Supermemory Model Card
这是可索引项目报告证据页：它保留 Supermemory 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。
Supermemory Model Card
| Field | Value |
|---|---|
| Repository | supermemoryai/supermemory |
| Category | Open AI Memory Infrastructure |
| Stars / forks snapshot | 22.7k / 2.1k |
| Language | TypeScript |
| License | MIT |
| Raw capture | raw-github/supermemoryai_supermemory.md |
| Updated by | hourly public metadata update, 2026-05-26 15:57 +0800 |
1. Role in Self Evolve
Supermemory provides a production-oriented memory substrate for agents, converting chat/browser context into indexed and retrievable long-term memory. It matters because self-evolving systems often improve through persistent state quality rather than only prompt mutation.
2. Working Principle
context ingest -> memory indexing and storage -> retrieval/ranking -> personalized context injection -> downstream agent loop reuse
3. Evidence Path
web-observed GitHub page showed 22.7k stars, 2.1k forks, 1,632 commits, MIT license, and README claims for open-source memory infrastructure with benchmark-aware memory workflows and service architecture. 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 teach the memory-substrate perspective: stable self-improvement requires robust write/retrieve/update memory pathways, not only better one-shot reasoning.
5. Limits
The repository was not cloned in this iteration; no memory benchmark rerun, service deployment, or stress test was executed. Counts and claims are visible public-page/search signals unless independently revalidated later.