← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

deepseekeyes

Auditable vision, cross-platform Computer Use, and MCP application runtime for DeepSeek Harness.

VisionUI & ProductivityTerminal & TUIDeveloper ToolsBrowser & WebSecurity & PolicySkills & WorkflowsRemote Execution
7GitHub Stars1ForksUpdated2026-09-22

Install

No clear install command was found in the current repository evidence.

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
DeepSeekEyes is a DeepSeek Harness plugin that bridges multimodal vision and cross-platform computer use into text-reasoning tasks. It processes pasted images, executes health-checked failover across multimodal providers, normalizes visual evidence against strict JSON schemas, and enables Playwright browser automation alongside native macOS/Windows desktop control and Model Context Protocol (MCP) integrations.

Key Capabilities

  • Auditable visual evidence extraction and clarification loop for text-based reasoning models
  • Active vision model capability probing and automatic failover routing
  • Browser Computer Use automation via Playwright with semantic state capture
  • Desktop Computer Use for Windows (UI Automation) and macOS (Accessibility API)
  • MCP Tools, Resources, and Prompts management with stdio and Streamable HTTP support
  • Token accounting tracking provider usage, bridge input, and automation metrics

Useful For

  • Analyzing screenshots and user-provided images directly inside DeepSeek Harness conversations
  • Automating browser workflows including web navigation, forms, and visual assertions
  • Controlling native Windows and macOS desktop interfaces with UI coordinate and semantic target binding
  • Connecting MCP servers securely to execute external tools within an explicit allowlist

Who It Fits

  • DeepSeek Harness users needing multimodal understanding with text-first reasoning models
  • Developers building automated browser and desktop agent workflows
  • Teams integrating local or remote MCP servers into DeepSeek Harness

Documented Limitations

  • Desktop Computer Use requires native OS support (Windows with PowerShell/user32 or macOS with CoreGraphics/Accessibility)
  • Requires Node.js >= 22.19 and DeepSeek Harness compatible environment
  • Browser automation requires a compatible Chromium runtime
  • Image and automation loops consume additional model tokens and provider quotas

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 3 runtime, 11 development, 2 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
dttxorg/deepseekeyes
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
32fdee8 · 2026-09-22

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
7GitHub stars
Forks
1
Open issues
0
Last commit
2026-09-22
Last release
2026-08-27
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app