Local Knowledge Base
My "second brain": a local knowledge base (context1) versioned in git that AI agents draw from.
About the project
The foundation almost everything else stands on. I keep all the context about projects, people, decisions, and procedures locally in a markdown base, context1, which I version in git, so I have history, certainty, and nothing gets lost.
Agents pull context from it exactly where they need it. I don't put large files (videos, binaries) in git, those live outside.
I have two skills for reading and maintaining the base so it stays clean. And what I want to share with the team then flows out through Toucan.
What you get
- The agents and I have all the context at hand.
- Versioned in git, nothing gets lost.
- I share selected parts with the team through Toucan.
How it works (under the hood)
- A markdown base, context1, versioned with git.
- Two skills for reading and maintenance.
- Large videos outside git; sharing is handled by Toucan.
Built with
Want to build like this too?
I teach building apps without programming in the AI First course.
More from Tool
Shoutbase: Testimonials Manager
An internal tool for managing testimonials: a queue of who to ask, a collection of what we've gathered, and an overview of where we use them.
Toucan: A Shared Second Brain for the Team
A shared cloud knowledge base that the team and its AI agents draw from, a "second brain" connected to my local context1.
Running a Project's Marketing Through Claude Code
A marketing team as a set of Claude Code skills: a director, department managers, and specialists that run a project alongside me.