knowlp-rag
A DeepSeek Harness bundle that exposes MCP retrieval tools for Markdown notes using dual knowledge graphs.
Install
Awaiting GitHub sync
Repository Intelligence
AI-assisted, source-grounded explanation based on the public repository snapshot. It does not replace compatibility or security verification.
Key Capabilities
- Installs into DeepSeek Harness through `dsh plugin add`.
- Builds prerequisite and similarity knowledge graphs from Markdown folders.
- Provides MCP tools for search, feedback recording, note retrieval, statistics, and skill search.
- Supports paragraph chunking and CPU n-gram retrieval.
- Optionally uses Qwen3-VL-Embedding-2B for semantic vectors and PixelRAG for visual search.
- Records explicit feedback and applies it to graph edge weights.
Useful For
- Give an agent structured retrieval and reading paths across personal Markdown notes.
- Search Obsidian, Logseq, Joplin exports, or plain Markdown folders.
- Retrieve prerequisite context and related alternative notes for a topic.
- Improve graph edge ranking using recorded consumption or ignored-result feedback.
Who It Fits
- DeepSeek Harness users managing Markdown knowledge bases.
- Users of Obsidian, Logseq, Joplin exports, or plain Markdown folders.
- Developers who want an MCP-based retrieval service for DSH or Claude Code.
Documented Limitations
- Requires Node.js 18+ and Python 3.11+.
- Users must configure a Markdown vault and graph directory before DSH use.
- The first plugin retrieval bootstraps a Python environment with `mcp` and `pyyaml`.
- Real embedding retrieval requires an RTX GPU and Qwen3-VL-Embedding-2B; CPU n-gram mode is the fallback.
- Visual search requires a PixelRAG server on a GPU machine.
- Honcho integration requires Honcho on localhost port 8000.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Traceable source and registry metadata for this entry, kept separate from runtime verification.
- Source repository
- wly8691-jpg/knowlp-rag
- Registry source
- Public GitHub repository
- Source snapshot
- 2b7bde5ea18d
- Artifact type
- plugin-bundle
- AI enrichment
- gpt-5.6-terra · 2026-08-14
- Prompt version
- dsh-plugin-enrichment-v3
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-14
- Last release
- —
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
DeepSeek Harness plugin that reviews risky tool calls with a stronger model and adds a BlockRun x402-paid LLM provider route.
View plugin →Adds an OpenAI-compatible vision bridge to DeepSeek Harness, forwarding images to a configured vision model and displaying descriptions in a web panel.
View plugin →Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
View plugin →An installable DeepSeek Harness bundle for robotics and embodied-intelligence research workflows.
View plugin →