ScienceClaw Model Card
这是可索引项目报告证据页：它保留 ScienceClaw Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
ScienceClaw Model Card
| Field | Value |
|---|---|
| Repository | beita6969/ScienceClaw |
| Category | Self-Evolving Research Agent |
| Stars / forks snapshot | 816 / 90 |
| Language | TypeScript |
| License | MIT |
| Raw capture | raw-github/beita6969_scienceclaw.md |
| Updated by | hourly public metadata update, 2026-05-24 |
1. Role in Self Evolve
ScienceClaw 是面向科学家的 self-evolving research agent，把 OpenClaw、长期记忆、285 个研究技能、领域适配和零幻觉引用约束组织成科研工作台。
2. Working Principle
research query -> field-specific skills -> persistent memory -> citation-checked analysis -> post-task reflection and skill evolution
3. Evidence Path
web GitHub page observed 25 commits, MIT license, TypeScript primary language, 285 skills, four-layer memory/research protocol, self-evolving topic, 816 stars and 90 forks. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Self-Evolving Research Agent in the raw -> classification -> project card -> site/report pipeline. The reading path is: raw capture -> classification row -> public site card -> project report -> aggregate GitHub analysis.
5. Limits
当前未克隆源码，未运行 benchmark、SDK examples、skill install flows、memory experiments 或 production deployments；star/fork/commit 快照来自公开 GitHub 页面文本或可见页面片段。