Integrations/Docker Hub

Control what your AI agents do in Docker Hub.

Let your team build AI agents for Docker Hub. Bollard AI controls what each one can do, repository by repository.

Request early accessSee how it works →
Docker Hub
Release Agent
app-images RepositoryOffReadFull use
base-images RepositoryOffReadFull use
private RepositoryOffReadFull use
Delete repositories and tokens
What agents can do

Set what each agent can do in every repository.

Each repository gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.

Off
No access
The agent can't see the repository or that it exists.
Read
Read-only
The agent can read the tags and metadata in that repository. It can't change anything.
Full use
Push and update
The agent can push and manage tags in that repository.

Some actions stay off until explicitly turned on

Each one removes images for good or hands out access to your registry, so it could override the limits set on individual repositories.

Deleting repositories or tagsCreating or deleting access tokensChanging team membership
Set up & manage

Connect once. Manage everyone from there.

Connect once, then control access person by person. No new keys to hand out.

Step 1 · Set up

Connect once, company-wide

An admin connects your company's Docker Hub a single time and chooses which repositories it covers. Any repository left out stays out of reach for every agent.

Step 2 · Manage

Control access per person and agent

From one dashboard, set what every person and their agents can reach. Change it any time, with no new keys for anyone.

OffNo access
ReadRead-only
Full useRead, push, and manage tags in a single repository
Example

A release publishing agent.

A release agent pushes tags to app-images and can read base-images, but it can't open the private repository or change access tokens.

app-images RepositoryOffReadFull use
base-images RepositoryOffReadFull use
private RepositoryOffReadFull use

Manage access

ALLOWEDRelease Agent pushed a tag to app-images
ALLOWEDRelease Agent read a tag in base-images
BLOCKEDRelease Agent tried to open the private repository, denied by default

Monitor activity

The security model

Top-tier security.

Bollard AI is access control for AI agents. It sits between your agents and Docker Hub, so they never hold your Docker Hub keys and never reach Docker Hub directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Docker Hub. Bollard AI checks each one against your rules and passes only the allowed requests through.

Denied by default

Every repository starts off-limits, and changing access tokens is held back on top of that. An agent gets in only where you've allowed it, and anything Bollard AI doesn't recognise is refused and held for review, never waved through on a guess.

Your keys stay sealed

Your Docker Hub keys are sealed in a vault unique to your company and never shown again. Bollard AI unlocks them only for the instant an allowed request needs it.

Activity you can read

Every attempt is recorded in plain English: who or which agent, what they tried, which repository or tag, and the decision. The record is readable and can't be edited after the fact.

Questions

Docker Hub, answered.

Does connecting Docker Hub hand Bollard AI all your repositories?+
Only what's connected. An admin chooses which repositories Bollard AI covers, and that sets the most any agent could reach. Bollard AI doesn't browse or copy your registry. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent delete images or hand out access?+
Not unless you turn it on. Deleting repositories and tags, and creating or deleting access tokens, are held off by default, so an agent can push where you allow without ever removing images or handing out access, until you explicitly allow it.
Can an agent see more than the person who owns it?+
No. An agent reaches only what its owner reaches. An explicit Off always overrides an inherited permission.
Where do our Docker Hub keys live?+
Sealed in an encrypted vault, behind a key unique to your company. It's never shown again once connected, and Bollard AI unseals it only for the instant an allowed request needs it.
What happens when an agent tries something it's not allowed to do?+
Bollard AI blocks the request before it reaches Docker Hub, and the blocked attempt lands in the activity record with the reason.
How do we connect Docker Hub?+
An admin connects the company's Docker Hub once. Bollard AI seals the connection and builds the list of repositories to set rules for. From then on, all management happens in the Bollard AI dashboard.
Early access

Put your team's agents to work in Docker Hub, without the risk.

We're onboarding our first development partners now. Tell us about your setup and we'll be in touch.

Request early accessAll integrations →