Memstem

Memstem — DevOps skill for Claude Code

DevOps community

Unified memory and skill infrastructure for AI agents — pull-based ingestion across Claude Code, OpenClaw, Codex, Cursor, and more.

How to install Memstem

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Memstem/memstem and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Memstem does

Unified memory and skill infrastructure for AI agents — pull-based ingestion across Claude Code, OpenClaw, Codex, Cursor, and more. Markdown canonical + SQLite hybrid index + MCP-native API.

Alternatives in DevOps

Skill Claw — OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox 2.8k ★
Second Brain Cloudflare — One memory layer, every AI tool 734 ★
Platform — Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops 228 ★

README

Memstem

[![Stars](https://img.shields.io/github/stars/Memstem/memstem?style=social)](https://github.com/Memstem/memstem/stargazers) [![PyPI](https://img.shields.io/pypi/v/memstem)](https://pypi.org/project/memstem/) [![CI](https://github.com/Memstem/memstem/actions/workflows/ci.yml/badge.svg)](https://github.com/Memstem/memstem/actions/workflows/ci.yml) [![License](https://img.shields.io/badge/license-MIT-blue.svg)](./LICENSE)

Unified memory and skill infrastructure for AI agents. One canonical knowledge store. Many AI clients. No version-fragility.

A central memory with stems reaching out to other systems, drawing their memories in.

![Memstem — one memory layer for every AI agent](./docs/images/hero.png)

**If memstem helps you, please ⭐ [the repo](https://github.com/Memstem/memstem)** — there's no telemetry here, so stars are the only signal I have for whether to keep building this in the open.

What it is

Memstem is a **standalone memory service** that acts as the single source of truth for memories and skills shared across multiple AI environments. Unlike traditional memory layers that you push to from each AI, Memstem **pulls** from the filesystem of each connected AI — so it's immune to upgrade churn in any of them.

Connect Claude Code, OpenClaw, and Codex today — adapters for Cursor, Aider, and more are on the [roadmap](./ROADMAP.md). Memstem watches each system's session and memory files, ingests new content within seconds, and exposes one unified search API via MCP.

Why

Existing AI memory systems break when their host upgrades. Push-based hooks fail silently across version changes. Each AI has its own memory format, and there's no clean way to share knowledge across them.

Memstem solves this by:

Pull-based ingestion via inotify / FSEvents filesystem watchers — no hooks, no push APIs to break
Markdown-canonical storage — files are the truth, the index is rebuildable
Hybrid search — BM25 (FTS5) + cosine similarity (sqli