AI Vector Memory
aivectormemory 是一款基于 Model Context Protocol (MCP) 开发的OpenClaw、OpenCode、ClaudeCodeAI记忆管理工具。它专门为 Claude、OpenCode、Cursor 和 主流IDE 编程工具设计，通过向量数据库技术解决 AI 在不同对话会话中「健忘」的问题。aivectormemory: A lightweight MCP Server enabling persistent, cross-session memory for
What is AI Vector Memory?
AI Vector Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to aivectormemory 是一款基于 model context protocol (mcp) 开发的openclaw、opencode、claudecodeai记忆管理工具。它专门为 claude、opencode、cursor 和 主流ide 编程工具设计，通过向量数据库技术解决 ai 在不同对话会话中「健忘」的问题。aivectormemory: a lightweight mcp se...
aivectormemory 是一款基于 Model Context Protocol (MCP) 开发的OpenClaw、OpenCode、ClaudeCodeAI记忆管理工具。它专门为 Claude、OpenCode、Cursor 和 主流IDE 编程工具设计，通过向量数据库技术解决 AI 在不同对话会话中「健忘」的问题。aivectormemory: A lightweight MCP Server enabling persistent, cross-session memory for
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- aivectormemory 是一款基于 Model Context Protocol (MCP) 开发的OpenCla
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx aivectormemoryConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AI Vector Memory
AIVectorMemory is a local-first MCP server that gives AI coding assistants persistent, cross-session memory using hybrid vector and full-text search. It stores code context, project preferences, task states, and developer notes in a local database — no cloud dependency, no API key — and retrieves semantically relevant memories on demand to reduce wasted tokens on re-explanation. It supports 11 IDEs including Claude Code, Cursor, Kiro, OpenCode, and VS Code.
Prerequisites
- Python 3.10 or later installed (for pip/uvx installation)
- pip or uv package manager available
- An MCP-compatible client such as Claude Desktop, Cursor, or Claude Code
- Optional: set HF_ENDPOINT env var if HuggingFace model downloads are slow in your region
Install aivectormemory
Install the package via pip. On first run it will download the ONNX embedding model locally — no API key required.
pip install aivectormemoryInitialize memory storage for your project
Run the install command from your project directory to create the local memory database.
cd /path/to/your/project
aivectormemory installConfigure your MCP client
Add aivectormemory to your client's MCP server configuration. For users in regions with slow HuggingFace access, set the HF_ENDPOINT env var.
Launch the web dashboard (optional)
Start the local web dashboard on port 9080 to browse and manage stored memories visually.
aivectormemory web --port 9080
# or run in background:
aivectormemory web --port 9080 --quiet --daemonStart using memory tools in your AI client
The server exposes 9 MCP tools (remember, recall, forget, status, track, task, readme, auto_save, graph). Ask your AI assistant to store or recall information using natural language.
AI Vector Memory Examples
Client configuration
Add aivectormemory as an MCP server in Claude Desktop. Set HF_ENDPOINT only if model downloads are slow.
{
"mcpServers": {
"aivectormemory": {
"command": "uvx",
"args": ["aivectormemory"],
"env": {
"HF_ENDPOINT": "https://hf-mirror.com"
}
}
}
}Prompts to try
Example prompts demonstrating the 9 memory tools in a real coding session.
- "Remember that this project uses PostgreSQL 15 with the pgvector extension enabled"
- "Recall what we decided about the authentication strategy last week"
- "Track a new issue: the login endpoint returns 500 when the email contains a plus sign"
- "Store my preference: always use async/await instead of promise chains"
- "Forget memory ID abc123 — that approach is no longer valid"Troubleshooting AI Vector Memory
Embedding model download is very slow or times out
Set the HF_ENDPOINT environment variable to a mirror: export HF_ENDPOINT=https://hf-mirror.com. You can also add this to the env block in your MCP client config.
Memories from a previous project are appearing in the wrong project context
AIVectorMemory stores databases per project directory. Make sure the MCP server is launched from the correct project root, and run 'aivectormemory install' in each project separately.
The 'recall' tool returns no results for something you stored
The hybrid search uses both vector similarity and full-text search. Try rephrasing your query with different keywords. Check the web dashboard (port 9080) to confirm the memory was saved successfully.
Frequently Asked Questions about AI Vector Memory
What is AI Vector Memory?
AI Vector Memory is a Model Context Protocol (MCP) server that aivectormemory 是一款基于 model context protocol (mcp) 开发的openclaw、opencode、claudecodeai记忆管理工具。它专门为 claude、opencode、cursor 和 主流ide 编程工具设计，通过向量数据库技术解决 ai 在不同对话会话中「健忘」的问题。aivectormemory: a lightweight mcp server enabling persistent, cross-session memory for It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AI Vector Memory?
Follow the installation instructions on the AI Vector Memory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AI Vector Memory?
AI Vector Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AI Vector Memory free to use?
Yes, AI Vector Memory is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
AI Vector Memory Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to AI Vector Memory? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AI Vector Memory in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use AI Vector Memory?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.