Dr. Claw AI scientist workspace for auditable research
An open-source workspace wrapping coding agents in a controllable, auditable human-in-the-loop workflow.
Dr. Claw is an open-source workspace designed to integrate AI coding agents into a human-in-the-loop workflow for scientific research. It focuses on making the research process auditable and recoverable by preserving decisions and linking them to AI execution.
AI-assisted scientific research, particularly in areas requiring auditable decision-making and recoverable workflows.
Free (open-source, AGPL-3.0 license)
https://github.com/OpenLAIR/dr-claw
Dr. Claw provides an auditable, human-in-the-loop workflow for AI coding agents. It preserves research decisions, links them to AI execution, and makes the process traceable and recoverable, improving research completeness compared to bare command-line agents.
It uses persistent state objects, a reusable skill library, and multi-executor coordination to link human decisions to AI execution, creating a traceable loop for planning, execution, and writing.
- Dr. Claw: An AI Scientist Workspace for Vibe Research ↗arXiv · arXiv cs.AI · Aug 31, 2026 · paraphrased
First seen on Subvolts Aug 31, 2026. Updated Sep 11, 2026. Spotted a problem? Tell us.
- Dr. Claw: An AI Scientist Workspace for Vibe ResearchAnthropic · arXiv cs.AI · Aug 31, 2026
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- HeuristicCompaction for multi-context window operationUtilize compaction to enable models to operate coherently across millions of tokens in multiple context windows. · 5 min
- ToolOpenAI API for general purpose text in, text out interfaceAccess new AI models via a general-purpose text interface for diverse English language tasks. · 10 min
- Case studyUsing LLMs to build tools for iOS location data analysisResearchers used an LLM to build a tool that decoded iOS location data, overcoming LLM analysis limitations. · 60 min
- ToolExtractor tool to recover protobuf schemas from Apple binariesPython tool to reliably recover protobuf schemas from Apple binaries for analysis. · 30 min
- HeuristicRegenerative software primitives for knowledge preservationUse machine-readable records and regeneration bundles to preserve software knowledge when code is deleted. · 60 min
- Troubleshooting fixUse Pseudo-Huber losses instead of LPIPS for consistency modelsReplace LPIPS with Pseudo-Huber losses to avoid undesirable bias in consistency model evaluation. · 5 min
Questions people ask
- Which AI tools does this work with?
- Any current model. It was seen with in the sources.
- Where did this come from?
- arXiv (arXiv cs.AI). Subvolts collected, normalized and credited it; the link above opens the original.