Claude Skill
JasonDocton/lucid-memory
Lucid Memory 是一个本地化、即时、持久的 AI 智能体记忆系统。比 Pinecone 快 13 倍，比 RAG 精简 5 倍，能发现 RAG 遗漏的信息。零云端，零成本。
概览
仓库信息
安装这个 Skill
git clone https://github.com/JasonDocton/lucid-memory.gitRegistry 信息
项目简介
Lucid Memory 是一个本地化、即时且持久的 AI 智能体记忆系统。它比 Pinecone 快 13 倍，比 RAG 精简 5 倍，能发现 RAG 遗漏的信息——完全无需云端，零成本。
Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG. Finds what RAG misses. Zero cloud, zero cost.
要点
- 本地优先：完全在本地运行，无需依赖云端
- 比 Pinecone 向量数据库快 13 倍
- 比传统 RAG 方法精简 5 倍
- 即时且持久的记忆检索
- 能发现 RAG 遗漏的信息
- 零运营成本
使用场景
- 长时间对话的 AI 智能体记忆
- LLM 应用的本地向量搜索
- 离线优先的 AI 工具和助手
- 智能体 AI 工作流的记忆增强
- 云向量数据库的经济高效替代方案
README 摘要
# Lucid Memory **2.7ms retrieval. 743,000 memories/second. $0/query.** Memory for AI that works like yours—local, instant, persistent. ```bash curl -fsSL https://lucidmemory.dev/install | bash ``` <div align="center"> <sub>Works with Claude Code, OpenAI Codex & OpenCode · macOS & Linux · <a href="#windows">Windows instructions</a></sub> <br><br> </div> **New in 0.6.0:** <a href="#memory-consolidation">Memory Consolidation</a> — Lucid Memory is now self-maintaining. Background consolidation strengthens recent memories, decays stale ones, prunes weak associations, and manages visual memory lifecycle. New memories are checked against existing traces — similar content reinforces or updates rather than duplicating. 307 tests, 0 tsc errors. **New in 0.5.0:** <a href="#episodic-memory">Episodic Memory</a> — Claude remembers not just what happened, but how it unfolded — reconstructing the story of your debugging session, not just the fix. "What was I working on before the auth refactor?" now has an answer. --- ## Why Lucid Memory? **We're not a vector database. We're the retrieval layer that makes vector databases obsolete for AI memory.** Pinecone stores vectors. We understand context. <table> <tr> <th></th> <th>Lucid Memory</th> <th>Claude-mem</th> <th>Pinecone RAG</th> <th>Traditional RAG</th> </tr> <tr> <td><b>Retrieval Speed</b></td> <td>✅ <b>2.7ms</b></td> <td>~50ms</td> <td>10-50ms</td> <td>200-800ms</td> </tr> <tr> <td><b>Token Efficiency</b></td> <td>✅ <b>5x</b></td> <td>1x (baseline)</td> <td>2.5x</td> <td>~2x</td> </tr> <tr> <td><b>Recall @ Fixed Budget</b></td> <td>✅ <b>82.5%</b></td> <td>28.9%</td> <td>55.3%</td> <td>~50%</td> </tr> <tr> <td><b>Storage Compression</b></td> <td>✅ <b>5x (80% smaller)</b></td> <td>1x</td> <td>1x</td> <td>1x</td> </tr> <tr>