dsh-kb
Team knowledge base and offline wiki plugin with automated LLM distillation and full-text search.
Install
$ dsh plugin --profile web add @weibaohui/dsh-kb -wPlugin 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.
Key Capabilities
- Sidebar full-page knowledge base with directory tree navigation and Markdown viewer
- Support for multiple independent knowledge bases with per-library schema.md rules
- Automatic background distillation queue for raw materials using LLM agent sessions
- Zero-dependency text scanning and full-text search with hit highlighting
- Ask-AI query mechanism injecting relevant knowledge references into agent prompts
- Automatic version history snapshots (up to 50 versions per page) with rollback support
- Feedback loop allowing unattended agent verification and automated article corrections
- One-click '@' path injection to pass documents or raw files directly to conversation agents
Useful For
- Creating cross-session team wikis, howtos, postmortems, and architectural decision records (ADRs)
- Automatically distilling raw logs, screenshots, and transcripts into structured markdown knowledge
- Querying local offline knowledge bases with AI grounded citations and page references
Who It Fits
- Engineering teams maintaining persistent, multi-session knowledge bases inside DeepSeek Harness
- FDEs and developers operating in air-gapped or offline deployment environments
Documented Limitations
- Requires DeepSeek Harness runtime >=0.1.7-rc.2 and Node.js >=20
- Requires installing companion skill from skill/dsh-kb/ into skills-management for full agent distillation capabilities
- Distillation throughput depends on the configured agent model and background queue execution
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.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- weibaohui/dsh-kb
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- f3a60ea · 2026-10-17
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
- 5GitHub stars
- Forks
- 3
- Open issues
- 0
- Last commit
- 2026-10-09
- Last release
- 2026-09-27
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent semantic memory layer for DeepSeek Harness backed by Markdown and Milvus.
View plugin →Lingshu long-term auditable memory system and cognitive graph for DeepSeek Harness.
View plugin →LLM-supervised persistent memory and graph-based recall integration bundle for DeepSeek Harness.
View plugin →Composable, view-based layered memory bundle for DeepSeek Harness with pluggable providers and strategies.
View plugin →