What this resource does
Core uses
About this resource
Scientify is an OpenClaw extension that continuously collects papers, maintains research knowledge, develops hypotheses, coordinates implementation and experiments, and produces research surveys or paper drafts.
This page groups representative academic components by task; review the repository for the complete inventory.
Continuous literature collection
Tracks papers, downloads accessible sources, reads large papers in parts, and maintains evolving research notes.
- Typical inputs
- Research direction and tracking criteria; Available paper sources and download permissions
- Output
- Paper metadata, downloaded sources, reading notes, and an updated research knowledge base.
Best for: Keeping a long-running AI research topic connected to new literature.
Extension components for this task
research-collect
Collects papers and source material for the configured research direction.
Suggested workflow requests (2)
Run a research survey for the papers already collected in this project.
List the papers downloaded for this research direction and show their metadata.
Adapted into complete requests from official trigger wording in README.en.md.
Hypothesis and experiment pipeline
Develops hypotheses, creates plans, implements code, runs experiments, and reviews artifacts across multiple agent roles.
- Typical inputs
- Research goal, project repository, data, compute, and evaluation rules
- Output
- Hypothesis records, plans, code, experiment artifacts, and review findings.
Best for: Computational research projects with clear success criteria and active human oversight.
Extension components for this task
Research writing
Drafts a result-driven research paper or review paper from the project's research and experiment artifacts.
- Typical inputs
- Verified project notes, sources, figures, and experiment results
- Output
- A research-paper or review-paper draft.
Best for: Preparing a draft after the source and experiment artifacts have been checked.
Extension components for this task
Use boundaries
Limits and checks
Continuous operation
The extension may consume model, network, storage, and compute resources over time.
Set schedules and budgets explicitly and inspect research state regularly.
Host code execution
Research code can change files or consume local compute outside an isolated GPU sandbox.
Use an isolated project environment and review commands, data paths, and permissions.
Paper access and messaging
Access rules, data handling, and account costs depend on those services.
Use authorised sources and review integration permissions and provider terms.
More boundaries
- Do not enable continuous research without a defined topic, compute limits, source policy, and a way to inspect its stored state.
- The extension cannot access closed papers or external services unless the configured environment has authorised access.
- Autonomous hypotheses and experimental results do not become valid research conclusions without independent replication and review.
Technical details
- Resource type
- Extension
- Author or maintainer
- tsingyuai
- Latest release
- v3.4.0
- Source last updated
- 30 Apr 2026
- Last verified
- 15 Jul 2026
- Documented applications
- OpenClaw
- 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
- TypeScript, Markdown, JavaScript or TypeScript
- Dependencies
- OpenClaw; Node.js and pnpm for source development; Configured model provider; Research-specific code, data, and compute
- Review status
- Not tested
Continue exploring