Pizza Bot is an open-source application for delegating work to AI agents and reviewing the results later in an inbox. Its server keeps agent runs and state while you switch threads, reload the page, or disconnect; finished work appears in Unread, and runs waiting for your decision appear in Action. It is a community project, not an AWS-hosted service. (AWS Open Source Blog)
What is Pizza Bot?
Pizza Bot is an interface for asynchronous AI-agent work: delegate a task, leave the conversation, and return when the agent finishes or needs input. Tasks can be started directly, scheduled, or triggered by a webhook. The application also has an Activity panel for delegated specialist workers. The AWS Open Source Blog describes work that may take minutes, pause for approval, or run on a schedule. (AWS Open Source Blog)
As an Amazon Associate I earn from qualifying purchases.
The inbox separates work by status. All contains thread history, Unread surfaces completed work you have not reviewed, and Action contains work paused for an approval or answer. That distinction lets you spot both finished results and tasks that cannot proceed without you. (Pizza Bot repository)
How do I run AI agents in the background?
Pizza Bot separates the backend that owns agents and their state from the clients used to interact with them. The server answers over HTTP; clients include an Electron desktop app, a browser, and a terminal CLI. The desktop app can start a local server, or clients can connect to a standalone backend. The launch article describes a stateful DeepAgents/LangGraph runtime, with SQLite and files used to persist state, and connections to MCP servers, skills, and the selected model provider. (Pizza Bot repository; AWS Open Source Blog)
#1 Best Overall
- High-Performance AI Processor：The MS-02 Ultra features an Intel Core Ultra 9 285HX (24C/24T, up to 5.5 GHz, 13 TOPS NPU), delivering fast and efficient performance for AI inference, algorithm development, and media workloads. A PCIe x16 expansion slot supports desktop-class GPU upgrades for advanced model training and accelerated computing tasks. It's ideal for creators, engineers, and teams handling intensive parallel workloads.
- 4 × M.2 PCIe 4.0 + 4 × DDR5 SODIMM slots:Four DDR5 SODIMM slots support up to 256 GB of memory, while ECC helps maintain data integrity in mission-critical environments. Four PCIe 4.0 M.2 slots support up to 24 TB of storage, supporting RAID 0/1/5/10, combining high-speed performance with data protection. It allows for the creation of independent scratch disks, media libraries, and project drives, providing high-throughput for production workflows.
- PCIe & USB 4.0 v2: Up to three PCIe slots can be equipped, including a dual-slot x16 GPU. The main slot supports PCIe 5.0, meeting the needs of high-bandwidth creative and computing workloads. USB 4.0 v2 (80Gbps) supports high-bandwidth external storage and displays.
- Ultra-fast Networking: Wi-Fi 7 further enhances wireless performance with next-generation speeds and low-latency stability. Intelligent bandwidth switching optimizes throughput in different network environments, ensuring optimal performance for enterprise or local networks. Dual 25GbE ports (providing up to approximately 3.125 GB/s bandwidth, about 25 times faster than traditional 1GbE), enabling seamless large-scale file transfers and parallel computing. 10GbE and 2.5GbE ports, with support for Intel vPro technology, ensure enterprise-grade remote management and deployment flexibility.
- Server-grade thermal architecture: Utilizing a dedicated CPU/GPU airflow design, equipped with a 6-pipe dual-fan cooler, it maintains stable performance even under sustained loads, delivering up to 140W Turbo power while maintaining a 100W TDP, and operating with noise levels as low as 36 dB. An integrated 350W power supply ensures stable and reliable output for demanding computing tasks and fully loaded extended configurations.
To use it, choose a client and backend arrangement, configure a supported model provider, and then delegate work. A live run requires provider configuration; the project’s current quick start says running from source requires Node.js 24 or newer. Setup commands, credentials, and provider details can change, so follow the repository’s current instructions rather than relying on an old installation guide. (Pizza Bot repository)
Can Pizza Bot keep working when I close the app?
A run can continue when you switch threads, reload a page, or disconnect because the server, not the open client window, owns the run. That does not mean a stopped or powered-off backend will keep executing. For scheduled tasks that must run while your personal computer is off, the AWS launch article recommends operating the backend on an always-on machine or in a container. You are responsible for keeping that deployment running, backed up, and current. (Pizza Bot repository; AWS Open Source Blog)
How do I self-host Pizza Bot?
Self-hosting means running the backend where you want its agent runs and stored state to live, then connecting a desktop, browser, or CLI client to it. The project’s documented default is local-first: the API server binds to 127.0.0.1, and threads, checkpoints, memories, attachments, and logs are stored under the Pizza Bot data root. Non-loopback access requires authentication and an explicit origin allowlist. (Pizza Bot repository)
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Choose where the backend runs
| Arrangement | Where work and data live | Operational consideration |
|---|---|---|
| Desktop app with local server | On the computer running the local backend; data is stored under its Pizza Bot data root by default. | Convenient for local use. Tasks requiring the computer to be off need a different always-on backend. |
| Browser or CLI connected to a standalone backend | On the host running the backend, not necessarily on the client computer. | For remote access, configure authentication and an explicit origin allowlist; the operator handles uptime, backups, and updates. |
| Backend on an always-on machine or in a container | On that host or in the environment where the backend stores its data. | Useful when scheduled work must run while your personal computer is off; no particular hardware is required by the project. |
These arrangements are deployment options, not published performance or cost comparisons. (Pizza Bot repository; AWS Open Source Blog)
Rank #3
- Professional AI & Creator Workstation: AMD Radeon AI PRO R9700 GPU with 32GB GDDR6 is engineered for AI development, professional content creation, and compute-intensive workloads.
- Massive 32GB Memory Capacity: 32GB of GDDR6 memory on a 256-bit bus provides ample bandwidth for large AI models, 8K video editing, and complex 3D rendering.
- Advanced RDNA 4 with AI Accelerators: 64 Compute Units with 3rd Gen Ray Tracing and dedicated 2nd Gen AI Accelerators for groundbreaking AI performance and visual computing.
- Professional Blower Cooling: Efficient single blower design exhausts heat directly out of the chassis, ideal for multi-GPU workstation and server configurations.
- Enterprise-Grade Thermal Solution: Vapor chamber heatsink with industrial Honeywell PTM7950 thermal interface material ensures reliable cooling under sustained professional loads.
Set access boundaries deliberately
Local folder access is not implicit: grant the folders the agent needs. Grants are read-only unless writes are enabled. If the backend is remote, a granted path refers to a folder on the backend host, not the client computer. Treat MCP servers and plugins as trusted code: the project warns they can execute with the permissions of the user account running them. (Pizza Bot repository)
Which model providers and downloads are listed?
The repository lists Amazon Bedrock, Anthropic, Google Gemini, OpenAI, OpenRouter, and Ollama as supported providers. Availability, model catalogs, credentials, and setup requirements can change; check the current repository before choosing a provider. Pizza Bot itself is released under the Apache 2.0 license. (Pizza Bot repository)
Rank #4
- FAST RUNS IN THE FAMILY — The 16-inch MacBook Pro with the M5 Pro or M5 Max chip brings next-generation speed and powerful on-device AI to personal, professional, and creative tasks. With all-day battery life, double the starting storage,* and a breathtaking Liquid Retina XDR display, it’s pro in every way.*
- BUCKLE UP — Along with a next-generation CPU, faster unified memory, and up to 2x faster SSD storage,* M5 Pro and M5 Max feature a more powerful GPU with a Neural Accelerator built into each core, delivering faster AI performance and on-device training capabilities. So you can blaze through demanding workloads at mind-bending speeds.
- BUILT FOR AI — Apple silicon, and every major component that powers it, is designed to run demanding on-device AI workloads like LLM inference and training. And Apple Intelligence helps you write, express yourself, and get things done effortlessly with groundbreaking privacy protections at every step.*
- ALL-DAY BATTERY LIFE — MacBook Pro delivers the same exceptional performance whether it’s running on battery or plugged in.*
- MACOS RUNS APPS FAST — All your go-to apps run lightning fast in macOS, including built-in apps like FaceTime and Messages. Plus, built-in virus protection and free software updates help keep your Mac running smoothly and securely.
At the time of the repository information reflected here, listed downloads include macOS installers for Apple silicon and Intel, Windows x64 setup installers, and Linux x64 and arm64 packages. The README describes the macOS packages as signed and notarized; it says Linux packages are not signed and directs users to verify them against SHA256SUMS. Check the release page and its verification instructions for the package you intend to install. (Pizza Bot repository)
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsWho made Pizza Bot, and what evidence is there of its use?
The AWS Open Source Blog published its launch article on September 10, 2026, by Joseph Dolivo and Igor Fil. It says the name refers to Amazon’s “two-pizza teams,” and describes Pizza Bot as an open-source rebuild following earlier internal versions. The article names Flávio Schuindt, Jacob Wert, Michael Karachewski, and Itzik Paz as contributors. (AWS Open Source Blog)
Best Value
- 【High-Performance APU】The MS-S1 MAX features an AMD Ryzen AI Max+ 395 APU, integrating a Zen 5 architecture CPU (up to 5.1GHz, 16C/32T, 64M L3 Cache), an RDNA 3.5 GPU, and an NPU (50 TOPS). The total system output is 126 TOPS. It provides powerful parallel computing capabilities for demanding AI workflows. It is ideal for running local LLMs, multimodal models, and computationally intensive tasks
- 【128GB UMA Memory】Equipped with up to 128GB of LPDDR5x-8000MT/s unified memory, it enables the CPU and GPU to access a shared, high-bandwidth memory pool with extremely low latency. Ideal for large-scale AI inference, 3D workloads, and complex timelines in video editing. It eliminates traditional VRAM bottlenecks, ensuring smoother data transfer during high-intensity computations. The UMA design maximizes performance stability under high loads
- 【Flexible Expansion】The MS-S1 MAX features USB4 V2 (up to 80Gbps), dual 10GbE LAN, HDMI 2.1 (up to 8K60), a full-length PCIe x16 expansion slot, and dual M.2 slots supporting up to 16TB RAID 0/1. Wi-Fi 7 provides stronger signal coverage and a more stable wireless experience. The slide-out design facilitates upgrades and maintenance. It easily adapts to personal, studio, or rack-mount enterprise environments
- 【High-Efficiency Cooling System】Utilizing an aerospace-grade aluminum alloy chassis, copper base plate, six heat pipes, dual turbine fans, and advanced PCM thermal conductive material, it maintains stable cooling performance even under continuous load. This system supports 130W continuous power and 160W peak power operation, with a built-in 320W power supply. It boasts multiple global certifications including CCC, FCC, UL, CE, and UKCA, ensuring stable and reliable operation in various environments
- 【Cluster Design】Two MS-S1 MAX units can be configured as a dual-unit cluster to run a large 235B Q4 model locally, achieving an output speed of 10.87 tok/s. Supporting 2U rack deployment, multiple MS-S1 MAX units can be cascaded into a distributed cluster to create a high-efficiency AI computing center. A cluster of four MS-S1 MAX units successfully ran a DeepSeek-R1 671B Q4 large model. A reserved cluster power-on interface allows for unified start-up and shutdown
That launch article reports that more than 2,000 Amazon employees used earlier versions for tasks including meeting preparation and follow-ups, email drafting, Slack summaries, CRM logging, prioritizing the day, and web research. This is a figure reported by the article, not an independent adoption study or a measured productivity result. The official sources cited here provide no independent benchmark or quantified performance result. (AWS Open Source Blog)
Pizza Bot is a community project; the AWS launch article says it has no AWS support or service-level agreement. That matters if you are evaluating it for work that depends on guaranteed support or uptime. (AWS Open Source Blog)
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
Free tools Windows power users keep installed
One-click scans. No signup required.
