The browser built for AI agents — fetch live pages as markdown, render JS/SPAs with built-in V8, take screenshots without Chromium, meta-search 20 engines, and drive interactive login sessions. One Rust binary, stealth TLS fingerprints, MCP native for Claude Code & Cursor. Headless browser alternative to Puppeteer/Playwright.
Desktop computer use for DeepSeek Harness: macOS app listing, accessibility-tree window capture, screenshots, and synthesized input, cloned from Codex Computer Use
Let your coding agent SEE what it builds. Cross-platform screenshot feedback for AI agents: an MCP server, a Claude Code hook, and a native DeepSeek Harness plugin that drops screenshots straight into the conversation as images. Python + uv, zero install via uvx. Windows / Linux / macOS.
Windows desktop UI context picker for AI agents: select windows, UI elements, or screen regions with hover highlighting, UI Automation, screenshots, local OCR, and user-approved MCP output. Works with OpenAI Codex, DeepSeek Harness, and other MCP-compatible clients.
PaperForge — forge your understanding of papers inside DSH: selection-to-highlight, selection-to-ask (one dedicated session per paper), marquee-to-note screenshots with backlinks.
WeChat Mini Program automated testing for DeepSeek Harness (dsh) — selector-addressed actions, build-freshness gates, geometry-first assertions for text-only models, real screenshots on vision routes · 微信小程序自动化测试 dsh 插件
在 DSH 里标注网页元素，像 Codex 那样圈选留评论，把 DOM 结构和你的批注直接随对话发送，不截图、不怕 X-Frame-Options。 Annotate web elements inside DeepSeek Harness, Codex-style: the DOM facts and your comments go straight into the chat. No screenshots, no X-Frame-Options pain.
Unofficial fork of computer-user: fixes the silent load failure on DSH >= 0.1.2, and returns screenshots as real images to vision models with an exact image->screen coordinate mapping.
