Lehigh researchers release open-source AI tool that consolidates research workflows
Lehigh University researchers have built Dr. Claw, an open-source AI assistant that handles the full arc of scientific research-from idea refinement and literature reviews through experiments, paper drafting, grant writing, and presentations-within a single interface.
The tool eliminates the friction of toggling between specialized AI systems. Instead of moving between separate applications for research agents, code generators, and writing assistants, researchers work in one unified environment.
"Everything an investigator, professor, or student needs to complete a project is within this ecosystem," says Lichao Sun, an assistant professor of computer science and engineering at Lehigh who led the development team. "It's meant to accelerate the ability to conduct scientific research."
Built as an integrated development environment
Dr. Claw operates as an Integrated Development Environment (IDE)-the kind of unified workspace programmers use daily-adapted for scientific work. It draws on three major large language models: Anthropic's Claude Code, Google's Gemini CLI, and OpenAI's Codex.
Sun's vision for the tool emerged after OpenAI released ChatGPT in late 2022. He noticed his own students constantly switching between disparate tools while conducting research. "I said to them, 'Why are we switching back and forth? Why don't we consolidate these tools into one system?'" he says.
Speed and scale in academic publishing
Sun and five Ph.D. students built the software in three months. A task that would have required 20 to 30 people working for a year or two in the past now took a small team weeks.
One student used Dr. Claw to finish a paper for a top-tier conference in two weeks-work that previously would have taken two to three months. Since its public release in mid-March, the tool has gained roughly 1,000 stars on GitHub.
How it handles accuracy and privacy
Dr. Claw addresses two concerns that plague AI research tools: hallucinations and data security. The system doesn't generate answers from scratch. Instead, it grounds outputs by cross-referencing verified, peer-reviewed databases and includes human checkpoints to validate critical steps.
For data privacy, sensitive information can be processed locally or on secure academic servers, ensuring proprietary data stays under researcher control.
Sun, whose background centers on AI safety, designed these safeguards into the tool from the start. "There are elements of the research process that are extremely time-consuming and could be more efficiently conducted by AI, under the direction and guidance of a human," he says. "Replacing these processes with algorithms would not only accelerate the process, but it could reduce the cost of doing research as well."
What comes next
Sun's immediate goal is to scale adoption of Dr. Claw across institutions. He envisions it becoming a standard tool supported by Lehigh's Library and Technology Services for the entire campus research community.
The recognition has extended beyond campus. Sun earned an invitation to the advisory board of the 2026 AI Scientists Conference at the University of Toronto.
Mayuresh Kothare, Lehigh's associate dean for research, noted the competitive landscape: "The market space for tools and bots to support research is crowded. Every major corporate entity, such as Microsoft, Google, and Apple, is developing a competitive product. It is truly remarkable that within such a short time, Dr. Sun's lab has been able to develop Dr. Claw as an open-source tool with the potential to play a major role in supporting the next generation of scientific discoveries."
For researchers interested in the technical foundations behind Dr. Claw, explore Generative AI and LLM Courses or AI Research Courses to deepen your understanding of the models and methods that power such tools.
Your membership also unlocks:
