ThinkingBox
Named by 2 kept items in this workspace.
Search every workspace for ThinkingBox. It matches the name as written, so it can find other things that share it.
The items that name it 2
Sandbox and framework that gives agents a real backend, MCP tools and a simulated LLM user, then grades the final database state with executable checks.
Agent sandbox that runs agents against isolated MCP tool sessions and grades terminal backend state and side effects left behind
All technologies in this workspace.