GitHub · Connector
How do we connect GitHub to AI agents on our own infrastructure?
Katonic connects to GitHub, reads a repository's documentation, issues, pull requests, wiki and code and indexes them in the Knowledge Engine on infrastructure you control. Agents answer from them with a model you serve, so your code and the questions are not sent to a public AI service.
What it reads.
From GitHub.
- 01The README and documentation files
- 02Issues, with their comments
- 03Pull requests, with their review comments
- 04Wiki pages
- 05Code files, for the file types you choose
Through: GitHub REST and GraphQL APIs
Where the content goes
Into a knowledge store you run.Content is pulled into the Knowledge Engine on infrastructure you own or control, and indexed there. Agents answer from it with a model you serve. The documents, the index and the questions are not sent to a public AI service.
How it signs in
In the set-up dialog you give the repository address and, where it needs one, a personal access token. The connector also supports a GitHub App.
The set-up dialog asks for
- Repository URL
- GitHub token (optional)
Permissions
Access is set on the source in Katonic: everyone given access to the source can retrieve its documents.
Sync
Incremental, by the time of the last push or update, and full.
You set how often the source is read again, in minutes, hours, days or weeks.
Does it read private repositories?
It reads the repository you name, with the token you give it.
Does it read code as well as documentation?
Yes, for the file types you choose.
Where is the repository indexed?
In the Knowledge Engine, on infrastructure you own or control. It is not sent to a public AI service.