EverOS Model Card
这是可索引项目报告证据页：它保留 EverOS 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。
EverOS Model Card
| Field | Value |
|---|---|
| Repository | EverMind-AI/EverOS |
| Category | Self-Evolving Agent Memory OS |
| Stars / forks snapshot | 6800 / 669 |
| Language | Python |
| License | Apache-2.0 |
| Raw capture | raw-github/evermind-ai_everos.md |
| Updated by | hourly public metadata update, 2026-06-03 19:56 +0800 |
1. Role in Self Evolve
EverOS 把长期记忆方法、HyperMem 架构、用例集成、EverMemBench 和 EvoAgentBench 放在同一仓库中，直接连接 agent memory、MCP/skills 和 self-evolution evaluation。
2. Working Principle
long-term memory methods -> hypergraph architecture -> use-case integrations -> memory/evolution benchmark suites
3. Evidence Path
web GitHub page observed Apache-2.0 license, Python primary language, benchmarks/methods/use-cases folders, EverMemBench/EvoAgentBench entries, and 6.8k stars with 669 forks, plus visible issue / pull-request surfaces (54 / 50). 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 Memory OS plus self-evolution benchmark suite 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 或 skill install flows；本轮也未拿到可靠的 pushed_at API 字段，所以只刷新了公开页面可见的 star/fork/issues/PR 与 memory-surface 信号。