jing-hy/picturereader
picturereader is a tool for DeepSeek Harness. DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A feature-rich, actively maintained local image-reading plugin for text-only models that is worth installing.
README documents versioned releases, platform-conditional OCR engines, peerDependency compatibility ranges, and specific bug fixes (issue #2, #3), but no test suite or CI configuration is mentioned.
Privacy mode is enforced host-side with isVlmConfigured() forced false and images kept local, and external VLM calls are opt-in, though the README does not describe how API credentials are stored.
Solves a real and common pain point by giving text-only models image reading, OCR, document conversion, and local editing through a twin adapter plus a local toolchain.
Last updated 2026-08-25 with v3.3.3, recent PR #4 merges, issue fixes, and stated plans to become a bundled EAC vision plugin, indicating active development.
README is extensive with install command, tool tables, routing mode explanations, and version compatibility warnings, though it is dense and largely in Chinese.
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 headless add picturereaderThis command was extracted from an explicit README install reference and is display-only; the DSH host will not execute it automatically.
PROJECT TOPICS
VALIDATION LADDER
FAQ
DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.
picturereader has 36 stars and 5 forks on GitHub, last updated 2026-09-19.
picturereader is distributed under the MIT license.
picturereader 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:image-reading、ocr、vision。
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.