Core vs Spectrum

Core is an open-source "AI operating system" built around a single premise: AI should remove operational friction, not just build-time friction. While most AI tools require you to brief them every session and manually synthesize their outputs, Core ships with Alfred — a persistent, named butler agent that executes scheduled tasks autonomously and surfaces results where you already work. The philosophical distinction is between directive AI (you tell it what to do each time) and ambient AI (it runs your backlog while you focus on other things). Alfred maintains context across sessions, executes routine operations on schedule, and doesn't wait to be invoked. Think scheduled research summaries, automated triage, or recurring data pulls — tasks that currently require either expensive automation platforms or manual check-ins. The project is self-hostable via GitHub and is currently in waitlist mode for the hosted version. It's early-stage, but the architecture — a persistent agent with long-running task support and integrations into existing workflows rather than a separate chat interface — points toward a category of tooling that's been largely missing. Most AI assistants are reactive; Core is explicitly designed to be proactive.

Spectrum, from Photon, launched on Product Hunt today with 105 upvotes and a simple but sharp premise: your users don't want to learn a new AI interface—they want AI to show up in Slack, Teams, email, and every other tool they already use. Spectrum is an agent deployment layer that routes your AI agents to wherever your users are, with no per-integration custom dev work. The core product is an abstraction layer that handles the connector plumbing: authenticate once, and your agent can receive messages and send responses across all connected channels. Built-in conversation management means agents maintain context across channels—a user can start a request in Slack, continue it in Teams, and finish in email without losing thread. The platform also handles rate limiting, authentication, and error handling for each channel. For teams building internal AI tools or customer-facing AI assistants, this solves real integration pain. Building a Slack bot, Teams integration, email handler, and web widget separately takes weeks per channel. Spectrum reduces that to a single agent definition deployed everywhere. The question is pricing and lock-in: if Photon becomes the integration layer, they sit in a strategically critical position.