Memoir Model Card
这是可索引项目报告证据页：它保留 Memoir 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。
Memoir Model Card
| Field | Value |
|---|---|
| Repository | zhangfengcdt/memoir |
| Category | Git-like Agent Auto-Memory |
| Stars / forks snapshot | 549 / 35 |
| Language | Python |
| License | Apache-2.0 |
| Raw capture | raw-github/zhangfengcdt_memoir.md |
| Updated by | hourly public metadata update, 2026-05-25 16:48 +0800 |
1. Role in Self Evolve
Memoir frames agent memory as declarative, hierarchical and Git-like, making memory state inspectable through commits and branches instead of only vector retrieval.
2. Working Principle
agent activity -> hierarchical memory paths -> Git-like commits/branches -> recoverable continuity
3. Evidence Path
web-observed GitHub page showed 155 commits, Apache-2.0 license, 549 stars, 35 forks, Python/Shell/TypeScript stack, v0.2.0 release on 2026-05-11, Codex/Claude plugin install paths, and README language about Git-like branching/commit/merge/rollback for AI memory; no benchmark was rerun. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Git-like Agent Auto-Memory in the raw -> classification -> project card -> site/report pipeline. It helps distinguish taxonomy evidence, memory substrate evidence and continuity benchmark evidence.
5. Limits
The repository was not cloned in this iteration; no benchmark, SDK example, memory experiment, eval run, skill install flow, agent loop, or production deployment was executed. Counts and claims are visible public-page/search signals unless independently revalidated later.