Amazon Web Services has launched Pizza Bot, an open-source application that gives developers an email-style inbox for overseeing AI agents that operate in the background. The project tackles a fundamental mismatch: chat interfaces don't work well for agents whose tasks continue after the human user has left for lunch or gone to bed. Pizza Bot borrows the familiar structure of email, where finished jobs appear as unread threads and anything requiring a human decision surfaces for action.
The desktop application, available for macOS, Windows, and Linux, runs a local server by default and lets developers choose the model powering it—including Anthropic, Amazon Bedrock, Google Gemini, OpenAI, OpenRouter or a local model via Ollama. The server can also run on an always-on host or in a container, allowing scheduled agents to keep working while the laptop is closed and their threads to be picked up later from another device. An Activity panel exposes jobs handed off to specialist agents, including their tool use and progress. Despite its Amazon roots, Pizza Bot is now a standalone community project rather than an AWS service—it lives in its own GitHub organization, separate from Amazon, and comes with no AWS support or service-level agreement.
Writing about the new project in a LinkedIn post on Thursday, co-creator Joseph Dolivo, principal technologist at AWS Startups, notes that Pizza Bot shifts the burden of monitoring agent work firmly away from the user. "Instead of you having to initiate every conversation or wait on a prompt, scheduled agents run autonomously in the background and surface updates directly into your inbox for review and triage," he writes. In the accompanying blog post for the project's official launch on Thursday, the creators emphasize that user absence is, in fact, a core tenet of the design brief. "The interface assumes you are not watching," they write, adding that this assumption "buys you pauses that outlast the session that created them, notifications worth acting on, and scheduled work that produces threads instead of logs."
Pizza Bot's agent runtime is built with DeepAgents, LangChain's open-source harness for long-running agent tasks, which itself runs on LangGraph, its runtime for stateful agent execution. The critical component is persistence: LangGraph checkpoints an agent's state as it works, allowing a run to stop for approval, survive a disconnected client and resume later without starting again from scratch. Pizza Bot stores those checkpoints, along with threads and other application data, locally in SQLite and ordinary files. The choice of LangGraph over AWS's own Strands Agents SDK came down to maturity and ecosystem breadth, according to Dolivo, who also wanted to reduce friction for community adoption since the team knew they'd be open-sourcing it.
The genesis of Pizza Bot can be traced back to April 2025, when Dolivo kicked off what he calls a "side-of-desk passion project" dubbed "JoeBot" that automated repetitive CRM logging. He later teamed up with colleague Igor Fil to turn that script into Pizza Bot, an MCP server that could execute parameterized, deterministic "recipes" across its internal systems. As the project evolved, it would eventually grow to more than 30 contributors and over 2,000 users inside Amazon, and so Pizza Bot needed a front end that people could open and use. "An MCP server requires an MCP client, and expecting non-technical users to work out of an IDE or terminal was never going to cut it," Dolivo adds, noting they had to meet people where they actually work and own the experience end to end. The result was the version released this week: a desktop app built around an inbox rather than a terminal. For organizations deploying autonomous agents at scale, the inbox metaphor may prove essential—not because it's novel, but because it acknowledges that human oversight can't be synchronous when the work isn't.