Show HN: Pizza Bot – An inbox for AI agents that work in the background

Show HN: Pizza Bot – An inbox for AI agents that work in the background. Please reload this page. pizza-bot-app / pizza-bot Public Notifications You must be signed in to change notification settings Fork 13 Star 194 mainBranchesTagsGo to fileCodeOpen more actions menuLatest commit History79 Commits79 CommitsFolders and filesNameNameLast commit messageLast commit date. github. github appsapps assetsassets docsdocs examples/pluginsexamples/plugins packagespackages pluginsplugins scriptsscripts skillsskills tests/langgraph-compattests/langgraph-compat. dockerignore. dockerignore. env. example. env. example. gitignore. gitignore. worktreeinclude. worktreeinclude AGENTS. mdAGENTS. md CLAUDE. mdCLAUDE. md CODE_OF_CONDUCT. mdCODE_OF_CONDUCT. md CONTRIBUTING. mdCONTRIBUTING. md DockerfileDockerfile LICENSELICENSE NOTICENOTICE README. mdREADME. md ROADMAP. mdROADMAP. md SECURITY. mdSECURITY. md docker-compose. ymldocker-compose. yml eslint. config. jseslint. config. js package-lock. jsonpackage-lock. json package. jsonpackage. json tsconfig. base. jsontsconfig. base. json tsconfig. jsontsconfig. json turbo. jsonturbo. json vitest. config. tsvitest. config. ts View all filesRepository files navigationPizza Bot OSS Pizza Bot is an inbox for long-running AI work.

What happened

AboutA local-first inbox for long-running AI agents, built with DeepAgents and LangGraph. github. com/pizza-bot-app/pizza-bot/releasesTopicsagentic-aiai-agentsamazon-bedrockdeepagentselectronhuman-in-the-looplanggraphlocal-firstmcptypescriptResourcesReadmeApache-2. Agents keep working when you navigate away or disconnect; the api-server process must remain running. Pizza Bot uses a stateful DeepAgents/LangGraph runtime with the same React experience in Electron and the browser. The Built-in Pizza Bot Guide can explain features, suggest workflows, help with setup, and point to project documentation. Start or schedule a task, return to your day, and let completed work collect in Unread while runs waiting for your decision collect in Action.

Pizza Bot was developed at Amazon and is released under the Apache 2. Completed work lands in Unread; durable approval requests land in Action.

The wider picture

Group threads into folders without hiding matching work from the global Unread and Action queues. Checkpointed runs survive client disconnects, and cron or webhook triggers can start work without an open conversation. Skills become tool-scoped subagents whose progress appears in the Activity panel. Human-in-the-loop approvals, long-term memory, file attachments, and desktop notifications are built into the workflow. Add individual read-only or writable folders under Settings > Files; Pizza Bot receives no default home-directory access. Ways to run Experience Best for Start here Electron desktop Local inbox with an embedded backend npm run dev Browser Web development or static deployment Browser development Terminal CLI Scripts, terminals, and remote backends CLI Standalone backend Remote Electron, browsers, containers, or Linux services Backend guide A running api-server needs access to at least one model provider; HTTP clients do not.

See Extending Pizza Bot for configuration, environment references, skill authoring, approval gates, and plugin installation. Project layout apps/ api-server (Hono) | cli | desktop-shell (Electron) | web (React) packages/ core | runtime-langgraph | inference-providers | plugin-api | plugin-sdk | storage | logging plugins/ bundled Plugin packages and their packaging workspace skills/ optional Built-in Agent Skills tests/ LangGraph compatibility and protocol conformance The production graph engine is isolated to packages/runtime-langgraph; frontends consume protocol projections rather than importing runtime or model bindings.

What has been reported

Contributing – development setup, CI checks, worktrees, releases, and layering rules. Security – network defaults, credentials, local data, and plugin trust. Threads, checkpoints, memories, attachments, and logs live under (~/. pizza-bot-oss by default). Contributors Pizza Bot was designed, built, and brought into the open by its Executive Chefs and Sous Chefs: Executive Chefs Sous Chefs Pizza Bot was also shaped by more than 2,000 users across Amazon who tested earlier versions and shared feedback from real-world use.

Their bug reports, ideas, and candid input helped make Pizza Bot ready for a broader community. 99 and works with the company’s Active Guard Outdoor Protection (starting at $49. This combines AI analysis with live agents to detect potential threats and respond proactively. The doorbell requires a SimpliSafe base station and keypad and works with any monitored SimpliSafe plan.

What happens next

RelatedSimpliSafe’s new camera lets live agents watch your propertySimpliSafe’s new outdoor monitoring service combines AI with live agents“Stop! Who’s there? ” SimpliSafe adds a live guard feature to its home security systemThe company has published a privacy page detailing how the system works, including that the footage is encrypted (at rest and in transit, not end-to-end) and that it “won’t share camera footage with law enforcement unless required by law. ”Color-coded LED status lights on the doorbell indicate when a monitoring agent (amber) or homeowner (blue) is speaking, and you can create a library of familiar faces so the monitoring agent doesn’t scare the bejeezus out of your dog walker.

Ring offers a similar proactive security feature called Virtual Guard that works with its Ring Alarm system for $99 a month. When Google broke those commitments, I resigned at significant financial cost so that I could publicly document Google’s broken promises. ’ Photograph: Dan Kitwood/Getty ImagesI worked at Google DeepMind. This July, OpenAI’s AI swarm of 700 agents broke containment to hack Hugging Face, a multi-billion dollar company. I then worked for years at Google DeepMind, which paid me to help ensure that future superintelligent AIs will want to help us.

They’re increasingly trusting their AIs with the process of improving the next crop of AIs, and it’s working.

The report has been compiled by The Daily Waves using information reported across github.com, theverge.com, theguardian.com. Details are presented according to the information available at the time of publication and may change as authorities, organisers or other relevant parties provide updates.