Archived

This project has been archived by its maintainers, and is no longer receiving any updates.

better-mem0-mcp

Self-hosted MCP Server for AI memory with PostgreSQL (pgvector).

PyPI Docker License: MIT

Thông báo ngừng phát triển

Dự án better-mem0-mcp đã ngừng phát triển kể từ tháng 02/2026.

Giải pháp thay thế đã được tích hợp trực tiếp vào EchoVault — black box cho toàn bộ lịch sử hội thoại AI của bạn. EchoVault không chỉ trích xuất và lưu trữ raw chat data mà còn:

  • Parse và embed nội dung từ 12+ AI coding tools (VS Code Copilot, Cursor, Cline, Claude Code, Gemini CLI, Aider...)
  • Tìm kiếm ngữ nghĩa + từ khóa — hybrid search kết hợp vector similarity (cosine) và FTS5 keyword search qua RRF fusion
  • Giao diện desktop app (Tauri) để quản lý, tìm kiếm trực quan với system tray, auto-sync, auto-update
  • MCP Server tích hợp (echovault-cli mcp) — AI agents truy vấn vault qua tool vault với các action: list, search, read, semantic_search

So với better-mem0-mcp, EchoVault có kiến trúc tốt hơn:

  • Không phụ thuộc dịch vụ bên ngoài — không cần Mem0, LiteLLM, hay PostgreSQL cloud (Neon/Supabase). Mọi thứ chạy local với SQLite + Ollama
  • Nguồn dữ liệu phong phú — tự động trích xuất từ 12+ IDE/CLI tools thay vì phải thêm thủ công
  • Trải nghiệm thống nhất — cùng một vault, dùng được trên cả desktop app, CLI, và MCP server

Chuyển sang EchoVault

  1. Cài đặt: Tải từ GitHub Releases hoặc chạy script: 
    # Windows - Desktop App + CLI
irm https://raw.githubusercontent.com/n24q02m/EchoVault/main/install.ps1 | iex

# Chỉ CLI/MCP (headless)
irm https://raw.githubusercontent.com/n24q02m/EchoVault/main/install-cli.ps1 | iex
  2. Trích xuất và index: echovault-cli extract && echovault-cli parse && echovault-cli embed
  3. Cập nhật MCP config: 
    {
  "mcpServers": {
    "echovault": {
      "command": "echovault-cli",
      "args": ["mcp"]
    }
  }
}

Tài liệu cũ

Features

  • Self-hosted PostgreSQL - Your data stays with you (Neon/Supabase free tier supported)
  • Graph Memory - SQL-based relationship tracking alongside vector memory
  • Multi-provider LLM - Gemini, OpenAI, Anthropic, Groq, DeepSeek, Mistral
  • Fallback chains - Multi-key per provider + multi-model fallback
  • Zero manual setup - Just DATABASE_URL + API_KEYS
Quick Start (Legacy)

1. Get Prerequisites

2. Add to mcp.json

uvx (Recommended)

{
  "mcpServers": {
    "better-mem0": {
      "command": "uvx",
      "args": ["better-mem0-mcp@latest"],
      "env": {
        "DATABASE_URL": "postgresql://user:pass@xxx.neon.tech/neondb?sslmode=require",
        "API_KEYS": "GOOGLE_API_KEY:AIza..."
      }
    }
  }
}

Docker

{
  "mcpServers": {
    "better-mem0": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "DATABASE_URL", "-e", "API_KEYS", "n24q02m/better-mem0-mcp:latest"],
      "env": {
        "DATABASE_URL": "postgresql://...",
        "API_KEYS": "GOOGLE_API_KEY:AIza..."
      }
    }
  }
}

3. Done!

Ask your AI: "Remember that I prefer dark mode and use FastAPI"

Configuration (Legacy)
Variable Required Description
DATABASE_URL Yes PostgreSQL with pgvector extension
API_KEYS Yes ENV_VAR:key pairs, comma-separated
LLM_MODELS No Model fallback chain
EMBEDDER_MODELS No Embedding model chain

Supported LiteLLM Providers

Use environment variable names from LiteLLM docs: GOOGLE_API_KEY, OPENAI_API_KEY, ANTHROPIC_API_KEY, GROQ_API_KEY, etc.

Single provider:

API_KEYS=GOOGLE_API_KEY:AIza...

Multi-key with fallback:

API_KEYS=GOOGLE_API_KEY:AIza-1,GOOGLE_API_KEY:AIza-2,OPENAI_API_KEY:sk-xxx
LLM_MODELS=gemini/gemini-3-flash-preview,openai/gpt-4o-mini
EMBEDDER_MODELS=gemini/gemini-embedding-001,openai/text-embedding-3-small

Defaults

Setting Default
LLM_MODELS gemini/gemini-3-flash-preview
EMBEDDER_MODELS gemini/gemini-embedding-001
Tools (Legacy)
Tool Description
memory Memory operations: add, search, list, delete
help Get full documentation for tools

Usage Examples

{"action": "add", "content": "I prefer TypeScript over JavaScript"}
{"action": "search", "query": "programming preferences"}
{"action": "list"}
{"action": "delete", "memory_id": "abc123"}
Build from Source (Legacy) 
git clone https://github.com/n24q02m/better-mem0-mcp
cd better-mem0-mcp

# Setup (requires mise: https://mise.jdx.dev/)
mise run setup

# Run
uv run better-mem0-mcp

Requirements: Python 3.13+

License

MIT - See LICENSE

Project links

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
  • Archived:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for n24q02m from gravatar.com n24q02m

Credits

Author: n24q02m

License

MIT License (MIT)

Requires

Python ==3.13.*

Tags

ai-agent deprecated llm mcp mem0 memory pgvector

Classifiers

Report project as malware

Metadata

Project links

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
  • Archived:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for n24q02m from gravatar.com n24q02m

Credits

Author: n24q02m

License

MIT License (MIT)

Requires

Python ==3.13.*

Tags

ai-agent deprecated llm mcp mem0 memory pgvector

Classifiers

Report project as malware

Release files for better-mem0-mcp 1.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for better-mem0-mcp 1.3.0
File Size Uploaded
better_mem0_mcp-1.3.0.tar.gz 100.3 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for better-mem0-mcp 1.3.0
File Interpreter ABI Platform
better_mem0_mcp-1.3.0-py3-none-any.whl 12.8 kB Python 3 none any Details

Total release size: 113.1 kB

Release files / better_mem0_mcp-1.3.0.tar.gz

Download URL better_mem0_mcp-1.3.0.tar.gz
Size 100.3 kB
Tags Source
SHA-256 checksum
How to use checksums 		1b2f7f44942fedf5cabc941012e2431ea1117a2675636e69180b4e89531e9b2c
BLAKE2b-256 checksum
How to use checksums 		b723dd3337cc64414bff2b050dd1795b4fcc44b6abdc02a61134b9c60b3f4230
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing? 		No
Uploaded via uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / better_mem0_mcp-1.3.0-py3-none-any.whl

Download URL better_mem0_mcp-1.3.0-py3-none-any.whl
Size 12.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums 		bca841621c67711d84c4b64386b7c4fea35520286a6c01eacb979f6106fe857a
BLAKE2b-256 checksum
How to use checksums 		97b514c13888d38b3e88370a0871ac48825100a72148ce1e1826f8ce1cc7345e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing? 		No
Uploaded via uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page