Agents demonstrate complete thinking

Project overview

internalcot Make agents show their full chain of thought.

internalcot adds an opt-in reasoning workspace to Codex and Claude Code. Turn it on once and the agent must externalize its problem decomposition, intermediate derivation, alternatives, evidence, uncertainty, and checks in the normal tool transcript for the full conversation.

The result is a persistent, readable chain of thought you can inspect as the agent works. The agent writes its reasoning into visible working notes. Install