Your agent knows everything you’ve typed and nothing you’ve lived. Connecting fixes that, and it takes one paste. Gobi gives you a short instruction for a space, you hand it to your agent, and your agent does the rest: it installs the Gobi CLI, authenticates, and confirms the connection. From then on, that space is context your agent can draw on.
Works with any agent that can run commands, including Claude Code, Codex, Cursor, and most agentic setups. If yours can use a terminal, it can connect.
Connect in three steps
Open the connect sheet
In the space you want to connect, open Space settings and choose Connectors. Gobi generates a connect instruction for that space.
Paste it into your agent
Copy the instruction and send it to your agent as a message. It looks like this:Your agent installs the CLI, authenticates with your token, and confirms. That’s the whole setup.The token is single-use and expires after 24 hours. If it expires before you connect, generate a fresh one from the same sheet. Treat it like a password, because it links an agent to that space.
Ask something only your life can answer
Try it right away:If your agent answers from your real day, you’re connected. One connection per space
Each connection is to one space. Connect your Personal space and your agent knows what you’ve captured there. Connect a team space and it knows what the team has captured. If you want your agent to have both, connect each one.
What your agent can access
Your agent sees what you see in the space you connected, and nothing more.
- Your Personal space: everything in it, including your notes with their Summaries, transcripts, attendees, side notes, and attachments, plus your posts.
- A team space: its public feeds and the private feeds you’re a member of. Other members’ notes show up as Summaries only, the same way you see them.
Your agent can’t see anyone’s Personal space but yours. Connecting never shares anything outward: information flows from the space to your agent, never the other way.
The full picture is in What agents can and can’t see.
Managing connections
You can connect as many agents as you like. Each connection uses its own single-use token from the connect sheet. Tokens expire 24 hours after they’re issued and can’t be reused, so an old instruction can never open a new connection.
Troubleshooting
The token expired. Tokens are single-use and last 24 hours. Generate a fresh instruction from the app and paste it again.
My agent says it can’t install the CLI. It needs terminal access. Agents that can only chat, without the ability to run commands, can’t connect yet.
It connected, but the answers seem empty. A new space doesn’t have much in it yet. Capture a few real conversations and ask again. The answers grow as you capture more. 
