OpenSpace Model Card
这是可索引项目报告证据页：它保留 OpenSpace 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。
OpenSpace Model Card
| Field | Value |
|---|---|
| Repository | HKUDS/OpenSpace |
| Category | Self-Evolving Skill Runtime |
| Stars / forks snapshot | 6300 / 780 |
| Language | Python |
| License | MIT |
| Raw capture | raw-github/hkuds_openspace.md |
| Updated by | hourly public metadata update, 2026-05-25 08:18 +0800 |
1. Role in Self Evolve
OpenSpace 把 skills 当作会选择、执行、监控、分析并演化的运行时实体，提供 OpenClaw、nanobot、Claude Code、Codex、Cursor 等 agent 的自进化技能层。
2. Working Principle
task execution -> skill selection/application -> quality monitoring -> auto-fix/auto-improve/auto-learn -> shared skill community
3. Evidence Path
web GitHub page observed 76 commits, MIT license, 6.3k stars, 780 forks, Python/TypeScript stack, no releases, GDPVal benchmark directory, 60+ evolved skills showcase, and README self-evolution engine language. Shell GitHub API access remained blocked by DNS in this run, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Self-Evolving Skill 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、skill install flows、memory experiments、MCP servers、agent evolution loops、security scanners 或 production deployments；star/fork/commit/release 快照来自公开 GitHub 页面文本或可见页面片段。