Bluecolumn Memory

io.github.bluecolumnconsulting-lgtm由 GitHub 账号 bluecolumnconsulting-lgtm 发布v1.4.0更新于 Oct 26, 2026

Persistent memory for AI agents — audio intelligence + Music Memory ingestion and recall

发布方自己的服务:Memory.fit

已验证STDIO仅桌面知识与记忆媒体与设计

概览

AI 生成的概览

BlueColumn Memory 为 MCP 智能体提供跨会话的持久语义记忆,并支持音频、通话与音乐内容的写入与检索。

可以做什么
  • 以自然语言查询持久记忆中的文本、文档与观察记录,返回综合答案与来源
  • 写入通话、语音备忘、会议、播客与音乐等音频,并按音频来源检索引用
  • 按乐器、调性、速度、技巧与风格标签记录和查询音乐练习内容
  • 在语音通话前准备记忆上下文,通话结束后记录变化
  • 分析非语音声音事件,并从音乐中提取速度、结构、配器与情绪
  • 写入并检索来自汽车、门铃、穿戴设备等边缘设备的流式音频片段
适用场景
适合希望助手在不同对话之间记住项目背景、决策或笔记,又不想自行维护数据库的场景;也适合把语音备忘、通话录音或音乐练习变成可检索记忆的用途。
运行要求
以 npm 包 bluecolumn-mcp 通过 stdio 在本地运行,通常在桌面 MCP 客户端中配置。需要 BLUECOLUMN_API_KEY 中的 BlueColumn API 密钥,提供免费额度。BLUECOLUMN_API_URL 可选,用于指定 API 地址,默认指向本地 localhost:8000 后端。需要能访问 BlueColumn 服务的网络。
安装前请注意
BLUECOLUMN_API_KEY 是凭据,不应写入共享配置文件。存入的内容(包括音频与转写文本)会发送到第三方云服务进行转写与向量化。记忆写入会跨会话保留,并按命名空间隔离,存放敏感内容前请确认当前命名空间。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Bluecolumn Memory,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

🧠 BlueColumn MCP Server

Give Claude Desktop, Cursor, and any MCP-compatible agent persistent memory across sessions.

[npm version] [License] [BlueColumn]

2-minute setup. Zero-config. Audio-native. Works with every MCP client.


MCP server for BlueColumn — persistent semantic memory for AI agents.

Give any MCP-compatible agent (Claude Desktop, Cursor, Windsurf, LangChain, AutoGen, CrewAI) the ability to remember, recall, and store observations across sessions.

Tools

Core memory

ToolDescription
rememberIngest text, audio, or documents into persistent memory
recallQuery memory with natural language, get AI-synthesized answer + sources
noteStore lightweight agent observations as searchable vectors
namespaceShow the configured namespace

Music Memory (new)

ToolDescription
music_rememberStore a musical recording, practice session, or lesson with rich musical context — instrument, key, tempo, technique tags, chord progression, notes. Audio is transcribed; the structured context is embedded alongside so a coach/teacher agent recalls it with full musical understanding
music_recallSearch stored musical content with musical filters — instrument, technique, or style. E.g. "show me every take with barre chord issues" or "what did we practice in E minor last month"

Audio Intelligence

ToolDescription
audio_ingestIngest calls, voice notes, podcasts, meetings, or music and extract semantic memory
audio_recallSearch audio memories and get audio-backed citations
call_prepareGet memory context before a voice call starts
call_completeStore what changed after a call ends
sound_analyzeDetect and index non-speech audio events
music_analyzeExtract tempo, structure, instrumentation, mood from music

Streaming audio memory

ToolDescription
streaming_audio_ingestIngest edge-device audio chunks (car, doorbell, wearable) into per-device streaming memory
streaming_audio_recallRecall over a device's streamed audio history

Music Memory example

Store a practice session:

music_remember {  "audio_url": "https://example.com/take3.mp3",  "title": "Week 3 practice — barre chords, Sep 7",  "instrument": "guitar",  "musical_key": "E minor",  "tempo_bpm": 92,  "technique_tags": ["barre-chords", "hammer-on"],  "style_tags": ["blues"],  "chord_progression": ["Em", "Am", "B7"],  "notes": "F-shape barre still buzzy on the B string; Fmaj7 subst worked well"}

Then recall it musically:

music_recall { "q": "which takes had barre chord issues?", "instrument": "guitar" }

Setup

1. Get your BlueColumn API key

Sign up free at bluecolumn.ai — 60 min audio + 100 queries/month, no credit card required.

2. Install

bash
npm install -g bluecolumn-mcp

3. Configure Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

json
{  "mcpServers": {    "bluecolumn": {      "command": "bluecolumn-mcp",      "env": {        "BLUECOLUMN_API_KEY": "bc_live_YOUR_KEY"      }    }  }}

4. Restart Claude

Done. Claude now remembers everything you tell it to.

What Makes BlueColumn Different

FeatureBlueColumn MCPOther MCP Memory Servers
Audio ingestion✅ Native (transcribe + store)❌ Text only
Plain English recall✅ "What did we decide about pricing?"❌ Keyword/vector only
Setup time~2 minutes~10-30 minutes
Cloud managed✅ No infra to run⚠️ Most require local DB
Namespace isolation✅ Built-in per key⚠️ Manual

Examples

Store project context

Remember: We're building a React component library called Aether with Tailwind CSS v4.

Recall across sessions (new conversation)

What project was I working on? What was my tech stack?

→ Claude recalls: "You're building Aether, a React component library with Tailwind CSS v4"

Store audio notes

Record a voice memo → BlueColumn transcribes it → Claude remembers it.

Advanced

Custom namespace

json
{  "mcpServers": {    "bluecolumn": {      "command": "bluecolumn-mcp",      "env": {        "BLUECOLUMN_API_KEY": "bc_live_YOUR_KEY",        "BLUECOLUMN_NAMESPACE": "my_project"      }    }  }}

Multiple environments

Use different namespaces for work, personal, and side projects. Each stays isolated.


Sign up free → · Docs · GitHub Issues

来源:README.md,提交 871a2bc

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.4.0最新Sep 16, 2026

评分

已满足适用检查项的 40%

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25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 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

    请在仓库或注册中心条目中声明许可证。

其他 Memory 集成