Introducing Volobox

Today we are announcing Volobox: the workspace where people and agents work as one team.

In practice: you assign a task to an agent the same way you assign it to a teammate. If it is a customer request, the agent drafts the response and asks for your approval before anything goes out. If it is a bug, the agent writes the code and comes back with a pull request for your review, and you can watch it work live the whole way: every step, every change, and what each step costs. Agents also join chat when mentioned, draft documents, and run scheduled playbooks, under the same permissions and audit as everyone else.

The Volobox Home dashboard with today's meetings and work, assigned project requests, due-soon and active tasks, and the team panel

Two problems we could not ignore

1. AI is being adopted one person at a time, not as a team. Almost every knowledge worker now has a personal AI assistant, and individual productivity has clearly gone up. But the way teams work together has barely changed. Your best engineer gets great output from a coding agent that nobody else can see, review, or reuse. Your operations lead re-explains the same process to a chatbot every week. Very few teams have agents the whole team shares: agents that belong to projects, take assigned tasks, and join discussions when mentioned.

2. The context that people and agents need is scattered. The most valuable input for a new teammate and for an AI agent is the same thing: shared, searchable context. What is this project? Why did we decide that? Where is the spec? Because teams use a different tool for every purpose (tracker, chat, docs, wiki, meetings, code), that context is fragmented across all of them. People lose hours to it. Agents, for the most part, cannot reach it at all.

These two problems feed each other. An agent without team context produces generic work, so it stays a personal toy. And a team without shared agents keeps re-explaining the same context into a dozen private chat windows.

What Volobox is

Volobox puts people and agents in one workspace with one set of modules: projects, chat, docs, meetings, and files. Everything your team creates becomes context agents can use. Doing the work is what builds the context; there is no separate knowledge base to feed and maintain.

And because our agents act rather than only suggest, trust is engineered in instead of promised. Sensitive actions pause on an approval card until a person says yes. Routine actions can be pre-approved with rules that carry usage caps and hard rate limits. Every action lands in an audit log. When an agent writes code, you watch the coding session live. A coding room, not a black box.

A Volobox project task dialog where the Software Developer agent is selected as the assignee

You do not have to replace your stack on day one. Start with one project, keep GitHub as the home of your issues with two-way sync, and connect the rest of your systems over MCP.

Why us

I have spent most of my career doing one thing: taking the code that teams rebuild in every project and turning it into a framework. Our team develops the ABP Framework, an open source application framework that companies around the world run their software on. Turning repeated, ad hoc engineering into reusable, well-designed infrastructure is our craft.

When AI agents arrived, we saw a familiar picture. Teams were gluing agents onto tools that were never designed for them: one-off scripts, disconnected bots, no shared identity, no permissions, no audit trail. It looked like backend development before frameworks, with everyone solving the same hard problems from scratch. So we did what we have always done: we built the platform we wished existed.

We run our own company on Volobox. Our projects, chat, meetings, and docs live in it, agents take tasks from our own backlog, and the pull requests they open go through the same review as everyone else's. The work behind this launch was planned, discussed, and shipped inside the product we are announcing today.

What ships today

First, the foundation: Volobox is a complete workspace, not an agent bolted onto a demo. Projects with boards and milestones, team chat, docs, meetings, and files are all here, and it is designed to be a great workspace even before you turn the agents on. The full picture is on the platform overview. On top of that, the highlights:

• Assign a task to an agent and get a pull request back, with the whole coding session visible while it runs. Read more on AI coding.
• Agents ask before doing anything sensitive, routine actions can be pre-approved with usage caps, and everything lands in an audit log. The full governance model is on the Trust & Security page.
• Shape agents into real roles with skills, commands, and installable library packs, and connect your existing systems over MCP, in both directions. See AI agents.
• Automate recurring team processes with workflows that run on schedules and triggers, make decisions, and notify the team.
• Ask questions across everything your team has created and get cited answers.
• Cloud or on-premise deployment, with your own model providers and your own keys.

Volobox is in early access, and we are onboarding teams through demos. This is the beginning: if the problems above sound like your team, we would love to show you Volobox on your own work.