Breeze136/dsh-kb-rag
dsh-kb-rag is a tool for DeepSeek Harness. Local-first literature knowledge base RAG (DeepSeek Harness plugin): hybrid retrieval of body text and figure captions, pin a fuzzy memory to the exact passage and figure, one-click DOI to the source. Local-first literature RAG for DSH — turn a fuzzy memory into an exact passage/figure, one-click DOI to source.
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A well-documented, local-first literature RAG plugin with clear scope and honest limits; worth installing for paper-heav
README describes a single shared engine (kb_engine.py) with three entry points, an npm installer that checks Node/pnpm, and documented async job handling, but no test suite or CI configuration is visible in the provided information.
All indexing, embedding, and reranking run locally with zero upload and no API cost, and the install path is a standard npm package, though the installer's automatic pnpm installation is a minor unverified side effect.
It targets a concrete, common pain point by returning passage-level provenance with section, PDF page, clickable DOI, and citation chains, plus native Zotero migration and MCP compatibility for multiple agents.
Last updated 2026-08-19 with an active release badge, versioned behavior notes (v1.6 anchors), and a non-archived repository, indicating ongoing development.
The README covers requirements, quick start, three deployment shapes, a tool reference, output examples, and an explicit known-limitations section, though the full install walkthrough is truncated in the excerpt.
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
npx dsh-kb-rag-installThis 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
Local-first literature knowledge base RAG (DeepSeek Harness plugin): hybrid retrieval of body text and figure captions, pin a fuzzy memory to the exact passage and figure, one-click DOI to the source. Local-first literat
dsh-kb-rag has 8 stars and 0 forks on GitHub, last updated 2026-09-03.
dsh-kb-rag is distributed under the MIT license.
dsh-kb-rag 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:literature、rag、zotero。
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.