Mem for AI agents
Mem is a note-taking and knowledge management app that helps individuals capture, organize, and retrieve notes and collections without heavy manual filing. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Mem.
Save a new note
Save a piece of content as a new note so it is captured in a collection.
Search notes by topic
Search existing notes for a topic to pull relevant context, a read-only lookup.
Approve before deleting a collection
Require approval before deleting a collection, since it removes every note filed under it.
11 Mem actions, graded by risk.
Every Mem action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- mem.list_notesList Notes
- mem.search_notesSearch Notes
- mem.get_collectionGet Collection
- mem.list_collectionsList Collections
- mem.search_collectionsSearch Collections
- mem.read_noteRead Note
write
3Create and change things. Allow, or ask the user first.
- mem.create_note_v2Create Note V2
- mem.create_collectionCreate Collection
- mem.save_contentSave Content
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- mem.delete_noteDelete Note
- mem.delete_collectionDelete Collection
Mem in three steps.
- 01Your users connect MemThey add their Mem api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Note V2” can wait for the user, and “delete Note” can be denied outright.
- 03Any agent can actYour agent calls Mem through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mem', { read: 'allow', write: 'ask', // create_note_v2 destructive: 'deny', // delete_note }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Mem connects.
Users add their Mem api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Mem connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Mem from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Mem and Arc0, answered.
Can I use Mem with Claude, ChatGPT or Cursor?
Yes. Connect Mem to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Mem actions you allow.
How do users connect Mem?
Users add their Mem api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Mem actions can my agent take?
11 in total: 6 read, 3 write and 2 destructive, such as “create Note V2”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Mem?
Yes. Actions like “delete Note” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Mem too?
Yes. The same Mem connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Mem into your agent.
Your users connect Mem once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan