LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
- GitHub 星标
- 497
- 许可证
- Apache-2.0
- 收录日期
- 2026-02-20
GitHub 信息
- GitHub 星标
- 497
- 许可证
- Apache-2.0
- 主要语言
- Go
- 最近推送
- 2026年8月19日 14:43
- 维护者
- mnemon-dev
- 收录日期
- 2026-02-20
README 演示图
从仓库 README 提取的截图/GIF（已过滤徽章、头像等装饰图）。
Knowledge Graph — 87 insights connected by temporal, entity, semantic, and causal edges
https://raw.githubusercontent.com/mnemon-dev/mnemon/master/docs/diagrams/10-knowledge-graph.jpg
LLM-Supervised Architecture — three patterns compared, with Mnemon hooks, protocol boundary, and deterministic memory engine
https://raw.githubusercontent.com/mnemon-dev/mnemon/master/docs/diagrams/llm-supervised-concept.jpg
安装
dsh plugin --profile web add github:mnemon-dev/mnemon标签
README 徽章
将这段 Markdown 添加到插件 README，链接到对应的详情页。
[](https://dshget.com/plugins/mnemon-dev/mnemon)相关插件
开发与运行时memsearch
★ 2531A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
DeepSeek-Reasonix
★ 35252DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
distilly
★ 24153Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.