Welcome to Vonzio
Vonzio runs Claude-powered AI agents in isolated Docker containers. You give them work — bug fixes, transaction summaries, statement chases, code reviews — and they execute autonomously, calling tools, integrating with your data sources, and notifying you when they’re done.
This is the reference. If you’re looking for the marketing pitch, start at vonzio.com. Everything below assumes you have an account on vonz.io and want to actually use the platform.
What you’ll find here
Section titled “What you’ll find here”What Vonzio is, in one screen
Section titled “What Vonzio is, in one screen”| Concept | One-line definition |
|---|---|
| Agent profile | A configuration: which model, which tools, which MCP servers, which secrets. Reusable. |
| Workspace | A running session — an agent profile + an isolated Docker container + conversation history. |
| Task | A single unit of agent work. Either fire-and-forget (mode: batch) or interactive (mode: session). |
| Playbook | A scheduled task. Cron triggers, optional notification on completion, multi-chain execution. |
| MCP server | A capability surface the agent can call: memory, notifications, Gmail, bank data, platform operations. |
| Integration | A connected third-party account (Slack workspace, Telegram bot, Gmail OAuth grant, Teller bank link). Scoped per-agent. |
Source of truth
Section titled “Source of truth”This documentation is hand-written and matches the code at the most recent release. The OpenAPI spec and Swagger UI are machine-generated from the same Zod schemas the server uses at runtime — use those for code generation, use this for understanding.
When the prose docs and the OpenAPI spec disagree, the spec wins — please let us know so we can fix the prose.