What this resource does
Core uses
About this resource
Dr. Claw is a full-stack research workspace with a web interface, CLI, built-in Skills, literature feeds, agent backends, experiment workflows, paper-writing tools, and optional autonomous research packs.
This page groups representative academic components by task; review the repository for the complete inventory.
Literature discovery and paper analysis
Provides literature feeds and Skills for finding papers, analysing papers, extracting images, and surveying prior work.
- Typical inputs
- Research topic, source filters, or paper files
- Output
- Paper records, analysis notes, extracted figures, or a literature survey.
Best for: Collecting and examining research sources inside one workspace.
Components for this task
Experiment planning and execution
Contains Skills and optional tool packs for planning, running, monitoring, and analysing computational experiments.
- Typical inputs
- Research goal, codebase, data, compute, and evaluation criteria
- Output
- Experiment plans, code changes, logs, metrics, and analysis artifacts.
Best for: Computational projects that need an integrated research workspace and agent backend.
Components for this task
Suggested workflow requests (2)
Read .claude/skills/inno-experiment-analysis/SKILL.md and follow it to analyse my results.
Create an experiment plan for this project before changing any code.
Adapted into complete requests from official trigger wording in README.md.
Paper and presentation production
Includes Skills for research writing, paper figures, review loops, slides, and posters.
- Typical inputs
- Verified findings, manuscript materials, figures, and target format
- Output
- A component-dependent manuscript draft, figure, slide deck, poster, or review report.
Best for: Preparing research deliverables from checked project artifacts.
Components for this task
Use boundaries
Limits and checks
Broad local access
A task can change project files or execute code.
Use a dedicated workspace, version control, and the narrowest permissions and backend needed.
Provider costs and data handling
Costs, rate limits, retention, and model availability vary.
Check provider terms and avoid confidential data without institutional approval.
Autonomous tool packs
Long runs may consume compute and propagate errors across stages.
Approve stage boundaries and inspect code, logs, results, and claims before continuing.
More boundaries
- Dr. Claw is a full research application, so it is not suitable when you only need one small Skill with no local service or agent backend.
- The application cannot run experiments or access sources without the required code, data, compute, accounts, and permissions.
- Agent-generated experiments, papers, and reviews do not establish novelty, validity, reproducibility, or submission readiness.
Technical details
- Resource type
- Software Tool
- Author or maintainer
- OpenLAIR
- Latest release
- Dr. Claw v1.1.4 (v1.1.4)
- Source last updated
- 13 Jul 2026
- Last verified
- 15 Jul 2026
- Documented applications
- Claude Code, Codex, Gemini CLI, OpenClaw, Dr. Claw desktop and web app, Dr. Claw terminal chat
- Documented AI models
- GPT, Claude, Gemini, DeepSeek, Llama, Mistral, Qwen
- Licence
- See source
- Access
- Publicly available
- Additional costs
- Platform terms or usage limits may apply. API usage fees may apply for selected components. External services, software, compute, or data access may have separate costs.
- Skill instruction language
- English
- Documentation language
- English
- Repository languages
- JavaScript, Markdown, JavaScript or TypeScript
- Dependencies
- Node.js 20 or later; At least one configured agent CLI or OpenRouter API key; Browser for the web interface; Component-specific research code, data, and packages
- Review status
- Not tested
Continue exploring