Install
$ dsh plugin --profile web add @zilliz/memsearch-dshPlugin 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
- Automatic conversation capture and turn summarization into daily Markdown logs
- Pre-step memory injection before the first model step when relevant context exists
- Semantic hybrid search combining dense ONNX vector embeddings and BM25 sparse recall with RRF reranking
- 3-layer progressive retrieval across search hits, section expansions, and raw transcripts
- Registered memory-recall skill for natural language or explicit agent recall
- Procedural skill distillation that drafts reusable Agent Skills from captured workflows
- Optional background maintenance for durable PROJECT.md and USER.md project context
- Web profile dock component for inspecting skill candidates and browsing memory files
Useful For
- Recalling past debugging solutions, configuration decisions, and architectural rationales across sessions
- Sharing conversational context and memory across DeepSeek Harness, Claude Code, and Codex
- Automatically converting multi-step debugging or deployment procedures into reusable agent skills
- Maintaining long-lived project state and user preferences across disjoint harness executions
Who It Fits
- DeepSeek Harness developers working on multi-session software projects
- Engineers using multiple AI coding agents who need unified memory
- Agent workflow authors looking to persist context and distill repeatable skills
Documented Limitations
- Requires installing the companion Python package (memsearch) via uv, pipx, or pip alongside the DSH plugin
- First run with local ONNX embeddings requires downloading an embedding model (~558 MB)
- External vector hosting requires network connectivity and credentials for Zilliz Cloud or a self-hosted Milvus instance
- Interactive memory dock features require the DeepSeek Harness web profile
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.
GitHub reports the repository license as MIT.
No root package.json was captured in the latest GitHub snapshot.
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
- zilliztech/memsearch
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 2e64124 · 2026-10-19
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
- 2.8kGitHub stars
- Forks
- 268
- Open issues
- 273
- Last commit
- 2026-10-19
- Last release
- 2026-09-24
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Comprehensive backup, restore, migration, and multi-channel sync plugin with web UI and CLI for DeepSeek Harness.
View plugin →Compatibility bridge running unmodified Pi ecosystem extensions natively on DeepSeek Harness.
View plugin →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →