ClawMem On-Device Memory Layer Model Card
这是可索引项目报告证据页：它保留 ClawMem On-Device Memory Layer 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。
ClawMem On-Device Memory Layer Model Card
| Field | Value |
|---|---|
| Repository | yoloshii/ClawMem |
| Category | On-Device Memory Layer and Retrieval Runtime for Agents |
| Stars / forks snapshot | 179 / 26 |
| Language | TypeScript |
| License | MIT |
| Raw capture | raw-github/yoloshii_clawmem.md |
| Updated by | hourly public metadata update, 2026-06-01 13:52 +0800 |
1. Role in Self Evolve
yoloshii/ClawMem provides an on-device memory layer for Claude Code, Hermes, and OpenClaw agents with hybrid retrieval and hooks. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
index local documents and session artifacts into a persistent memory substrate -> combine hybrid retrieval, hooks, and MCP tooling to surface relevant context automatically -> preserve decisions and handoffs across sessions and agents -> enable compounding memory quality through repeated retrieval and feedback loops
3. Evidence Path
web-observed GitHub page showed 179 stars, 26 forks, 252 commits, MIT license, and TypeScript-dominant implementation. 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 On-Device Memory Layer and Retrieval Runtime for Agents: 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.