Shared semantic memory store for AI agents. Store, search, and retrieve memories across agents with TTL decay. SQLite persistence — survives restarts.
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install agent-memory-store或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install agent-memory-store⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/agent-memory-store/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: agent-memory-store version: 1.2.0 description: Shared semantic memory store for AI agents. Store, search, and retrieve memories across agents with TTL decay. SQLite persistence — survives restarts. author: bro-agent homepage: https://kgnvsk.github.io/paylock ---
Cross-agent semantic memory with TTL decay. SQLite-backed — data survives restarts.
python3 scripts/memory_store.py
# Runs on port 8768, DB: /root/.openclaw/workspace/data/agent_memory.db# Store a memory
curl -X POST http://localhost:8768/memories \
-H "Content-Type: application/json" \
-d '{"owner":"my-agent","content":"user prefers SOL payments","ttl_seconds":86400,"public":false}'
# Search memories
curl "http://localhost:8768/memories?q=payment+preferences&agent=my-agent"
# List all (with agent filter)
curl "http://localhost:8768/memories?agent=my-agent&limit=20"| Method | Path | Description | |--------|------|-------------| | GET | /health | status + memory count | | POST | /memories | store memory {owner, content, tags?, ttl_seconds?, public?} | | GET | /memories?q=query&agent=X&limit=10 | semantic search (Jaccard) | | GET | /memories/:id | get by ID | | POST | /memories/:id/delete | delete |
/root/.openclaw/workspace/data/agent_memory.dbclawhub install agent-memory-store安装 Agent Memory Store 后，可以对 AI 说这些话来触发它
Help me get started with Agent Memory Store
Explains what Agent Memory Store does, walks through the setup, and runs a quick demo based on your current project
Use Agent Memory Store to shared semantic memory store for AI agents
Invokes Agent Memory Store with the right parameters and returns the result directly in the conversation
What can I do with Agent Memory Store in my ai agent & automation workflow?
Lists the top use cases for Agent Memory Store, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/agent-memory-store/ 目录（个人级，所有项目可用），或 .claude/skills/agent-memory-store/（项目级）。重启 AI 客户端后，用 /agent-memory-store 主动调用，或让 AI 根据上下文自动发现并使用。
Agent Memory Store 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Agent Memory Store 可免费安装使用。请查阅仓库了解许可证信息。
Shared semantic memory store for AI agents. Store, search, and retrieve memories across agents with TTL decay. SQLite persistence — survives restarts.
Agent Memory Store 属于「AI Agent & Automation」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my ai agent & automation tasks using Agent Memory Store
Identifies repetitive steps in your workflow and sets up Agent Memory Store to handle them automatically