面向 LLM Agent 的持久化记忆层:三级热/温/冷存储、融合检索、热度淘汰、配置热加载。作为 DeepSeek Harness 插件分发。| Heat-aware memory layer for LLM agents: three-tier hot/warm/cold storage, fusion retrieval, heat-based eviction, hot-reload config. Ships as a DeepSeek Harness cordis plugin.
- License
- MIT
- Added
- 2026-08-30
GitHub info
- License
- MIT
- Primary language
- JavaScript
- Last push
- Aug 21, 2026, 3:05 PM
- Maintainer
- necigit
- Added
- 2026-08-30
Preview from README
Screenshots and GIFs extracted from the repository README (badges and avatars filtered out).
Install
Installation unavailable
This entry is not currently marked as installable.
Tags
README badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/necigit/Coral-Memory)Related plugins
Development & RuntimeEverOS
★ 12559One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
MemOS
★ 11085Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
ReMe
★ 3369ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.