Native headless and visible Chromium browser automation agent for DeepSeek Harness with DOM tree extraction, screenshot capture, and built-in SSRF protection.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:menotbobbybrown/dsh-plugin-browser
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
Native Headless & Visible Web Browser Automation Agent Plugin for DeepSeek Harness (
dsh)
dsh-plugin-browser empowers DeepSeek Harness agents with native web browsing, live page content extraction, DOM parsing, form interaction, and visual screenshot verification.
Features
- 🌐 Web Navigation & Exploration: Navigate to any public or internal website URL.
- 📄 Semantic Markdown & Link Extraction: Convert complex HTML pages into clean, token-efficient Markdown.
- 📸 Visual Screenshots: Capture high-resolution visual snapshots for multi-modal verification.
- 💻 CLI Utility (
dsh-browser): Direct terminal commands (open,extract,screenshot). - 🧩 Cordis Native: Automatically exposes
browser_navigate,browser_extract, andbrowser_screenshottools.
Installation
# Add from GitHub
dsh plugin --profile web add "github:menotbobbybrown/dsh-plugin-browser"
CLI Usage
# Navigate to a URL and inspect HTTP status
npx dsh-browser open https://news.ycombinator.com
# Extract clean Markdown and hyperlinks
npx dsh-browser extract https://github.com/deepseek-ai/deepseek-harness
# Capture a screenshot
npx dsh-browser screenshot https://github.com my_screenshot.png
Programmatic Usage (Cordis API)
import { Context } from 'cordis';
import * as BrowserPlugin from 'dsh-plugin-browser';
const ctx = new Context();
ctx.plugin(BrowserPlugin);
// Navigate to a URL
await ctx.browser.navigate('https://deepseek.com');
// Extract clean markdown
const { markdown, links } = await ctx.browser.extract();
// Capture screenshot
const screenshot = await ctx.browser.screenshot();
License
MIT © DeepSeek Harness Community
🤝 Contributing
Contributions are warmly welcome! Whether you are reporting an issue, proposing an adapter, optimizing performance, or fixing a bug, please check out our Contributing Guide.
- Fork the Project
- Create your Feature Branch (
git checkout -b feat/AmazingFeature) - Commit your Changes (
git commit -m 'feat: add some AmazingFeature') - Push to the Branch (
git push origin feat/AmazingFeature) - Open a Pull Request
📄 License & Community
Distributed under the MIT License. See LICENSE for more information.
Built with 💙 for the DeepSeek Harness community.
Links
More in this category
Tencent/BrowserSkill#dsh-plugin-browserskill★ 9929
BrowserSkill bridge for controlling visible Chrome and Edge Agent Windows from DeepSeek Harness, with native browser tools, accessibility and VOM observations, screenshots, owned multi-session control, and a live Web UI overlay.
omdsh-dev/dsh-browser#packages/browser/bridge-browser★ 966
Chrome sidebar extension that lets DSH operate your browser directly, no vision capabilities required.
liustack/modsearch★ 911
Web search bridge for text-only agents: ask the web or X, get structured JSON evidence (search, fetch, citations).
DDDMUC/dsh-free-search★ 817
Free, keyless web search for DSH: 7 engines (DuckDuckGo/Bing/SearXNG free + Exa/Perplexity/DeepSeek paid), auto-failover, settings-page UI with API key inputs and official links, web_fetch, and an engine test tool.
Fisfzy/dsh-ego-browser★ 395
Drive a real Chrome/Chromium browser from DeepSeek Harness with 35 structured tools for navigation, snapshots, clicks, forms, JavaScript/CDP, screenshots, downloads and tabs; a live sidebar mirrors the page and accepts mouse and keyboard input. It ships a managed CDP runtime, keeps login state across calls, and can import cookies from your everyday Chrome through a companion extension.
wqty123/dsh-browser★ 162
Shared real browser for DSH: a native Electron window the human can watch and take over, driven by the agent over CDP with 20 browser_* tools (open/snapshot/execute/fill/screenshot/download/auth), per-task session isolation, cookie persistence, CAPTCHA detection; self-hosts on plain dsh web without a desktop shell.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.