Memori Model Card
这是可索引项目报告证据页：它保留 Memori 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。
Memori Model Card
| Field | Value |
|---|---|
| Repository | MemoriLabs/Memori |
| Category | Agent-Native Memory Infrastructure |
| Stars / forks snapshot | 14,900 / 2300 |
| Language | Python/TypeScript |
| License | Apache-2.0 |
| Raw capture | raw-github/memorilabs_memori.md |
| Updated by | hourly public metadata update, 2026-05-24 |
1. Role in Self Evolve
Memori 是 agent-native memory infrastructure，把 agent execution 和 conversation 转成结构化持久状态，并用 LoCoMo benchmark 报告记忆质量和上下文成本表现。
2. Working Principle
agent execution/conversation -> structured memory capture -> background augmentation -> recall on demand -> benchmarked context reduction
3. Evidence Path
web GitHub page observed 600 commits, Apache 2.0 license, Python/TypeScript/Rust stack, LoCoMo 81.95% accuracy claim, Version 3.3.4 latest May 20 2026, 14.9k stars and 2.3k 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 Agent-Native Memory Infrastructure 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。