Basic Memory vs Memlo: which memory to use
Last updated
Basic Memory keeps your knowledge as Markdown files on your computer that both you and your AI can read, write and search, through an MCP server, with an optional paid cloud for sync, version history and teams. Memlo is a hosted memory server: Claude Code, Codex, claude.ai, ChatGPT and other MCP apps share memories that agents save on purpose, and every version records who wrote it. Pick Basic Memory if you want plain files you own, edit in Obsidian and can keep entirely local. Pick Memlo if you want one hosted memory shared across agents and people, with authors on every change and nothing to install.
At a glance
Facts about Basic Memory come from its own site, repository and documentation, read on October 31, 2026. Links are in Sources at the end.
| Basic Memory | Memlo | |
|---|---|---|
| What it is | Markdown files that "both you and your AI can read, write, and search," with a knowledge graph built from them | A hosted MCP memory server for your agents |
| Where data lives | On your computer as Markdown; optionally synced to Basic Memory Cloud | In your Memlo account, hosted in the United States |
| How memories are made | The AI writes and edits notes with MCP tools; you can edit the same files yourself | The agent saves a memory with a tool when something is worth keeping |
| Install | A local app and MCP server | Nothing to install: add https://memlo.ai/mcp and sign in |
| Agents | Claude Desktop, Claude Code, Codex, Cursor, VS Code and ChatGPT, per its README | Claude Code, Codex, claude.ai, Claude Desktop, ChatGPT, Gemini and other MCP clients that sign in with OAuth |
| Edit by hand | Yes: the files work in Obsidian and any editor | In the Memlo app |
| History of a memory | On Basic Memory Cloud: "Every saved version of a note is preserved automatically" | Every change is a version you can view and restore |
| Restore an earlier version | On Basic Memory Cloud: restore or merge an old version from File history | Yes: restore_memory brings back any version, as a new version |
| Which agent wrote each change | Versions show time, a version ID and size; "who changed what" is in the Business plan's audit log | Every version records the person and the connected app or agent that wrote it; memory_history lists them |
| Share with a person | Cloud workspaces with Viewer, Editor and User Admin roles | A space or a single page, by email as a Viewer or an Editor, with a link, or with a team |
| Audit trail | "Audit logs of who changed what" on the $249 Business plan | Included at no extra tier: every memory version and every sharing change is recorded. No space-wide activity view or export yet |
| License | AGPL-3.0 | Not open source |
| Price | Free and open source; Cloud $19, Pro $99 and Business $249 a month, per workspace | Free during the invitation-only beta |
| Can you start today | Yes | By invitation; join the waitlist |
How Basic Memory works
Basic Memory stores each note as a Markdown file. Its README says "observations and wikilinks compound into context": notes link to each other, and Basic Memory builds "a real knowledge graph" from those links. Your AI reaches the notes through MCP tools to write, read, edit, move, delete, search and list them, and you can open the same files in Obsidian or any editor.
The app is free and open source under AGPL-3.0. Basic Memory Cloud adds sync between devices, version history ("Every saved version of a note is preserved automatically in Basic Memory Cloud") and team workspaces. On October 31, 2026 its pricing page listed Cloud at $19 a month per workspace (you and one other member), Pro at $99 (up to 5 members) and Business at $249 (up to 25 members, with a User Admin role and audit logs). Its GitHub README still mentions earlier $15 beta pricing.
How Memlo works
Memlo is an MCP server at https://memlo.ai/mcp. You add it to each agent and sign in once, with no API key. Agents get tools to save, search, read, change and retire memories.
- One memory for every agent. Claude Code, Codex, claude.ai and ChatGPT find the same memories when they sign in to the same account, on any computer.
- History, with authors. Every change is a version, with when it was written and by whom: the person, and the connected app or agent they used. Any version can be restored, and
edit_memoryrefuses a write when someone else changed the note first. - Spaces and sharing. Keep memories in spaces, and share a space or a page with people by email as a Viewer or an Editor.
- A wiki and a graph. Memlo keeps a page for each person, project and tool your memories mention, with every line citing its memory.
Where Basic Memory is the better choice
- You want plain files you own. Notes are Markdown on your disk, readable without any service.
- You want to keep everything local. The free app needs no account. Memlo is hosted.
- You use Obsidian. Basic Memory reads and writes the same files.
- You use Cursor. Basic Memory lists Cursor among its clients; Memlo's sign-in doesn't work from Cursor yet.
- You want to read or change the code. Basic Memory is AGPL-3.0.
Where Memlo is the better choice
- You want hosted memory with nothing to install. Add one URL to each agent and sign in, on any computer.
- You want to see which agent wrote each version. Every version names the person and the connected app or agent, on every account. Basic Memory's file history shows when and how big, and its audit log is on the Business plan.
- You want an audit trail without a business plan. Memory versions and sharing changes are recorded for everyone.
- You share single pages with people. Share one page, not only a whole workspace, by email with a role.
- You want conflict checks between agents.
edit_memoryrefuses a stale write instead of overwriting another agent's change.
What Memlo doesn't do yet
- Cursor. Memlo's sign-in doesn't work from Cursor yet, while Basic Memory lists Cursor as a client.
- Local files. Memlo stores memories in your account, not as Markdown on your disk. You can export them.
- Automatic capture. Agents save memories on purpose; nothing records sessions in the background.
- An SDK or API keys. Memlo is reached over MCP with your own sign-in.
- Open sign-up. Accounts are by invitation for now; you can join the waitlist.
Frequently asked questions
Is Basic Memory free?
The app is free and open source under AGPL-3.0, and runs locally. Basic Memory Cloud, with sync, version history and teams, starts at $19 a month per workspace on its pricing page, read on October 31, 2026.
Does Basic Memory have an MCP server?
Yes. Basic Memory is an MCP server: its tools let your AI write, read, edit, move, delete, search and list notes. Its README lists Claude Desktop, Claude Code, Codex, Cursor, VS Code and ChatGPT.
Does Basic Memory keep a history of notes?
On Basic Memory Cloud, yes: "Every saved version of a note is preserved automatically." Each version shows its time, a short version ID and its size. Audit logs "of who changed what" are on the Business plan.
Is there a Basic Memory alternative that's hosted?
Memlo is one: a hosted MCP memory server that Claude Code, Codex and chat apps share, with no files to sync. See also claude-mem vs Memlo and Supermemory vs Memlo.
Sources
Checked on October 31, 2026:
- Basic Memory pricing
- Basic Memory on GitHub and its license
- Cloud sync, file history and members and roles
- Memlo: the setup page, how it works and terms
Try Memlo
Memlo is invitation only for now. Join the waitlist and we'll email you when your invitation is ready.
Join the waitlist