Sqhao-O/dsh-docs
dsh-docs is a tool for DeepSeek Harness. Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek Harness fully local document intelligence plugin, supports PDF, Office, images, and offline OCR
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A well-documented, actively maintained local document parsing plugin with strong offline privacy guarantees and broad fo
README describes an integration suite that generates binary documents and verifies PDF, DOCX, XLSX, PPTX, PNG OCR, and scanned-PDF OCR, plus hash-pinned runtime fetch and manifest verification scripts.
The plugin is fully local with no Docker, HTTP service, or API keys, confines reads to the workspace or explicitly authorized roots, and verifies runtime archives by SHA-256, though the install flow does download and execute a prebuilt Python runtime.
It solves the common need for parsing PDF, Office, image, and scanned documents into Markdown/text/JSON for an LLM agent, with offline OCR for English and Simplified Chinese.
Last updated 2026-08-21, not archived, MIT licensed, and the README documents a rename from dsh-docling with a migration note, indicating ongoing development.
The README provides a one-prompt install, manual YAML configuration, quick-start examples, supported input list, and a separate INSTALL.md, though the excerpt is truncated mid-sentence in the runtime build section.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
dsh plugin --profile web add dsh-docThis command passed the install-plan safety checks and can be executed by the DSH host. Validation is not a security audit or official endorsement.
PROJECT TOPICS
VALIDATION LADDER
FAQ
Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek Harness fully local document intelligence plugin, supports PDF, Office, images,
dsh-docs has 13 stars and 0 forks on GitHub, last updated 2026-08-21.
dsh-docs is distributed under the MIT license.
dsh-docs is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:document-intelligence、document-parsing、document-processing、ocr、pdf、rag。
liustack
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | The strongest vision add-on plugin for DeepSeek Harness, adding vision capability to text-only models like DeepSeek and GLM, paste an image and get structured JSON evidence (OCR, layout, semantics).
tong-io
TongFlow — Multimodal GenAI Studio
Anionex
[dsh] A more powerful visual toolkit for text-only models: one-line install and use, paste images for direct recognition, multi-image Q&A, screenshot-to-frontend UI restoration, and more｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
DDDMUC
Free web search provider for DeepSeek Harness - DuckDuckGo backend, no API key needed
anysearch-team
AnySearch web search provider and advanced search tools for DeepSeek Harness (DSH)
omdsh-dev
Connect DSH to your database for conversational data analysis and actionable business insights.