v

vasperamemory

@RCOLKITT/vasperamemory
Hosted
0 Stars 1 次浏览 RCOLKITT 更新于 2026-08-23

Persistent AI memory for coding assistants. 80+ tools for decisions, patterns, errors.

MCP 服务配置

复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用

{
  "mcpServers": {
    "vasperamemory": {
      "args": [
        "vasperamemory@1.40.0"
      ],
      "command": "npx"
    }
  }
}

可用工具 （5 个）

该服务在 MCP 协议中暴露的工具，AI 可按需调用

tavily_search 14 个参数 需填 1 项

Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.

必填参数：query

tavily_extract 6 个参数 需填 1 项

Extract content from URLs. Returns raw page content in markdown or text format.

必填参数：urls

tavily_crawl 11 个参数 需填 1 项

Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.

必填参数：url

tavily_map 8 个参数 需填 1 项

Map a website's structure. Returns a list of URLs found starting from the base URL.

必填参数：url

tavily_research 2 个参数 需填 1 项

Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings.

必填参数：input

服务介绍

VasperaMemory

Stop AI Context Amnesia. Your AI forgets everything between sessions. VasperaMemory remembers.

npm version
Downloads

MCP 2025

# The Problem

Every time you start a new AI coding session:

  • Your AI forgets all architectural decisions you made yesterday
  • You repeat the same explanations over and over
  • Context from Cursor doesn't carry to Claude Code (or vice versa)
  • Team knowledge walks out the door when developers leave

# The Solution

npx vasperamemory@latest connect

One command. Your AI now remembers everything across Claude Code, Cursor, Windsurf, and VS Code.

# Quick Start (3 minutes)

# # 1. Install

npx vasperamemory@latest connect

# # 2. Verify

vasperamemory status

# # 3. Use

Ask your AI: "What decisions have been made in this project?"

That's it. Your AI now has persistent memory.

# # Local-Only Mode (Privacy-First)

npx vasperamemory@latest connect - -local

All data stays on your machine. No cloud, no API keys.

# Why VasperaMemory?

| Without Memory | With VasperaMemory |
|- -- -- -- -- -- -- --|- -- -- -- -- -- -- -- -- --|
| Context lost after restart | 95%+ context recall |
| Repeat explanations daily | Never repeat yourself |
| Each tool is isolated | Cross-tool sync |
| Team knowledge fragmented | Shared knowledge base |

# Key Features

Cross-Tool Memory - Context syncs across Claude Code, Cursor, Windsurf, VS Code, JetBrains

82 MCP Tools - Comprehensive toolset: memory, decisions, errors, help_me, and more

Pattern Learning - AI learns your coding conventions and suggests them automatically

Team Collaboration - Shared memory for entire development teams

Local-Only Mode - Complete privacy with SQLite storage

MCP 2025 Compliant - Task-based workflows with progress tracking

# How It Works

You Code → Decisions Captured → AI Remembers → Better Suggestions
    ↓              ↓                 ↓               ↓
 Cursor      VasperaMemory      Next Session    Context-Aware
 Claude      (Vector Store)     Any Tool        Responses

# Troubleshooting

# # "MCP connection failed"

vasperamemory status  #  Check connection
vasperamemory connect - -force  #  Reconnect

Then restart your AI tool.

# # "No memories found"

Capture your first memory:

vasperamemory capture "Project uses TypeScript with strict mode"

# # "Command not found"

Ensure Node.js 18+ is installed:

node - -version  #  Should be 18+
npx vasperamemory@latest - -help

# Documentation

# Developer Setup

git clone https://github.com/RCOLKITT/VasperaMemory.git
cd VasperaMemory

#  Install Doppler CLI for secrets (macOS)
brew install dopplerhq/cli/doppler

#  Setup
npm install - -legacy-peer-deps
npm run dev     #  Start dashboard
npm run server  #  Start MCP server (separate terminal)

# Support

# License

MIT License - see LICENSE

Built by developers who were tired of re-explaining context to AI.

查看源码 项目主页