Work / BigBrain
BigBrain
The control plane for the whole engineering estate: one place that knows every project, runs AI work against them, and keeps the evidence.
What it does
BigBrain is the system the other projects are built inside. It keeps a registry of 36 internal projects and 131 studied external repositories, with their ports, status and health. Work is started and watched in BigTerminal. What the work teaches is kept in a provenance-tracked knowledge graph, and design quality has its own research lab. Models, budgets and providers are governed in one place, so every run's route and cost can be checked afterwards.
- Every estate project is registered with its ports, status and health
- Start, stop and open project servers from one page
- Start AI work against a project in BigTerminal
- Models, providers and budgets are governed in one place
- What the work teaches is kept in the knowledgebank
- Each run’s route and cost can be audited afterwards
How it works
BigBrain is a Node and Express control plane with a React interface, organised around a handful of questions: what is in the estate, what work is running, what has been learned, and what it cost. The estate registry is compiled from the projects themselves and records where each claim came from and how confident it is. Model routing, provider pools and budget ceilings are shared by every run. An MCP bridge lets external coding agents ask BigBrain for project context instead of rediscovering it. Each subsystem has its own proof scripts, and an operator switch turns autonomous work on or off for the whole estate.
Skills shown
- Data engineering
- Compiles one estate registry from the projects themselves, recording the provenance and confidence of every field.
- Cloud, servers & networking
- Starts, stops and health-checks every project’s local server from one page, with one switch that halts all autonomous work.
- DevOps & CI/CD
- GitHub Actions CI validates the repository, and every subsystem has its own proof scripts.
- APIs & backend
- An Express control plane with an MCP bridge that serves project context to external coding agents.
- AI, agents & ML
- Shared model routing, provider capacity and budget ceilings across cloud and local models, with free-only spending enforced before each call.
- Frontend, 3D & graphics
- A React and TypeScript interface built with Vite.
Worth knowing
- Compiles one registry of the estate from the projects themselves, with the provenance and confidence of every field.
- Shares model routing, provider capacity and budget ceilings across every run, with a free-routes-only mode enforced before each call.
- Exposes project context to external coding agents over MCP.
- Has a single operator switch that stops all autonomous work across the estate.