memsearch
zilliztech
Cross-agent memory layer backed by human-readable Markdown and Milvus, local by default.
What is memsearch?
A persistent, cross-platform memory layer for AI coding agents that auto-captures conversations, summarises them into daily Markdown files as the source of truth, and indexes them in Milvus for recall. Retrieval uses hybrid dense plus BM25 search with progressive recall, and one memory is shared across Claude Code, OpenClaw, OpenCode and Codex.
Pros & Cons
Pros
- Markdown as source of truth keeps memory human-readable, editable and version-controllable
- Genuinely cross-agent: one shared long-term memory across several coding agents
- Local-first by default (ONNX embeddings plus Milvus Lite, no API key needed), MIT-licensed
Cons
- Pre-1.0 (0.4.x) with a broad, young feature surface (auto-capture, skills distillation, background maintenance)
- Built by the Zilliz/Milvus team and centred on Milvus as the vector backend
- No quantified recall benchmarks published, so retrieval quality is unverified
License
MIT (OSI-open)
When it is interesting
Using several coding agents and wanting one shared, inspectable long-term memory.
When it is too early
If you need a stable 1.0, backend-neutral memory, or proven recall before auto-ingesting all agent conversations.
Commercial alternative & related
- Commercial counterpart: Mem0
This repo featured in the 2026-07 edition of the Open-Source AI Radar.
claude-mem
thedotmack
Persistent memory layer across agent sessions with automatic semantic summaries and token-cost transparency.
graphify
safishamsi
AI coding skill that turns a folder of code, docs and images into a queryable knowledge graph across 20+ agents.
memU
NevaMind-AI
Memory framework for proactive AI agents - typed memory graph from chats, docs and media.