Home/AI Agents/memsearch

memsearch

zilliztech/memsearch

A persistent, unified memory layer for all your AI agents backed by Markdown and Milvus.

GitHub Website

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

138views this month

2.6k stars253 forksLast push Sep 20, 2026 Python MIT

Decision brief

memsearch is a hybrid memory management solution for AI agents with Markdown and Milvus backing, ideal for rich semantic search and long-term data storage.

Good fit when

When you need robust integration with AI agents like Claude Code or Codex
For projects that require efficient vector searches alongside traditional text storage

Avoid when

If your application doesn't require integration with specific AI agents like Claude Code
In cases where only simple text data storage without semantic search is needed

Observed Jul 12, 2026 · Source: enrich:decision_facts

memsearch alternatives Trust report

memsearch vs mempalace

Verify the decision

Maintenance and security

Full trust report

Maintenance: Very active (0d since push); As of Sep 20, 2026
Provenance: Not a fork · Organization account; As of Sep 20, 2026
Security (OSV): No lockfile; As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Backing

Company context for Zilliz. Display-only - separate from trust and ranking.

Company: Zilliz·GitHub org profile·Jul 11, 2026
Funding: $60,000,000 (2022-08)·GraphCanon curated seed (public press)·Jul 11, 2026
Commercial model: Open core·GraphCanon curated seed·Jul 11, 2026

Install

pip install memsearch

PyPI

How it fits your stack(1)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Alternative

mempalace

Both MemPalace and memsearch offer persistent memory layers for AI agents but utilize different storage backends (ChromaDB vs Markdown + Milvus).

alternative

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

claude-mem

Persistent Context Across Sessions for Every Agent

91k★

mem0

Drop-in memory infrastructure for AI agents and apps

66k★

planning-with-files

Persistent file-based planning for AI coding agents

27k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

memsearch provides a robust memory storage solution designed to integrate with various AI agents. It combines both traditional text-based memory storage (Markdown) and vector database capabilities (Milvus), offering enriched search functionalities critical for maintaining long-term记忆存储解决方案，旨在与各种AI代理集成。它结合了传统的基于文本的记忆存储（Markdown）和矢量数据库功能（Milvus），提供了增强的搜索功能，对于维护长期记忆和语义检索至关重要。

Capability facts

CLI: CLI entrypoint
Source: pyproject.toml:[project.scripts] · Sep 20, 2026
Languages: python
Source: github.language+pyproject.toml · Sep 20, 2026

Graph entities

Zillizcompany

README

Install /plugin marketplace add zilliztech/memsearch /plugin install memsearch Install git clone depth 1 https://github.com/zilliztech/memsearch.git bash memsearch/plugins/codex/scripts/install.sh codex yolo needed for ONNX model network access bash ls .memsearch/memory/ $memory...

For agents

This page has a .md twin and JSON over the API.

/tools/zilliztech-memsearch.md GET /api/graphcanon/tools/zilliztech-memsearch GET /api/graphcanon/graph?tool=zilliztech-memsearch