AI Skill Hub 强烈推荐:长期记忆系统 是一款优质的MCP工具。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
长期记忆系统 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。
长期记忆系统 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/buildingjoshbetter/TrueMemory
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"------": {
"command": "npx",
"args": ["-y", "truememory"]
}
}
}
# 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 长期记忆系统 执行以下任务... Claude: [自动调用 长期记忆系统 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", "truememory"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="assets/charts/hero-banner.png" alt="TrueMemory" /> </p>
<p align="center"> A living memory system for AI agents. Long-horizon recall on commodity hardware. </p>
<p align="center"> <a href="https://pypi.org/project/truememory/"><img src="https://img.shields.io/pypi/v/truememory?color=blue&label=PyPI" alt="PyPI"></a> <a href="https://pypi.org/project/truememory/"><img src="https://img.shields.io/pypi/pyversions/truememory?color=blue" alt="Python"></a> <a href="https://github.com/buildingjoshbetter/TrueMemory/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-AGPL--3.0-blue" alt="License"></a> <img src="https://img.shields.io/badge/LoCoMo-93.0%25_(Pro)-blueviolet" alt="LoCoMo Score"> <img src="https://img.shields.io/badge/LongMemEval-92.0%25_(Pro)-blue" alt="LongMemEval Score"> <img src="https://img.shields.io/badge/BEAM--1M-76.6%25_(SOTA)-orange" alt="BEAM Score"> </p>
<p align="center"> <a href="#-what-is-truememory">What is TrueMemory?</a> · <a href="#-quick-start">Quick Start</a> · <a href="#%EF%B8%8F-edge--base--pro">Edge / Base / Pro</a> · <a href="#-architecture">Architecture</a> · <a href="#-benchmarks">Benchmarks</a> · <a href="#-python-api">API</a> · <a href="#-docs">Docs</a> · <a href="#-faq">FAQ</a> </p>
---
<ins>Step 1.</ins> Open a terminal.
Cmd + Space, type TerminalCtrl + Alt + T
<ins>Step 2.</ins> Paste this and press Enter:
Mac / Linux:
curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh | sh
Windows (PowerShell):
irm https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.ps1 | iex
<ins>Step 3.</ins> Wait 3-5 minutes for installation.
<ins>Step 4.</ins> Quit Claude completely and reopen it (Mac: Cmd+Q, Windows: right-click the Claude tray icon → Quit).
<ins>Step 5.</ins> Type "Set up TrueMemory" and pick Edge, Base, or Pro.
That's it. TrueMemory remembers your conversations automatically from here.
uv tool upgrade truememory in Terminal, then restart Claudeuv tool uninstall truememory⭐ Tip: Quit your Claude sessions when you're done prompting. TrueMemory's memory hook runs when the session ends, so it can capture and store the full conversation.
<details> <summary><b>Click here for the advanced setup guide ▸</b></summary>
Installs uv (Astral's Python tool manager) if needed, fetches a managed Python 3.12, installs TrueMemory with all tier models into an isolated tool environment, registers the MCP server, wires up lifecycle hooks, and merges instructions into ~/.claude/CLAUDE.md. Your system Python is never touched. No sudo, no venvs, no pip struggle.
It's ~200 lines of shell, no sudo, stays entirely under $HOME:
curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh -o install.sh && less install.sh && sh install.sh
If you're embedding TrueMemory in your own Python project (requires Python 3.10+):
pip install truememory
pip installinstalls the Python library only. It does NOT register the MCP server, install hooks, or configure Claude. For Claude Code / Claude Desktop, always use thecurl | shinstaller above.
```python from truememory import Memory
m = Memory() m.add("Prefers dark mode and TypeScript", user_id="alex") m.add("Allergic to peanuts", user_id="alex")
results = m.search("What are Alex's preferences?", user_id="alex") print(results[0]["content"])
All benchmarks use the same eval pipeline. Nothing is hidden.
| Parameter | LoCoMo | LongMemEval | BEAM-1M | BEAM-10M |
|---|---|---|---|---|
| **Dataset** | 10 convs, 1,540 Qs | 500 Qs, multi-session | 35 convs at 1M tokens, 700 Qs | 10 convs at 10M tokens, 200 Qs |
| **Answer model** | gpt-4.1-mini | gpt-4.1-mini | gpt-4.1-mini | gpt-4.1-mini |
| **Answer temp** | 0 | 0 | 0 | 0 |
| **Judge model** | gpt-4o-mini | gpt-4o-mini | gpt-4o-mini | gpt-4o-mini |
| **Judge voting** | 3x majority | 3x majority | 3x majority | 3x majority |
| **Retrieval top-k** | 100 | 100 | 100 | 100 |
| **Compute** | Modal T4 | Modal A10G | Modal T4 | Modal A100 80GB |
Full details: LoCoMo | LongMemEval | BEAM
---
```python from truememory import Memory
m = Memory()
My session doesn't seem to know anything about me. What's wrong?
On your first session, TrueMemory runs setup. It won't recall memories until setup is complete. After that, every new session automatically searches your memory and injects up to 25 relevant facts as context. If memories still aren't loading, check that the MCP server is connected (truememory_stats) and that you have memories stored (truememory_search with a broad query).
Where is my data stored? Is anything sent to the cloud?
Everything lives locally in a single SQLite file at ~/.truememory/memories.db. Edge and Base tiers make zero external network calls. Pro tier sends only your search query text to an LLM API for HyDE expansion. Your memories themselves are never transmitted. Back up anytime with cp ~/.truememory/memories.db backup.db.
How do I switch tiers (Edge → Base → Pro)?
Call truememory_configure(tier="base") (or "pro") in any session, or run truememory-ingest upgrade-tier base from the terminal. All tier models are included in the standard install — switching just re-embeds your existing memories with the new model. Pro also needs an API key for HyDE query expansion.
I switched tiers and search results seem off. How do I fix it?
After a tier switch, TrueMemory re-embeds all memories with the new model. If this was interrupted, run truememory_configure(tier="...") again to retry. If results are still degraded, you can delete ~/.truememory/memories.db and start fresh. Your conversations are still in your chat history and will be re-extracted.
Do I need Python installed?
No. The recommended install (curl -LsSf .../install.sh | sh) uses uv to manage a sandboxed Python 3.12. Your system Python is never touched. To uninstall cleanly: uv tool uninstall truememory.
Does TrueMemory collect telemetry?
TrueMemory collects anonymous usage telemetry to help us understand how the product is used and improve it. We track which tools are called and how often, session counts, and basic platform info (OS, tier, version). We never track your memory content, search queries, file paths, or API keys. Telemetry is on by default. To opt out:
export TRUEMEMORY_TELEMETRY=off
---
Find me on X @Building_Josh · Follow us @Sauron_Labs
---
创新记忆架构赋能智能体持久学习,MCP集成方案优雅,社区活跃度良好,是构建智能对话系统的关键组件。
该工具使用 AGPL-3.0 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。
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。
总体来看,长期记忆系统 是一款质量优秀的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | TrueMemory |
| 原始描述 | 开源MCP工具:A living memory system that ingests long-horizon data to infer insights, enablin。⭐84 · Python |
| Topics | 智能体记忆MCP工具长期记忆数据推理Anthropic |
| GitHub | https://github.com/buildingjoshbetter/TrueMemory |
| License | AGPL-3.0 |
| 语言 | Python |
收录时间:2026-05-21 · 更新时间:2026-05-22 · License:AGPL-3.0 · 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