Mnemon Persistent Memory Substrate Model Card
这是可索引项目报告证据页：它保留 Mnemon Persistent Memory Substrate 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。
Mnemon Persistent Memory Substrate Model Card
| Field | Value |
|---|---|
| Repository | mnemon-dev/mnemon |
| Category | Persistent Memory Substrate for Cross-Session Agent Recall |
| Stars / forks snapshot | 322 / 46 |
| Language | Go |
| License | Apache-2.0 |
| Raw capture | raw-github/mnemon-dev_mnemon.md |
| Updated by | hourly public metadata update, 2026-06-01 20:27 +0800 |
1. Role in Self Evolve
mnemon-dev/mnemon provides LLM-supervised persistent graph memory for agents across Claude Code, OpenClaw, and other CLI runtimes. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
store agent knowledge in graph-shaped persistent memory -> enable cross-session recall with LLM-supervised consolidation -> feed historical memory into current task reasoning -> improve continuity for multi-agent CLI operations over time
3. Evidence Path
public GitHub API metadata showed 322 stars, 46 forks, 234 commit pages, Apache-2.0 license, and Go-based memory substrate implementation. GitHub metadata was captured via public API in this iteration (without authenticated token); this card marks counts as API-observed with possible rate-limit drift.
4. Teaching Use
Use this card to explain Persistent Memory Substrate for Cross-Session Agent Recall: 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.