ReMe vs cabinet
Markdown-based AI memory and knowledge workspaces compared
ReMe and cabinet both keep AI context in Markdown files on disk for reuse across sessions. ReMe focuses on capturing, organizing, and retrieving agent memory, while cabinet combines a knowledge base with agent workflows, scheduled jobs, and team tools.
ReMe: Build a File-Based Memory Workspace for AI Agents
ReMe is a Python memory-management kit for agents, built around a local-first, self-evolving knowledge base stored as Markdown files. It helps agent users capture conversations and resources, refine durable knowledge, and retrieve relevant context across supported agent integrations.
cabinet: Build a Self-Hosted AI Knowledge Base
Cabinet combines a local, Markdown-based knowledge base with AI agents, scheduled jobs, and team workflows. It is aimed at people who want persistent AI context and automation while keeping their files on disk and under their control.
| ReMe | cabinet | |
|---|---|---|
| Language | Python | TypeScript |
| License | Apache-2.0 | MIT |
| Stars | 3.7k | 2.9k |
| Forks | 321 | 302 |
| Last analyzed | Oct 23, 2026 | Oct 3, 2026 |
Key differences
- ReMe is a memory toolkit with conversation capture, linked notes, and passage retrieval; cabinet is a self-hosted workspace with missions, tasks, and team workflows.
- ReMe offers CLI, HTTP, MCP, and Python interfaces, plus runtime integrations; cabinet provides a local web application with Claude Code and Codex CLI adapters.
- ReMe is written in Python and uses the Apache-2.0 license; cabinet is written in TypeScript and uses the MIT license.
- ReMe can perform basic file operations and BM25 search without LLM credentials, though LLM-powered processing needs configuration; cabinet’s agent tasks require a supported AI CLI provider.
- ReMe is suited to developers seeking persistent, user-controlled agent memory; cabinet targets individuals and small teams managing project knowledge and repeatable work.
- ReMe has 3.5k stars and 306 forks; cabinet has 2.9k stars and 302 forks.
Choose ReMe if you…
- need agent conversations and resources turned into searchable, editable memory notes.
- want to access a shared memory workspace through interfaces such as MCP, HTTP, or Python.
- prefer basic file operations and BM25 search that can work without LLM credentials.
Choose cabinet if you…
- want a self-hosted knowledge base with Git-backed history, diffs, and page restoration.
- need agents, scheduled jobs, task boards, and internal chat in one workspace.
- want to render HTML apps from knowledge-base folders or use an included web terminal.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.