AI / Agents
Every member can create their own agent in SweetHive: for all their hives, one hive, or a single context. Every agent obeys one law: it can never know more than the person who owns it.
Your agent reads only where you put it, and only what you can see there. Your visibility is checked again on every request, so when your access changes, your agent's reach changes with it. The rule is enforced in the platform's retrieval layer, not promised by a filter.
What your agent reads = its scope ∩ your visibility.
Create an agent in seconds and choose where it lives. Wherever you put it, your agent sees only what you can see: your groups, your subtree, nothing more. It works from the messages in its scope: recent activity, keyword search, briefings. It can also read the attachments of those messages, up to 20 MB: PDFs and text files directly, scans and images with a local model that reads images or with your own Claude. Its answers come to you; posting into a context is always your explicit choice, and the agent asks for confirmation first.
One agent across everything you belong to. “Give me a morning digest of all my hives.”
Focused on a single organization. “Watch this hive for anything about the audit.”
Pointed at a project. “Brief me every Monday on what's new in Project A.”
Turn the asks you repeat into Workflows: build them in My agents > Workflows, and your agent runs them within its scope, manually, on a schedule or from a webhook.
There is no shared bot answering for the whole company. Every teammate creates a personal agent of their own, with its own scoped token, and each agent stays inside its owner's visibility. An agent knows what its owner can see, and nothing more.
On Organization plans, the SweetHive Agents Server runs the personal agents of all your members on one machine you own, such as a Mac mini, a Mac Studio or any Docker host. Each member's agent runs in its own encrypted space, on shared local models.
How Agents Server works →Run your agent on your own computer with the free Agents Node, using local models (Ollama is bundled) or your own Claude Code login. On Organization plans, the Agents Server hosts every member's agent on hardware your organization owns, inside your perimeter.
OpenClaw showed the world what a personal AI agent feels like: it lives on your own computer, remembers your context, and quietly manages your tasks: one person, one machine, full control. SweetHive agents are that same idea, grown up for organizations.
| A personal agent on your PC | A SweetHive agent | |
|---|---|---|
| Where it runs | Your own machine | Your computer with the Agents Node, or your organization's own Agents Server |
| Who it works for | You | You. Every teammate gets their own |
| What it knows | Your files and chats | Its scope ∩ your visibility, checked on every request |
| The boundary | Your machine | The context tree, enforced in the retrieval layer |
A personal agent proves that people want AI that runs on their own terms. SweetHive brings the same idea to a whole organization: every member gets their own agent, each one working within what its owner may see, and the organization can host them all on its own hardware.
OpenClaw is an independent open-source project, not affiliated with SweetHive.The SweetHive Agents Node is the free desktop app that runs your agents on your own computer with local AI models. Install it, sign in with your SweetHive account, pick the hives your agent may see, and you're done. It also connects Claude Desktop and Claude Code to your SweetHive content through MCP, and updates itself.
Download for macOS (Apple Silicon) macOS (Intel) Windows
Read the setup guide Free download · OpenClaw remains supported as an alternative runtime for the same agent tokens.Aristeo, SweetHive's Consultant Agent, uses the admin capability of a connected agent to design and run your organization's structure with you: contexts, groups, invitations. Agents are included in every plan, per member.
Meet Aristeo →With SweetHive Agents Server your company runs the AI agents of the whole organization on its own hardware. Edge computing meets SaaS: collaboration in the cloud, intelligence and data inside your perimeter.
One IT-managed server hosts the agents of every member of your hives. Employees create an agent in SweetHive web and choose the company server: nothing to download, nothing to configure on their machine.
Every user’s agent runs in its own isolated, encrypted workspace. Conversations, tokens and memory are sealed per user: data of different people is never mixed, and inference never leaves your network.
IT installs it with Docker or as the desktop edition for Mac and Windows, and manages models and capacity from an admin console; the organization plan sets how many agents each member can host. Revoke a server or a single agent at any time.
An organization admin opens the Agent servers tab in the organization settings and downloads the package with its enrollment key. That panel is the only place the tool is distributed from.
IT starts it with Docker on a Linux machine, on-premise or in a private cloud, or installs the desktop edition on a Mac or a Windows workstation, then pastes the key. The server appears online in the panel.
Members create agents as usual and pick the company server as the location. Each agent goes online in its own isolated workspace, within the per-member limit of the plan.
Prompts, documents and AI output are processed on hardware the company owns. Sensitive content never transits third-party AI clouds.
Inference runs on your own GPU or CPU, with no per-token billing. The plan is flat, per organization.
Employees get sanctioned, scoped agents instead of pasting company data into public chatbots.
These are the same personal agents members create and use in SweetHive web and mobile. The experience stays the same; only the infrastructure changes.
No. The desktop Agents Node remains available for personal use, but with a company server nobody needs it: agents run server-side, in isolated per-user workspaces.
No. The admin console shows operations only (status, models, counts), never message content. Each user’s data is encrypted with keys dedicated to that user.
A Linux machine with Docker, or the desktop edition on a Mac (Apple Silicon or Intel, such as a Mac mini or a Mac Studio) or a Windows workstation. A GPU improves speed but is not required: models run locally via the bundled Ollama runtime.
It depends on your Organization plan tier: each member has a per-member agent allowance, enforced automatically.
Organization plans only. Hives owned by the organization get it for all their members.
Every agent output is labeled and attributed: Agent · name · created by …. AI never impersonates a person.
Every answer discloses its effective scope and its sources; every run is logged with what it read.
An inspector shows any agent's reach on the context tree.
Agents never send, move, or share anything without an explicit confirmation.
See how each teammate's own agent answers from the same hive, always inside what that person can see, live.
Get a demo