Description
When an AI coding agent does work, it's hard to review afterward what it called and how it progressed. Agenttrace lets you see through it: a local-first TUI for inspecting AI coding agent sessions, replay each of the agent's steps, tool calls and key decisions in the terminal, with data kept locally, handy for debugging and reviewing agent behavior. A macOS app, open source.
Session inspection: Replay each agent step.
Local-first: Session data kept locally.
Terminal UI: A TUI you view in the terminal.
Open and free: An open-source project, free to use.
Features
Session inspection: Replay each agent step.
Local-first: Session data kept locally.
Terminal UI: A TUI you view in the terminal.
Open and free: An open-source project, free to use.
