A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
MemSearch is a cross-platform semantic memory layer for AI coding agents that stores human-readable Markdown memories and indexes them with Milvus for searchable retrieval. It is used by agent users who want persistent context and by developers building memory features into agents across tools such as Claude Code, Codex, DeepSeek Harness, OpenClaw, and OpenCode. Catalogue add-ons provide the hooks, skills, and plugin workflows that capture, retrieve, and maintain this memory.
This repository also configures its own agents. See what memsearch tells them →
▶ Using Open-Source memsearch, Giving Your AI Agents Persistent, Human-Readable Memory Zilliz · about zilliztech/memsearch · on YouTube → Skill Claude CodeCodex
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…