DeepSeek Harness Plugin Introduction: dsh-llm-wiki (A Local-First, Workspace-Level LLM Knowledge Base)
`dsh-llm-wiki` is a local-first memory plugin for DeepSeek Harness, designed to solve the challenges of AI-maintained knowledge bases. It builds indexes based on the workspace directory structure and supports hybrid search (including vector, full-text, and graph retrieval) along with agent-based maintenance tools. The plugin keeps all data fully local and securely isolated, making it suitable for privacy-sensitive or offline scenarios. The current version has no Web UI and supports Markdown/TXT files only.
Read MoreDeepSeek Harness Plugin: dsh-llm-wiki
dsh-llm-wiki is a zero-runtime-dependency plugin based on DeepSeek Harness (DSH), built with a pure ESM architecture and requiring Node.js 18 or above. By invoking the LLM-Wiki engine CLI, it encapsulates seven core tools for agents: retrieval, page reading, statistics, validation, fixing, error log viewing, and data ingestion. This plugin aims to implement the philosophy of "everything is a plugin," supporting direct knowledge base queries within conversations, ingesting source texts into the knowledge base, and continuously maintaining the knowledge base structure. Among these, query-type tools require no additional LLM configuration, while data ingestion and the fix functionality with Finalize require configuring an OpenAI-compatible LLM API. The installation process includes installing the Python engine via pip, adding the plugin via the dsh command, and configuring it in the pr
Read More