Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
View plugin → 
volcengine
memsearch
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
Plugin facts
GitHub stars 2738
LicenseMIT
Primary languagePython
Last push2026-10-09T11:51:36Z
Maintainerzilliztech
Added to this directory2026-08-24
Screenshots
About this plugin
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
Install this DSH plugin
Copy the command below and run it in your DeepSeek Harness terminal.
dsh plugin add github:zilliztech/memsearch Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety →
More about this plugin
Optional Jev reranking — rerank memory search results with Jev through the TypeSafe API, with no local model download. See configuration and the Chinese/English evaluation.
Related guides
Learn how to choose, install, and use memory plugins.
About this plugin: memsearch
What is memsearch?
memsearch is a memory plugin maintained by zilliztech. A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
How do I install memsearch?
Run dsh plugin add github:zilliztech/memsearch in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:zilliztech/memsearch#commit.
Is memsearch free?
memsearch is a community open-source project released under the MIT license. You can inspect its source and install it for free.
Related plugins
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
View plugin → 
Tencent
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
View plugin → 
MemTensor