英格拉姆记忆 是 AI Skill Hub 本期精选MCP工具之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
英格拉姆记忆 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
英格拉姆记忆 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/EngramMemory/engram-memory
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"------": {
"command": "npx",
"args": ["-y", "engram-memory"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 英格拉姆记忆 执行以下任务... Claude: [自动调用 英格拉姆记忆 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"______": {
"command": "npx",
"args": ["-y", "engram-memory"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<img src="assets/logo.svg" alt="Engram Memory" width="360" />
Three-Tiered Brain for AI agents. Self-hosted. Zero API costs.
Docs · Quickstart · Dashboard · Cloud SDKs
</div>
---
Engram gives your AI agent persistent memory across sessions. Store, search, recall, and forget memories using semantic embeddings — all running on your own hardware. No API keys, no cloud dependencies, no data leaving your machine.
One container bundles Qdrant, FastEmbed, and the MCP server. One command to install. Works with Claude Code, Cursor, Windsurf, VS Code, OpenClaw, or anything else that speaks MCP.
---
Python 3.10+ only needed if running the stdio MCP server or CLI tools directly on the host.
---
mkdir -p ~/.claude/commands docker cp engram-memory:/app/commands/. ~/.claude/commands/
**Cursor, Windsurf, VS Code, Claude Desktop, Cline, Zed, and 9 other clients** — one command via [`install-mcp`](https://www.npmjs.com/package/install-mcp):bash npx -y install-mcp@latest http://localhost:8585/mcp \ --client <your-client> --name engrammemory --oauth=no -y
**OpenClaw:**bash git clone https://github.com/EngramMemory/engram-memory.git cd engram-memory && bash scripts/install-plugin.sh
**Manual (any client)** — add to `.mcp.json`:json { "mcpServers": { "engrammemory": { "type": "http", "url": "http://localhost:8585/mcp" } } } ```
The container exposes four transports off the same recall engine:
| Transport | Endpoint | Use case |
|---|---|---|
| Streamable HTTP | http://localhost:8585/mcp | Modern MCP clients |
| SSE | http://localhost:8585/sse | Legacy MCP clients |
| Stdio | docker exec -i engram-memory python /app/mcp_server.py | Process-per-session |
| REST | http://localhost:8585/{store,search,...} | OpenClaw plugin, curl, custom tooling |
Engram is the primary memory layer for any MCP-aware agent — Claude, ChatGPT, Cursor, Perplexity, OpenClaw — and works best when the agent is configured to save every turn, recall before acting, and trust the local + cloud dual-write as the failsafe / hive backbone.
See docs/SOUL-RULES.md for the recommended ruleset. Drop the rules block into your SOUL.md / CLAUDE.md / equivalent and the agent will use Engram the way it was designed:
memory_store for both user input and assistant output on every turn.api.engrammemory.ai when ENGRAM_API_KEY is set. The cloud copy is the failsafe and the hive sync layer; without the key, capture is purely local.memory_store MCP tool is the only channel — there is nothing else to install or run.Engram runs fully local by default. When you need TurboQuant compression, automatic deduplication, overflow storage, or auto-category detection, connect to Engram Cloud:
For MCP users (Claude Code, Cursor, etc.): ```bash
| Variable | Default | Description |
|---|---|---|
QDRANT_URL | http://localhost:6333 | Qdrant vector database |
FASTEMBED_URL | http://localhost:11435 | FastEmbed embedding service |
COLLECTION_NAME | agent-memory | Qdrant collection name |
DATA_DIR | /data/engram | Recall engine state (hot tier, hash index, graph) |
ENGRAM_API_KEY | *(empty)* | Engram Cloud API key (enables cloud extensions) |
ENGRAM_API_URL | https://api.engrammemory.ai | Cloud API endpoint |
memory_answer("What database are we using?")
memory_answer("What did we decide about the auth system last month?") ```
---
docker rm -f engram-memory docker run -d --name engram-memory --restart unless-stopped \ -p 6333:6333 -p 11435:11435 -p 8585:8585 \ -v engram_data:/data \ -e ENGRAM_API_KEY=eng_live_YOUR_KEY \ engrammemory/engram-memory:latest
**For OpenClaw users:**bash openclaw config set "plugins.entries.engram.config.apiKey" "eng_live_YOUR_KEY" openclaw gateway restart ```
Cloud extends your local stack — it does not replace it. Your FastEmbed still generates embeddings locally. Your Qdrant still stores and searches locally. Cloud adds an intelligence layer on top: the API returns compressed vectors, dedup checks, and category detection for every store, and overflow results for every search when local results are insufficient.
Get an API key (free tier, no credit card) at app.engrammemory.ai.
SDKs: - Python: pip install engrammemory-ai — PyPI - Node: npm install engrammemory-ai — npm - Dashboard | Privacy
---
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
经综合评估,英格拉姆记忆 在MCP工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | engram-memory |
| 原始描述 | 开源MCP工具:The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM 。⭐30 · Python |
| Topics | aiai-memorypython |
| GitHub | https://github.com/EngramMemory/engram-memory |
| License | NOASSERTION |
| 语言 | Python |
收录时间:2026-06-01 · 更新时间:2026-06-01 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端