Why my AI agents keep lie-ing? How do we trust?

dotpals is an open-source (MIT) floating desktop pal that watches coding agents like Claude Code and Codex, checking what they changed, what they ran, and whether tests actually passed, and sending an agent back to fix failing tests before it finishes, commits or pushes. It offers a report card comparing agents' real work, replay and rewind of requests, an MCP server so any AI tool can query what really happened, and a local-only bridge that keeps agent work on your computer.