kenn-io/msgvault

Archive a lifetime of email and chat. Offline search, analytics, and AI query over your full message history. Powered by SQLite and DuckDB

What it solves

msgvault provides a local-first, unified archive for your personal and professional communications. It solves the problem of fragmented history across multiple platforms (email, chat, calendars, and contacts) by consolidating them into a single, searchable, and self-hosted repository that you own.

How it works

It acts as a local daemon that syncs data from various sources into a database on your own hardware. Once archived, you can interact with your data via a web UI, a terminal-based interface (TUI), a CLI, or an HTTP API. It supports semantic search and document extraction, allowing you to find information by meaning rather than just keywords. It also includes an MCP (Model Context Protocol) server, which enables AI assistants to query your archive securely.

Who it’s for

It is for individuals who want to take ownership of their digital history, researchers or professionals who need to manage large volumes of cross-platform communication, and power users who want to integrate their personal data with AI agents.

Highlights

  • Local-first architecture ensures your data stays on your own hardware.
  • Supports semantic search, document text extraction, and image search via configurable providers.
  • Includes an MCP server to connect AI assistants to your personal archive.
  • Provides multiple interfaces including a Web UI, TUI, CLI, and SQL querying.
  • Features tools for deduplication, backup, and managing contact relationships.

Related

  • Project
    bitbonsai/mcpvault

    MCPVault is a local MCP server that lets AI assistants read, search, and edit notes in an Obsidian vault. It provides 18 tools for file operations, search, and metadata management, with strong safety features and no need for an Obsidian plugin.

  • Project
    webcoyote/sandvault

    SandVault is a macOS utility that runs AI agents and shell commands in a restricted, sandboxed user account to provide security without the overhead of virtual machines.

  • Project
    Infisical/agent-vault

    Agent Vault is an open‑source HTTP proxy that stores secrets and injects them into outbound requests for AI agents, preventing the agents from ever seeing real credentials. It offers a management UI, CLI, per‑agent tokens, pluggable secret back‑ends (including Infisical), egress filtering, request logging, and optional PostgreSQL scaling. Deployable as a single binary or Docker image, it integrates via standard `HTTPS_PROXY` environment variables and is aimed at securing remote‑coding, all‑purpose, custom, and sandboxed AI agents.

  • Project
    Waishnav/devspace

    DevSpace is a self-hosted MCP server that securely connects ChatGPT to your local machine, letting it read, edit, search, and run code in your own projects. You run it locally, expose it through a tunnel you control, and approve connections with a password. It supports Linux, macOS, and Windows (with Bash-compatible shells), requires Node >=22.19 <27, and is installed via npm.

  • Project
    silverstein/minutes

    minutes is an open‑source desktop/CLI app that records, locally transcribes, and stores meetings as Markdown files with rich metadata. It exposes a simple MCP API (`search_meetings`) so any LLM agent (Claude Code, Cursor, Codex, etc.) can retrieve relevant excerpts, enabling privacy‑first, agent‑first workflows.