17 results
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
Accessibility-first macOS Computer Use capability for DeepSeek Harness with stale-observation protection, app leases, confirmations, screenshots, and Web diagnostics
Better Browser for DeepSeek Harness: drive the user's real browser through Kimi WebBridge with navigation, snapshots, interaction, screenshots, network inspection, and tab management
Playwright-powered browser capability for DeepSeek Harness: accessibility-snapshot interaction with stable element refs, session-scoped browser sessions, screenshots as attachments.
Desktop computer use for DeepSeek Harness (DSH): macOS app listing, accessibility-tree window capture, screenshots, and synthesized input — the seam, the local Swift-daemon provider, the computer_use_* tools, the approval policy, and a standalone MCP server in one installable plugin package
Windows Computer Use for DeepSeek Harness: window-bound screenshots, robust OCR, verified clicks, pure-OCR mode, pluggable vision models.
DeepSeek Harness plugin that turns UI screenshots into implementation-grade web specs using OCR, deterministic geometry, scene graphs, assets, and render comparison.
让 DSH 直接操控你的浏览器，无需视觉能力：零 spawn 连接你已开启调试端口的 Chrome/Edge，截图、像素断言、执行页面 JS。Drive your already-running Chrome/Edge over CDP — screenshots, pixel assertions, page JS — no vision model, no per-use approval, zero child processes.
Windows computer-use bundle for DeepSeek Harness: screenshots, window enumeration, and mouse/keyboard control with approval gates.
Pixel-diff two screenshots into diff.png + a labeled triptych (pixelmatch)
Browser patrol and website inspection plugin for DeepSeek Harness: teach once, replay deterministic runbooks with managed Chromium, credentials, screenshots, checkpoints, and selector recovery.
Shots tab for DeepSeek Harness: a video-player view (live + YouTube-style scrubber) over a browser daemon's screenshot feed in <workspace>/shots/
The small deterministic operations an agent needs mid-task. JSON/YAML round-trip, JSON Schema validation, text diff, JWT decode, regex testing, SQL dialect transpiling, QR codes, timezone and unit conversion, page screenshots.
Read-only browser verification tools for the DeepSeek Harness web GUI: browser_open / browser_mock / browser_assert / browser_screenshot — verify a page (H5/desktop) in ≤4 tool calls with mock interception, DOM assertions, and screenshots that auto-project into the model context.
Computer Use for DeepSeek Harness backed by the cua-driver daemon (trycua): accessibility element-level targeting, background-first input delivery, window/desktop screenshots, deterministic verification.
Preview, debug (logs and screenshots), and publish WeChat Mini Games inside the dsh Web GUI, through the official mini game helper service
Local file-upload plugin for DeepSeek Harness: a paperclip button and drag-and-drop that store files per-session under .dsh-uploads/<sessionId>/, plus a read_document tool that pages text and OCRs images (tesseract.js) so a text-only model can still read screenshots.