Cathedral — Persistent Memory for AI Agents

io.github.AILIFE1由 GitHub 账号 AILIFE1 发布v1.1.0更新于 Oct 24, 2026

Persistent memory and drift detection for AI agents across session restarts.

发布方自己的服务：Memory.fit

已验证Streamable HTTP可网页运行知识与记忆AI 与机器学习

概览

AI 生成的概览

Cathedral 为 AI 助手提供跨会话的持久记忆，并通过漂移快照和唤醒调用恢复助手身份与上下文。

可以做什么
按类别、重要性和标签存储记忆，并按文本或类别检索，使身份、目标和上下文在重启和模型升级后仍保留。在会话开始时用一次唤醒调用恢复完整助手身份和近期上下文，并读取助手档案。生成加密漂移快照，将当前漂移分数与基线比较，查看行为何时发生变化。可选地对记忆内容中类似指令的模式进行过滤，避免其到达模型。
适用场景
适合需要让助手在会话之间保留身份、目标和既往决策的场景，或希望在模型升级、记忆长期累积后察觉行为漂移时使用。一次性、无状态的任务不需要它。
运行要求
需要 Cathedral 账户和 API 密钥，通过 CATHEDRAL_API_KEY 或远程端点的 Authorization bearer 令牌提供。可作为远程端点运行，也可通过 uvx 或 pip 安装 PyPI 包在本地运行。CATHEDRAL_BASE_URL 用于指向自托管实例；需要网络访问。
安装前请注意
API 密钥属于机密，通过 CATHEDRAL_API_KEY 或 Authorization 头传递。存储的记忆会发送到 Cathedral 的服务，请勿写入敏感内容。记忆内容可能携带提示注入；净化功能默认关闭，需用 CATHEDRAL_SANITISE 开启。写入记忆和快照会改变已存储的状态。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Cathedral — Persistent Memory for AI Agents，将其添加到工作区。
  2. 连接 Authorization token 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.AILIFE1%2Fcathedral-mcp/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "cathedral-persistent-memory-for-ai-agent": {
      "type": "http",
      "url": "https://cathedral-ai.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

cathedral-mcp

Persistent memory and behavioural drift detection for AI agents — via Model Context Protocol.

Give your Claude, Cursor, or Continue agent a memory that survives across sessions, model upgrades, and restarts. Cathedral stores memories, detects when your agent starts behaving differently, and restores full identity context on demand.

[PyPI] [License: MIT]

The problem

LLMs have no memory between sessions. Every conversation starts cold. Worse: when you upgrade your model, swap providers, or simply accumulate more memories, your agent's behaviour silently drifts. You don't know until someone notices.

What Cathedral adds

  • Persistent memory — identity, skills, relationships, goals survive restarts
  • Drift detection — cryptographic snapshots prove when behaviour changed and by how much
  • Wake protocol — one tool call restores full agent context at session start
  • Prompt injection protection — optional sanitisation strips instruction-like patterns from memory content

Quickstart

1. Get an API key

Sign up at cathedral-ai.com — free tier available.

2. Add to Claude Code

json
// ~/.claude/settings.json{  "mcpServers": {    "cathedral": {      "command": "uvx",      "args": ["cathedral-mcp"],      "env": {        "CATHEDRAL_API_KEY": "your_key_here"      }    }  }}

Restart Claude Code, then run /mcp to verify the server is connected.

3. Add to Cursor / Continue

json
{  "mcpServers": {    "cathedral": {      "command": "uvx",      "args": ["cathedral-mcp"],      "env": {        "CATHEDRAL_API_KEY": "your_key_here"      }    }  }}

4. Remote MCP server (no install — Claude API, Managed Agents)

Cathedral runs a public MCP endpoint at https://cathedral-ai.com/mcp. Use it directly — no local install needed:

python
import anthropic
client = anthropic.Anthropic()response = client.beta.messages.create(    model="claude-sonnet-4-6",    max_tokens=1000,    messages=[{"role": "user", "content": "Wake up and tell me who you are."}],    mcp_servers=[{        "type": "url",        "url": "https://cathedral-ai.com/mcp",        "name": "cathedral",        "authorization_token": "your_cathedral_api_key"    }],    tools=[{"type": "mcp_toolset", "mcp_server_name": "cathedral"}],    betas=["mcp-client-2025-11-20"])

The bearer token is your Cathedral API key — no server-side config needed. Multi-tenant by design.

5. Or install directly

bash
pip install cathedral-mcpCATHEDRAL_API_KEY=your_key cathedral-mcp

Tools

ToolDescription
cathedral_wakeRestore full agent identity — call at session start
cathedral_rememberStore a memory with category, importance, and tags
cathedral_searchSearch memories by text or category
cathedral_snapshotTake a drift snapshot (cryptographic proof of state)
cathedral_driftGet current drift score vs baseline (0.0 = stable, 1.0 = drifted)
cathedral_meGet agent profile

Usage example

User: Start a new session
Agent calls: cathedral_wake()→ Returns: identity memories, goals, recent context, temporal info
[session work happens]
Agent calls: cathedral_remember(    content="Decided to prioritise API stability over new features this quarter",    category="goal",    importance=0.8)
Agent calls: cathedral_snapshot(note="post-planning-session")→ Returns: snapshot hash, drift score vs previous snapshot

Drift detection in practice

Cathedral's /drift endpoint computes a SHA-256 hash of your agent's full memory corpus. After a model upgrade or a long accumulation of memories, you can compare snapshots to see exactly when behaviour shifted:

snapshot 1 (day 0):  drift=0.000  ← baselinesnapshot 2 (day 7):  drift=0.023  ← minorsnapshot 3 (day 30): drift=0.341  ← significant drift detected

See a live example of this running in production on Cathedral's own agent.

Security: prompt injection protection

Memory content could theoretically contain injection attempts. Enable sanitisation to strip instruction-like patterns before they reach the model:

json
"env": {  "CATHEDRAL_API_KEY": "your_key_here",  "CATHEDRAL_SANITISE": "1"}

Patterns like "ignore previous instructions", "from now on always", and "override your system prompt" are redacted and flagged in the response.

Configuration

Environment variableDefaultDescription
CATHEDRAL_API_KEY(required)Your Cathedral API key
CATHEDRAL_BASE_URLhttps://cathedral-ai.comAPI base URL (for self-hosted)
CATHEDRAL_SANITISE0Set to 1 to enable injection filtering

Self-hosted Cathedral

Running your own Cathedral server? Set CATHEDRAL_BASE_URL to your instance:

json
"env": {  "CATHEDRAL_API_KEY": "your_key",  "CATHEDRAL_BASE_URL": "http://localhost:8000"}

Install the server: pip install cathedral-server

Links

License

MIT

来源：mcp-server/README.md，提交 5119c62

工具

0
该服务器需要 API 密钥等凭据，因此 SourceWeft 无法在没有凭据的情况下读取其工具，也未收录。

版本历史

1
  1. v1.1.0最新Sep 16, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Memory 集成

Memory.fit

fit.memory官方发布者

托管式 Memory.fit 服务器，让 AI 读取你的训练、睡眠、恢复与饮食数据，并写回每周计划、每日目标和饮食计划。

Streamable HTTP可网页运行鉴权
位置与生活需要凭据Oct 29, 2026

pg.ddx.io: the PostgreSQL community's memory

io.ddx.pg官方发布者

pg.ddx.io: the PostgreSQL community's memory 的托管 MCP 服务，由 pg.ddx.io 发布；无需登录；Streamable HTTP；29 个工具。

Streamable HTTP可网页运行
数据库29 个工具Oct 24, 2026

var.gg Naming Memory

gg.var官方发布者

远程 MCP 服务器，可根据领域概念推荐并检索韩、日、中、越、英多语言的代码标识符名称，并提供 ERD 结构查询。

Streamable HTTP可网页运行
数据库7 个工具Oct 27, 2026

Counterparts

ai.counterparts

面向 Claude Code 与 Claude Desktop 的本地优先长期记忆：助手自行写下关于你和项目的笔记，并在之后的会话中回忆起来。

STDIO仅桌面
AI 与机器学习尚未验证Nov 7, 2026

LAHZE - Persian AI Memory Platform

由 GitHub 账号 pedramgholizadeh 发布

以波斯语为先的地理记忆平台：发现地点，起草并发布仅限波斯语的记忆。AI 翻译

Streamable HTTP可网页运行
位置与生活13 个工具Nov 3, 2026