mem9 Model Card
这是可索引项目报告证据页：它保留 mem9 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。
mem9 Model Card
| Field | Value |
|---|---|
| Repository | mem9-ai/mem9 |
| Category | Persistent Memory Layer for Multi-Agent Runtimes |
| Stars / forks snapshot | 1100 / 111 |
| Language | Go |
| License | Apache-2.0 |
| Raw capture | raw-github/mem9-ai_mem9.md |
| Updated by | hourly public metadata update, 2026-05-27 09:59 +0800 |
1. Role in Self Evolve
mem9 provides a persistent memory server and plugin integrations so multiple agent runtimes can share durable context instead of isolated session notes. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
memory write/search/get/update/delete API -> runtime plugins and skills -> cross-session recall -> shared multi-agent memory reuse
3. Evidence Path
web-observed GitHub page showed 1.1k stars, 111 forks, 433 commits, Apache-2.0 license, and README claims for OpenClaw/Hermes/Claude Code/OpenCode/Codex/Dify integrations with shared API-driven memory. 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 Persistent Memory Layer for Multi-Agent Runtimes: 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.