deepseek-visionary
Multimodal vision, OCR, and text-model image bridging for DeepSeek Harness via DeepSeek Web backend.
Install
$ | DeepSeek Harness | [deepseek-harness.md](docs/integrations/deepseek-harness.md) | 原生插件 dsh plugin --profile web add @xlight-oss/visionary-dsh（推荐）或 visionary-server init dsh（skill + CLI 轻量接入） |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.
Key Capabilities
- Analyzes single or multiple images using DeepSeek multimodal vision models
- Extracts text from screenshots, documents, and code via dedicated OCR pipeline
- Provides automated browser login via CDP to capture auth tokens without API keys
- Bridges pasted images in text-only model sessions into structured prompt prompts
- Supports multi-turn conversational image follow-ups and persistent sessions
- Runs natively via Rust-powered visionary-server binary with CLI and MCP support
Useful For
- Giving text-based DSH agent sessions visual perception and diagram understanding
- Extracting text or structured data from screenshots and document images
- Multi-turn image inspection and visual reasoning workflows inside DSH
Who It Fits
- DeepSeek Harness users needing visual understanding capabilities without API keys
- Developers looking for seamless image OCR and visual inspection in coding agents
Documented Limitations
- Requires Chrome, Chromium, or Edge installed on the local system for automated browser login
- Requires the standalone visionary-server Rust binary installed and accessible in PATH or configuration
- Requires DSH version 0.1.5-rc.1 or higher for latest plugin bundle support
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
GitHub did not report an SPDX license for this repository snapshot.
No root package.json was captured in the latest GitHub snapshot.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- xlight/deepseek-visionary
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- ad31672 · 2026-10-07
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
- 18GitHub stars
- Forks
- 1
- Open issues
- 8
- Last commit
- 2026-09-13
- Last release
- 2026-08-30
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Compatibility bridge running unmodified Pi ecosystem extensions natively on DeepSeek Harness.
View plugin →Multimodal vision router and deep pixel tools for text-only DeepSeek Harness agents with free fallback chains.
View plugin →Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →Multi-model workflow teams and DAG orchestration GUI for DeepSeek Harness Web profile.
View plugin →