qmd-autosearch
Automatically adds QMD semantic-search results after a model runs grep or glob in configured knowledge-base directories.
Install
$ dsh plugin --profile web add qmd-autosearchPlugin 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
- Detects top-level grep and glob activity within configured or dynamically discovered QMD collection paths.
- Runs a QMD query using lexical and vector retrieval with server-side LLM reranking.
- Uses the latest user message as the primary semantic query, with fallback to the grep pattern when appropriate.
- Queues results for next-step context injection without blocking the current tool call.
- Avoids repeated supplementation for the same tool, path, and pattern within an agent.
- Silently skips enrichment when the QMD service is unavailable or returns no results.
Useful For
- Supplement keyword searches across a QMD-backed knowledge base with semantic matches.
- Help an agent discover relevant documents that grep or glob may miss.
- Provide follow-up document paths for the model to open with read after searching.
Who It Fits
- DeepSeek Harness users with QMD knowledge-base collections.
- Developers running a QMD MCP HTTP service alongside DSH.
- Teams using grep or glob to navigate local knowledge repositories.
Documented Limitations
- Requires a running QMD MCP service and at least one configured QMD collection.
- Requires qmdUrl and collections configuration; the plugin disables itself and logs a warning when they are missing.
- Only triggers for top-level grep or glob searches within configured or detected collection paths.
- Search results are injected on the next pre-step rather than into the current tool call.
- The npm installation command is documented as available after publication.
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
- zhangzhenwen1/qmd-autosearch
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- e55636c · 2026-09-16
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
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-11
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Previewable cross-preset session migration for DeepSeek Harness with bounded, fixed-schema handoffs.
View plugin →Multi-agent team collaboration plugin for DeepSeek Harness with DAG task scheduling, mailbox messaging, and an interactive Web UI monitor.
View plugin →