ferstar/dsh-tool-ocr
dsh-tool-ocr is a tool for DeepSeek Harness. Local OCR plugin: lets text-only generative LLMs read images | Local OCR plugin: give text-only generative LLMs the ability to read images
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Solid, well-documented local OCR plugin for text-only LLMs, but requires installing a separate third-party engine binary
README documents typecheck, vitest tests, oxlint, and an opt-in real-engine E2E smoke test gated behind NBOCR_BIN and OCR_E2E_IMAGE env vars, indicating real engineering rigor.
The README's quick start instructs piping a remote install script directly into a shell (curl | sh and irm | iex), which is a notable supply-chain risk, though the plugin itself only spawns a local subprocess.
It solves a concrete, common gap by giving text-only DeepSeek Harness models OCR over local images or conversation attachments, with bounding boxes, review flags, and Markdown table heuristics.
Last updated 2026-08-18, not archived, and it tracks a recent dsh release (>= 0.1.0-rc.7) for its settings card, suggesting ongoing upkeep despite only 4 stars.
The README covers install, mounting config, a full configuration table, tool usage, image input modes, and development commands, making setup and usage clear for a new user.
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-tool-ocrThis 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
Local OCR plugin: lets text-only generative LLMs read images | Local OCR plugin: give text-only generative LLMs the ability to read images
dsh-tool-ocr has 4 stars and 0 forks on GitHub, last updated 2026-08-18.
dsh-tool-ocr is distributed under the MIT license.
dsh-tool-ocr 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: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.