memsearch

Zilliz's unified memory for coding agents: one Markdown + Milvus store shared across Claude Code, Codex, OpenCode and OpenClaw — hybrid search, plus repeated workflows distilled into skills.

2,345 206 Python MITupdated yesterday

memory coding

View on GitHubDispute this mapping →

Curator's take

The cross-platform play is the point: a conversation in Claude Code becomes searchable context in Codex, OpenCode and OpenClaw — one memory, four plugins, zero per-agent setup. Memories live in readable Markdown (greppable, versionable) with Milvus doing hybrid search, and the standout feature is procedural: it watches for workflows you repeat and distills them into installable skills, maintained in the background. NOT for single-agent loyalists — if you only run Claude Code, opencode-mem-style plugins are lighter — and it's a Zilliz project: the Milvus dependency is also the funnel; check what 'backed by Milvus' costs you operationally before teams adopt.

Mapped by ShipWithAI editors · links verified

README.md

memsearch

Cross-platform semantic memory for AI coding agents.

memsearch demo

📰 What's New

Skills from memory — MemSearch now distills the workflows you repeat into reusable, installable agent skills (a third "procedural memory" layer) and keeps them up to date in the background. See Skills from Memory.
Advanced memory maintenance — optional background tasks keep durable PROJECT.md and USER.md notes current across sessions. See Advanced Memory Maintenance.

Why memsearch?

🌐 All Platforms, One Memory — memories flow across Claude Code, OpenClaw, OpenCode, and Codex CLI. A conversation in one agent becomes searchable context in all others — no extra setup
👥 For Agent Users, install a plugin and get persistent memory with zero effort; for Agent Developers, use the full CLI and Python API to build memory and harness engineering into your own agents
📄 Markdown is the source of truth — inspired by OpenClaw. Your memories are just .md files — human-readable, editable, version-controllable. Milvus is a "shadow index": a derived, rebuildable cache
🔍 Progressive retrieval, hybrid search, smart dedup, live sync — 3-layer recall (search → expand → transcript); dense vector + BM25 sparse +

Continue your stack

What teams reach for next — and why each earns a place beside memsearch. Ranked by curator confidence.

Alternative to See all + compare →

opencode-mem

OpenCode plugin giving coding agents persistent cross-session memory — local SQLite + vector search, automatic memory capture, user-profile learning, and a web UI. Nothing leaves your machine.

Why it fitsSame job — persistent cross-session memory for coding agents — different reach: opencode-mem goes deep on one host (OpenCode, local SQLite, nothing leaves the machine); memsearch spans four hosts with one shared Markdown+Milvus store.

claude-reflect

Claude Code plugin that learns from your corrections — hooks capture them in-session, /reflect syncs approved learnings to CLAUDE.md/AGENTS.md, /reflect-skills mines history into reusable commands.

Why it fitsBoth mine your sessions into reusable assets: claude-reflect captures corrections into CLAUDE.md and /reflect-skills commands for Claude Code; memsearch's skills-from-memory does the same distillation continuously, across four agent platforms.

MemMolt

Structured long-term memory over MCP: an enforced bucket-thread-memo hierarchy in one SQLite file, hybrid FTS5 + vector search fused with RRF, local embeddings.

Why it fitsBoth are structured long-term memory with hybrid search for agents: MemMolt enforces a bucket-thread-memo hierarchy in one SQLite file over MCP; memsearch bets on free-form Markdown + Milvus and per-agent plugins.