Open-source AI agents, trust-scored with autonomy and sandbox awareness. 9 agents available.
Showing 1–9 of 9 results
Interactive coding agent that runs code locally with human confirmation.
Code-generation agent that builds applications from a natural-language spec.
An AI-powered code review agent built with Mastra that analyzes any GitHub pull request and returns detailed feedback directly in chat. It uses a structured wor
Princeton coding agent that fixes real GitHub issues; runs in a Docker sandbox.
Dynamic breakpoints Review We discussed motivations for human-in-the-loop: (1) Approval - We can interrupt our agent, surface state to a user, and allow the use
Breakpoints Review For human-in-the-loop, we often want to see our graph outputs as its running. We laid the foundations for this with streaming. Goals Now, let
Parallel node execution Review In module 3, we went in-depth on human-in-the loop, showing 3 common use-cases: (1) Approval - We can interrupt our agent, surfac
Time travel Review We discussed motivations for human-in-the-loop: (1) Approval - We can interrupt our agent, surface state to a user, and allow the user to acc
Editing graph state Review We discussed motivations for human-in-the-loop: (1) Approval - We can interrupt our agent, surface state to a user, and allow the use