Nemori Model Card
这是可索引项目报告证据页：它保留 Nemori 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。
Nemori Model Card
| Field | Value |
|---|---|
| Repository | nemori-ai/nemori |
| Category | Episodic Agent Memory Substrate and Knowledge Store |
| Stars / forks snapshot | 202 / 17 |
| Language | TypeScript |
| License | MIT |
| Raw capture | raw-github/nemori-ai_nemori.md |
| Updated by | hourly public metadata update, 2026-05-28 22:03 +0800 |
1. Role in Self Evolve
Nemori is an episodic memory and persistent context engine for autonomous agents that need durable recall across sessions. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
episodic interaction capture -> memory graph indexing and retrieval -> semantic recall for future agent plans -> persistent memory feedback into subsequent actions
3. Evidence Path
web-observed GitHub page showed 202 stars, 17 forks, 79 commits, MIT license, and project framing around episodic memory for autonomous agents. 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 Episodic Agent Memory Substrate and Knowledge Store: it shows how harness/runtime/benchmark layers convert agent behavior into reproducible and auditable engineering workflows.
5. Limits
The repository was not cloned in this iteration; no benchmark run, plugin install, workflow execution, or agent loop experiment was executed. Counts and claims are visible public-page/search signals unless independently revalidated later.