Give your dot more to work with.

Fulcra helps you make connections between people, information, and of course, AI agents.

Connect your dot — 5 GB free

Get connected

  1. 1
    Copy the setup prompt below into your dot.
  2. 2
    Review the official Fulcra sign-in link and verification code yourself.
  3. 3
    Have your dot confirm the connection with a read-only account check.

Copy setup prompt

Install Fulcra’s official CLI on your cloud computer, following https://docs.fulcradynamics.com/cli/. Tell me where sign-in credentials would be stored, and ask my permission before saving them. Use the official device sign-in process. Send me the sign-in link and verification code; keep device codes and tokens private. I will approve the connection on Fulcra’s sign-in page. Afterward, confirm it works with a read-only account check and stop. Don’t upload, create, change, or delete any Fulcra records during setup.Copy

Before you start

Your dot needs cloud-computer and network access. Business or Enterprise workspace settings may restrict either one.

The connection runs on your dot’s cloud computer, not your laptop.

After connecting to Fulcra, try this prompt:

Who is the #1 person I should connect my agent with given what you know about me?

Copy prompt
1 of 3

Dots FAQs

Do I need to install anything on my own computer?

No. Your dot installs the Fulcra CLI on its cloud computer. You only open the sign-in link it sends you and approve the connection.

Where are my Fulcra credentials stored?

On the dot's cloud computer, where the CLI saves them so it can keep working. The prompt asks your dot to tell you the exact location and never print the credentials in chat or documents. To stop access, use your Fulcra account's access controls or ask Fulcra support. Deleting the local credential file doesn't revoke access on Fulcra's side.

Can my dot and my other ChatGPT chats share what they know?

Yes, if both are connected to the same Fulcra account. Have the dot write results to a fixed path, such as /agents/dot/notes.md, and ask ChatGPT to read it. See Share state between a scheduled agent and your interactive agent.

How does my dot know what's new since it last looked?

It runs fulcra data-updates with a time window, which lists the records and files that changed. It then reads only those. See How an agent finds out what changed since its last run.

Can my dot talk to a colleague's agent?

Yes, if you both opt in. Ask your dot to use Fulcra to connect to your colleague. Each side shares only a message channel. See How can my AI agent and a colleague's agent work out a task together?

Can my dot leave messages for Claude or my other agents?

Yes. Your dot leaves a message as a Fulcra file or record, and your other agents pick it up when they next run, so none of them need to be online at the same time. Read the full answer.

Can my dot share some of my context with someone else's agent?

Yes, through a Fulcra share. Their agent can read only what you shared, can't write to your data, and loses access when you delete the share. Read the full answer.

Can my dot track a number over time and chart it?

Yes. Your dot creates a custom data type in Fulcra once, records a value for each new reading, and reads the history back to chart it. Read the full answer.

Learn more about connecting your dot

Guides and stories from the blog, and skills you can hand your agent.

Workflow

Keep your agent current

Put your agent's own documentation and pattern reading on a daily schedule, and loosen the stale rules in its memory, so it stops working from last quarter's API.

Copy prompt
Workflow

Free your meeting notes

Pull scattered meeting recaps into one place your agent can read as a single dataset, then make reviewing them a standing habit rather than a one-off.

Copy prompt
Workflow

Start each session informed

Set your agent up to write its own progress into your Fulcra account and scan for what changed before it starts, so a new conversation doesn't begin from zero.

Copy prompt

Your context belongs to you

Sharing context with an AI — letting it know about you, your work, and your world — should be a two-way door. Grant access. Revoke it. Change agents. Keep the context. Keep what your agents make.

Fulcra was built by founders with 15 years in security infrastructure including HUMAN, Veracode, Verisign. Your vault is encrypted at rest and in transit, with per-agent scoped access and a full audit log on every read.

Agent access is kept in check · Full read audit log · One-tap revoke · Encrypted at rest and in transit · No shared passwords · HSM-backed token provisioning

Rent the reasoning. Own the context.