# One platform. Every layer. — Hanzo AI > Models, agents, the record they leave, and the machines underneath. One API for all of it. Platform # One platform. Every layer. Models, agents, the record they leave, and the machines underneath. One API for all of it. The system ## One OS. Every layer of the company. From the company down to the machines under it, with learning and governance across every layer. api.hanzo.ai [Company/v1/team /v1/books46 ops](https://hanzo.team)[Intelligence/v1/ai296 ops](https://hanzo.ai/enso)[Execution/v1/tasks5 ops](https://tabs.hanzo.ai)[Infrastructure/v1/platform /v1/deploy56 ops](https://cloud.hanzo.ai)across every layer [Learn & adapt/v1/o11y381 ops](https://insights.hanzo.ai)[Trust & govern/v1/iam /v1/kms /v1/compliance179 ops](https://hanzo.ai/security) 10 of 120 route families · read from /v1/openapi.json ## One system from the first prompt to production. Ask a question, ship a change, launch a product, or run the stack yourself. Every path opens onto the same models, agents, data, and policy. [### Ask Use every model through one conversation and one API. Your app stays as it is.](https://hanzo.ai/models)[### Build Give Dev a goal. It reads the repo, makes the change, runs the tests, and prepares it to ship.](https://hanzo.ai/dev)[### Deploy Launch with data, identity, secrets, storage, search, and events already connected.](https://cloud.hanzo.ai)[### Own it Take the same open stack to your Kubernetes or laptop. Keep the control plane and data where you choose.](https://hanzo.ai/open-source) Agent runtime ## Agents with hands. Enso decides. Agents coordinate. Tabs gives them somewhere secure to act. tool     post_v1_exec_run subsystemexec · runs in a sandbox round    2 of 8 · the eighth gets no tools actor    acme/z · billed here arguments{"lang":"py","code":"…"} · redacted result   returned to the modelok bounds · 30s a call · 90s a run · 3 agents deep one tool dispatch, as the run’s span records it · sample values [Explore Tabs](https://hanzo.ai/tabs)[Explore agents](https://hanzo.ai/agents) ## Autonomous within boundaries. Accountable everywhere. Every action leaves the same record, whoever or whatever started it. actor   acme · service principal auth    api-key action  automations.tool.call resourceautomations/deploy seq     #4821 · append-only chainverified one audit record · sample values Every tool has a permission, every secret a policy, every execution a boundary, and every consequential action an approval when you require one. Identity, authorization, secrets, isolation, networking and audit are built into Hanzo OS. [Read the security architecture](https://hanzo.ai/security) ## See the whole company think. One trace connects the objective that started the work to everything that followed. Models→agents→tools→infrastructure→result→cost→evaluation Logs, metrics, traces, sessions and scores share the same operational context. [Explore Observability](https://hanzo.ai/o11y) ## Everything works better together. Thinkwith Enso. Buildwith App and Dev. Workin Team. Learnwith Insights. Runon Hanzo Cloud. $curl -fsSL https://hanzo.sh | sh $hanzo auth login $hanzo # a coding session in your repo install, sign in, start working [Start building](https://hanzo.sh) Platform-as-a-Service ## The services an app needs anyway Platform ships your code. These are the pieces it lands next to. Deploy each one beside your app, or reach it on Hanzo Cloud. ### Core Services [#### Auth & IAM Authentication, SSO, OAuth, JWT, and sovereign user management out of the box](https://hanzo.ai/iam)[#### Serverless Functions Serverless functions with automatic scaling and edge deployment](https://hanzo.ai/functions)[#### Database & Datastore High-performance SQL, vector search, and real-time subscriptions](https://hanzo.ai/database)[#### Object Storage S3-compatible distributed object storage with global CDN integration](https://hanzo.ai/storage)[#### Realtime Sync WebSockets, presence, and live state replication for collaborative apps](https://hanzo.ai/realtime)[#### Secrets & KMS Hardware-backed secret management, envelope encryption, and key rotation](https://hanzo.ai/kms) ### Additional Services [API GatewayRate limiting, auth verification, and intelligent request routing](https://hanzo.ai/gateway)[Background TasksScheduled cron jobs and durable task queues with retry logic](https://hanzo.ai/tasks)[PubSub & WebhooksEvent-driven messaging and real-time webhook delivery](https://hanzo.ai/pubsub)[Observability & O11yOpenTelemetry traces, metrics, structured logs, and audit trails](https://hanzo.ai/o11y)[Edge NetworkGlobal edge compute, smart routing, and low-latency cache](https://hanzo.ai/edge)[Vector & SearchHybrid keyword and dense vector search with sub-millisecond retrieval](https://hanzo.ai/vector) hanzo platform $ hanzo init my-app ✓ Created project configuration ✓ Initialized Auth, Database, Storage ✓ Generated TypeScript types $ hanzo dev Starting local development server... Platform running at http://localhost:8000 $ hanzo serve cloud Deploying to production... Live at https://my-app.hanzo.app [Get Started](https://docs.hanzo.ai/docs/services/platform)[Explore Cloud](https://hanzo.ai/cloud) "The wise engineer owns their tools, lest their tools own them." Principle 14 ## Where it runs is your call Same platform, same console, same API. You pick the machines. ### Self-Hosted One command on a server you already pay for. The whole platform, on hardware you can walk up to. - ✓ Runs anywhere Docker runs - ✓ Scales out across a Swarm cluster - ✓ Drives a Kubernetes cluster you own [View on GitHub](https://github.com/hanzoai) ### Hanzo Cloud The same platform, run for you. Sign in and deploy. - ✓ The machines are already running - ✓ Deploy on push, or only on a tag - ✓ Metered and billed per organization [Explore Cloud](https://hanzo.ai/cloud) ### Hybrid Run the control plane on your own server. It deploys to the servers and clusters you already have. - ✓ Servers stay where they are - ✓ One console over all of them - ✓ Per-app target: this host, Swarm, or Kubernetes [Contact Sales](https://hanzo.ai/enterprise) ## Open source, all of it Apache-2.0. Forked from Dokploy, and it says so in the NOTICE. #### Apache-2.0 Use it commercially. Change it. The upstream attribution travels with it. #### It is your server Builds, images, databases and backups sit on machines you chose, in a region you picked, under credentials you hold. #### Read the code The code behind every deploy is right there, and so is the OpenAPI document the console itself calls. [Star on GitHub](https://github.com/hanzoai) Open Source Revenue Sharing ### Up to 5% of compute goes back to open source Every deployment is SBOM-verified. Contributors to Dokploy earn a share of compute revenue — transparent, on-chain, and customizable by the community. [Connect & Earn](https://hanzo.ai/open-source/dividends)[Learn More](https://hanzo.ai/open-source) ## Start building The whole platform is on GitHub. Clone it and run it. [Get on GitHub](https://github.com/hanzoai/platform) ## Open source License: Apache-2.0[hanzoai](https://github.com/hanzoai) ## Get Platform PaaS — deploy from git [Deploy to Cloud](https://platform.hanzo.ai/deploy)