Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
View plugin → 
volcengine
dsh-docs
Fully local document intelligence for DeepSeek Harness: the agent can read PDFs, Office documents, images, and scanned files, with offline OCR so nothing leaves your machine. Markdown, HTML, CSV, and plain text are covered too.
Plugin facts
GitHub stars 14
LicenseMIT
Primary languageTypeScript
Last push2026-09-11T14:05:30Z
MaintainerSqhao-O
Added to this directory2026-08-15
Screenshots
Install this DSH plugin
Copy the command below and run it in your DeepSeek Harness terminal.
dsh plugin add github:Sqhao-O/dsh-docs Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety →
More about this plugin
Install the published package into the web profile: dsh plugin --profile web add dsh-doc
Related guides
Learn how to choose, install, and use memory plugins.
About this plugin: dsh-docs
What is dsh-docs?
dsh-docs is a memory plugin maintained by Sqhao-O. Fully local document intelligence for DeepSeek Harness: the agent can read PDFs, Office documents, images, and scanned files, with offline OCR so nothing leaves your machine. Markdown, HTML, CSV, and plain text are covered too.
How do I install dsh-docs?
Run dsh plugin add github:Sqhao-O/dsh-docs in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:Sqhao-O/dsh-docs#commit.
Is dsh-docs free?
dsh-docs is a community open-source project released under the MIT license. You can inspect its source and install it for free.
Related plugins
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
View plugin → 
Tencent
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
View plugin → 
MemTensor