← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

knowlp-rag

Dual knowledge-graph RAG bundle providing MCP tools and Cordis integration for Markdown notes in DeepSeek Harness.

VisionUI & ProductivityDeveloper ToolsSkills & Workflows
3GitHub Stars0ForksUpdated2026-10-06

Install

No clear install command was found in the current repository evidence.

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
KnowLP-RAG is an agent-first knowledge retrieval bundle for DeepSeek Harness and Claude Code. Combining an MCP server and a native Cordis patch, it transforms Markdown vaults into a self-maintaining dual knowledge graph (P/S-Agent) with adaptive edge decay, vector search, and reading path recommendations.

Key Capabilities

  • Four-engine fan-out retrieval combining dual-graph navigation, vector search, and full-text search
  • Reading path generation displaying prerequisite chains and substitute notes
  • Self-maintaining graph with half-life decay and explicit feedback weight adjustments
  • Path-traversal safe Markdown note retrieval and lifecycle health checks via MCP tools
  • Optional cross-machine visual retrieval via PixelRAG endpoints
  • Out-of-the-box support for bilingual and Chinese note vaults

Useful For

  • Querying complex Markdown knowledge bases and technical documentation within DeepSeek Harness
  • Providing AI coding agents with contextual prerequisites and reading order across notes
  • Maintaining long-term dynamic agent memory with automated relevance decay

Who It Fits

  • DeepSeek Harness users with personal or team Markdown note vaults
  • Developers building agentic retrieval workflows and knowledge graphs
  • Researchers managing interconnected reference notes and documentation

Documented Limitations

  • Requires manual configuration of KNOWLP_VAULT and KNOWLP_GRAPH_DIR environment variables
  • First search triggers an initial Python environment bootstrap that takes approximately 30 seconds
  • Optional PixelRAG visual retrieval requires a dedicated external GPU machine and network endpoint
  • Requires Python 3.11 or newer installed in the host environment

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
wly8691-jpg/knowlp-rag
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin Bundle
Source checked
21a5e57 · 2026-10-16

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
3GitHub stars
Forks
0
Open issues
1
Last commit
2026-10-06
Last release
2026-10-06
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app