EdgeClaw Model Card
这是可索引项目报告证据页：它保留 EdgeClaw 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。
EdgeClaw Model Card
| Field | Value |
|---|---|
| Repository | OpenBMB/EdgeClaw |
| Category | Edge-Cloud Personal Agent Runtime |
| Stars / forks snapshot | 1200 / 70 |
| Language | TypeScript |
| License | MIT |
| Raw capture | raw-github/openbmb_edgeclaw.md |
| Updated by | hourly public metadata update, 2026-05-24 |
1. Role in Self Evolve
EdgeClaw 是 OpenBMB 等机构基于 OpenClaw 的边云协同个人 AI Assistant，把 cost-aware routing、multi-layer memory、skill discovery、tool governance 和 sandbox 组织成个人 Agent runtime。
2. Working Principle
edge runtime -> cloud collaboration -> cost router -> memory engine -> skill/tool governance -> self-driven agent loop
3. Evidence Path
web GitHub page observed MIT license, OpenClaw-based edge-cloud collaborative agent, ClawXMemory/ClawXSkill/ClawXTool/ClawXKairos signals, 1.2k stars and 70 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 Edge-Cloud Personal Agent Runtime 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。