How Does Prime Agent Limit Tools to IPython?

Alex Zhang describes Prime Agent as a harness on top of Pi Mono, the minimalist harness he uses as the reference for other coding harnesses. Prime Agent is Pi with one hard limit: IPython is the only tool the model can call directly.

Every other tool loads in as a Python module or a bash script the model can run. The setup puts the core code RLM abstraction on top of Pi. A continual harness also lives inside the IPython kernel as a tool. The principle is to decide which parts of the harness the harness itself may change: its own skills, the subagents available to it, and the system prompt sent to the model. Everything else in Prime Agent is standard.

Newer frontier models work well inside Prime Agent, and some newer open source models do too. Because RLMs tend to spawn many subagents, Prime Agent adds an agent-to-agent communication setup so subagents can talk to the root or to each other, with rules for whom each subagent may reach and how.