Mob – A personal CRM as an MCP server

7 hours ago

MobCRM allows users to interact with their CRM via an AI assistant over MCP or manually through a web app, with seamless switching between modes.
The beta version is free, offering all features and no caps on contacts.
MobCRM supports the Model Context Protocol (MCP) and Streamable HTTP for connectivity.
Users can browse, edit, search, and import data, with access from both AI and web interfaces.
Alerts for birthdays and follow-ups are sent to phone and desktop in advance, even when the app is closed.
The CRM includes relationship management, food preferences, addresses, custom fields, tags, and timeline tracking.
Supports one-off or recurring reminders tied to specific people, along with wishlists and IOUs in any currency.
Quick search allows finding contacts, notes, or reminders with a single keystroke.
Data can be imported from Monica, vCard, and Google Contacts, and is always portable.
After beta, managed hosting will be a small subscription, while self-hosting remains free and unlimited.

Echoed uses ~150MB of RAM compared to Discord's 700MB+, built on Tauri (Rust) instead of Electron.
No ads, tracking, or unnecessary features; focuses on voice, video, screen share, and task boards.
Offers six channel types, task boards, calendar events, custom bots, and moderation tools.

OpenMarkdown is a local-first, feather-light, and fast Markdown editor built for users and their agents.
It uses a native Rust core, ensuring quick loading times and native performance.
The editor is AI-free; instead, it runs on the user's existing agent, providing direct integration.

PMB is a local memory system for AI agents that stores decisions, lessons, and project facts in a SQLite file you own.
It works offline with no API keys or cloud, providing memory recall in about 35 ms.
PMB automatically injects relevant memory before the agent thinks and journals work afterward, without requiring the agent to call tools.

The problem: when switching between AI assistants, context must be rebuilt from memory, causing friction and loss of fidelity.
Segue allows saving a working context (brief, notes, plans) in one AI and getting a short, pronounceable handle (e.g., 'brelavo') that can be passed to another assistant.
The second AI loads the context via the handle, picking up exactly where the user left off — no copy-paste or re-explaining.

Hasty Briefsbeta