open source | — | CLI, Chrome extension |
| Agent Gateway | Freemium | — | API |
| agent-browser | Open source | — | CLI, macOS, Linux, Windows |
| Browser Use | Paid | $0.02, usage-based | API, Web, CLI |
| BrowserOS | Open source | — | macOS, Windows, Linux |
| Playwright MCP | Open source | — | CLI, MCP, Node.js |
| Stagehand | Open source | — | API |
Agent Gateway
One API key for dozens of agent-ready web services such as DNS, screenshots, scraping and crypto prices, paid per request in USDC.
agent-browser
Native Rust command-line browser automation tool built for AI agents, with compact accessibility snapshots and 50+ commands.
Open sourceVisit agent-browser (official site)
Browser Use
Cloud browsers and hosted web agents for AI, plus an MIT-licensed open-source browser agent, billed pay-as-you-go from $0.02 per hour.
BrowserOS
Free, open-source Chromium browser with built-in AI agents and an MCP server, so agents like Claude Code or Codex can browse as you.
Open sourceVisit BrowserOS (official site)Playwright MCP
Microsoft's Model Context Protocol server that lets LLMs and coding agents control a browser through Playwright accessibility snapshots.
Open sourceVisit Playwright MCP (official site)
Stagehand
Open-source SDK from Browserbase for building browser agents with act, extract and observe calls in TypeScript, Python or Go.
Open sourceVisit Stagehand (official site)
BrowserSkill FAQ
How much does BrowserSkill cost?
BrowserSkill is free. It is published on GitHub as open-source software under the MIT license and has no paid plans.
Which agents work with BrowserSkill?
Cursor, Claude Code, Codex, OpenClaw, Hermes Agent, CodeBuddy, WorkBuddy and any other agent that can run shell commands. DeepSeek Harness has a dedicated plugin.
Which browsers does BrowserSkill support?
It works with Google Chrome and Microsoft Edge through a browser extension.
Is BrowserSkill open source?
Yes. The project is hosted on GitHub under the Tencent organization and uses the MIT license.
Does BrowserSkill take over my browser?
No. The agent works in its own visible Agent Window, can borrow an open tab and hand it back when the task ends, and you can step in by hand for login or verification.
What are alternatives to BrowserSkill?
Browser Use, Stagehand, Playwright MCP and agent-browser also give agents control of a browser.
Sources & verification
Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.
| Source | Type | Accessed |
|---|---|---|
| github.com/Tencent/BrowserSkill | official |
Image credits
- Logo: from avatars.githubusercontent.com · fetched · Vendor trademark, used only to identify the product; removed on request
- Cover: none collected yet, so a generated tile is shown.
Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.
More in Developer platforms 4
All developer platforms toolsPublic registry where you find, install and publish skills and plugins for the OpenClaw AI assistant, with a CLI and API.
Open sourceFree scorecard of 420 APIs rated on how well coding agents can use them, queryable through an MCP server and a JSON API.
FreeBatch LLM inference API and workflow orchestration for extraction, summarization and classification over large data sets.
