AI product Open source
arc-code is a minimal harness for testing whether a general coding agent can learn unfamiliar ARC-AGI-3 games during play. It runs a headless coding agent with a shell, filesystem, and action command inside an internet-isolated sandbox; the harness provides no solver, planner, world model, grid tooling, fine-tuning, MCP servers, subagents, plugins, or hooks.
The agent interacts with each game only through `act.py`, which executes actions and appends resulting boards and actions to a log. It uses the shell and approved file tools to parse that log, record findings, and build task-specific machinery such as parsers, rule models, simulators, and search procedures, which are discarded when the game ends. `run.py` launches and records one session per game, while the `rig/` directory supplies sandboxing, brokering, auditing, scoring, and export infrastructure. The repository includes the harness and six complete session records.
1 use taken from transcripts — each links to the moment in the video.
A minimal harness for testing whether a general coding agent can learn unfamiliar ARC games by building tools during play. The agent receives a shell, files, and an action command inside a default-deny sandbox.
1 in the library.