Integrations/GitHub

Control what your AI agents do in GitHub.

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

Request early accessSee how it works →
GitHub
Dev Agent
app-backend RepositoryOffReadFull use
infra RepositoryOffReadFull use
payments RepositoryOffReadFull use
Manage secrets and settings
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 code, issues, and pull requests in that repository. It can't change anything.
Full use
Open and update
The agent can open issues and pull requests and update them in that repository.

Some actions stay off until explicitly turned on

Each one can leak credentials, remove work for good, or ship to production, so it could override the limits set on individual repositories.

Reading or changing repository secretsDeleting a repository or branchRunning and approving workflows
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 GitHub 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, open, and update issues and pull requests in a single repository
Example

A code review agent.

A dev agent opens pull requests on app-backend and can read infra, but it can't open the payments repository or touch secrets.

app-backend RepositoryOffReadFull use
infra RepositoryOffReadFull use
payments RepositoryOffReadFull use

Manage access

ALLOWEDDev Agent opened a pull request in app-backend
ALLOWEDDev Agent read an issue in infra
BLOCKEDDev Agent tried to open the payments 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 GitHub, so they never hold your GitHub keys and never reach GitHub directly.

Everything runs through Bollard AI

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

Denied by default

Every repository starts off-limits, and touching secrets 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 GitHub 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 pull request, and the decision. The record is readable and can't be edited after the fact.

Questions

GitHub, answered.

Does connecting GitHub 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 code. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent read our secrets or ship to production?+
Not unless you turn it on. Reading or changing repository secrets, and running workflows, are held off by default, so an agent can open and review pull requests where you allow without ever touching credentials or shipping, 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 GitHub 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 GitHub, and the blocked attempt lands in the activity record with the reason.
How do we connect GitHub?+
An admin connects the company's GitHub 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 GitHub, 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 →