Persistent Agent Memory Substrate Model Card

这是可索引项目报告证据页：它保留 Persistent Agent 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。

Persistent Agent Memory Substrate Model Card

1. Role in Self Evolve

memweave is a zero-infrastructure async Python memory library for AI agents using markdown files and SQLite-backed searchable persistence. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.

2. Working Principle

agent writes memory markdown -> sqlite vector+fts index build -> hybrid retrieval and reranking -> persistent memory feedback for next agent turns

3. Evidence Path

web-observed GitHub page showed 39 stars, 2 forks, 57 commits, MIT license, plain-Markdown source-of-truth memory, SQLite indexing, OpenClaw inspiration, and release notes referencing LongMemEval-S benchmark work. This iteration keeps freshness honest: the snapshot comes from the current public GitHub page, while shell GitHub API access remained blocked in this workspace.

4. Teaching Use

Use this card to explain Persistent Agent Memory Substrate: it shows how harness/runtime/benchmark or memory/skill 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 signals unless independently revalidated later.