Dr. Claw：用於氛圍研究的人工智慧科學家工作區

摘要

命令列編碼代理（如 Claude Code、Gemini CLI）已能讀寫檔案並維持長時間的工作階段，但端對端研究仍舊分散於聊天工具、整合開發環境、終端機與寫作環境之間，而且使研究可被稽核的決策過程也鮮少被保存下來。我們提出 Dr. Claw，一個開源工作區，它將現有的編碼代理執行器包覆在可控、可稽核的人機迴圈工作流程中，而非再引入另一個自主代理。透過持久化狀態物件、可重用技能庫與多執行器協調，將人類決策與 AI 執行連結起來，使規劃、執行與寫作形成單一、可追蹤且可回復的迴圈。我們透過互動式三視圖情境與失敗回復逐步示範來展示 Dr. Claw，並將其與使用相同後端執行器的裸命令列代理進行比較，因此該比較對照了整體編排層（任務圖、狀態物件與技能庫）與其所包覆代理之間的差異。在固定執行器的條件下，Dr. Claw 在研究完整性上獲得更高的評分，同時留下可稽核、可回復的流程軌跡。示範存取：存放庫 https://github.com/OpenLAIR/dr-claw，以 AGPL-3.0 授權釋出，並包含 GPL-3.0 上游元件。

English

Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fragments across chat tools, IDEs, terminals, and writing environments, and the decisions that make it auditable are rarely preserved. We present Dr. Claw, an open-source workspace that wraps existing coding-agent executors in a controllable and auditable human-in-the-loop workflow rather than introducing another autonomous agent. Persistent state objects, a reusable skill library, and multi-executor coordination link human decisions to AI execution, turning planning, execution, and writing into one traceable, recoverable loop. We demonstrate Dr. Claw through an interactive three-view scenario and a failure-recovery walkthrough, and evaluate it against a bare command-line agent sharing the same backend executor, so the comparison contrasts the whole orchestration layer (task graph, state objects, and skill library) with the agent it wraps. Holding the executor fixed, Dr. Claw scores higher on research completeness while persisting an auditable, recoverable process trail. Demo access: repository https://github.com/OpenLAIR/dr-claw, released under AGPL-3.0 with GPL-3.0 upstream components.