Hippo Memory Model Card
这是可索引项目报告证据页：它保留 Hippo Memory 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。
Hippo Memory Model Card
| Field | Value |
|---|---|
| Repository | kitfunso/hippo-memory |
| Category | Agent Memory System |
| Stars / forks snapshot | 675 / 34 |
| Language | TypeScript |
| License | MIT |
| Raw capture | raw-github/kitfunso_hippo-memory.md |
| Updated by | hourly public metadata update, 2026-05-25 08:18 +0800 |
1. Role in Self Evolve
Hippo Memory 是偏研究/工程混合的 agent memory 系统，重点在衰减、强化检索、巩固和可审计 benchmark，尤其适合比较 memory 是否带来随任务序列改进。
2. Working Principle
memory event -> decay/retrieval strengthening/consolidation -> LongMemEval and sequential-learning harness -> cross-agent transfer questions
3. Evidence Path
web GitHub page observed 535 commits, MIT license, 675 stars, 34 forks, 105 releases with v1.12.10 latest on 2026-05-24, TypeScript primary language, LongMemEval benchmark details, sequential-learning benchmark, and explicit retraction notes for non-reproduced magnitude claims. 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 Agent Memory System 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。