Researchers introduce Dr. Claw, an open-source workspace that wraps existing command-line coding agents, such as Claude Code and Gemini CLI, in an auditable, human-in-the-loop workflow for end-to-end research rather than introducing another fully autonomous agent. The system uses persistent state objects, a reusable skill library, and multi-executor coordination to link human decisions to AI execution, keeping planning, execution, and writing in one traceable, recoverable process. In evaluations against a bare command-line agent sharing the same backend executor, Dr. Claw scored higher on research completeness while preserving an auditable process trail.
