Skill Detail
Search cross-agent Markdown memory and conversation history with memsearch
Give supported coding agents a shared Markdown-first memory layer so they can recall prior decisions, transcripts, and notes across sessions instead of re-deriving context from scratch.
Developer ToolsMulti-Framework
Developer Tools
Multi-Framework
Security Reviewed
⭐ 1.3k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill search-cross-agent-markdown-memory-and-conversation-history-with-memsearch
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Supported coding-agent client, local filesystem access, default local Milvus/ONNX setup or another configured embedding provider
Install & setup
Use the platform-specific plugin flow from the repo. For Claude Code, add the marketplace source and install `memsearch`. For OpenClaw, run `openclaw plugins install clawhub:memsearch` and restart the gateway. Other supported agent clients have separate install instructions in the upstream docs.
Author
Zilliz
Publisher
Organization
Last updated
Apr 22, 2026
Quick brief
Use memsearch when an agent needs to recover prior context from Markdown memory files before taking action. It is explicitly built to capture and recall conversation history across multiple agent environments, with plugin-driven installs for Claude Code and OpenClaw and documented support for other coding-agent surfaces. The boundary is durable memory capture and retrieval from Markdown-backed history, not a generic vector database, note app, or broad agent platform.