Keera Agents
Sandboxed AI agents that assist your team
Keera Agents runs AI agents for your business. Each agent is an assistant with its own sandbox, workspace and memory. Your team gives it work in Microsoft Teams or Slack, and every model call passes through Keera Gateway.
How Keera Agents works
Work reaches an agent's sandbox through Keera Agents, and every model call leaves through Keera Gateway. Without work, an agent sleeps and holds no compute.
- Teams
- Slack
- Keera Chat
- Schedule
- GitHub and GitLab
Keera Agents
Your agent in its own sandbox, with its memory and files
Keera Gateway
Checks every model call: own key, budget, filters, audit log
- Swiss open-weight models
- Frontier models
- Self-hosted models
What Keera Agents does
Each agent has instructions, a model, tools and a monthly budget.
Work from your chats
Write to an agent in Teams, Slack or Keera Chat. It answers in the same thread and remembers what was said there.
A board and a schedule
Assign it a card, and it moves the card to Review when it is done. Or let it run every weekday at eight and post the result to a channel.
Your folders
It reads and writes in the Google Drive, OneDrive and SharePoint folders you connect, and starts when a new file lands.
Your repositories
In GitHub or GitLab it pushes a branch of its own and opens a pull request for a person to review. Your main branch stays yours.
Agents under your rules
An agent is not a loophole. It follows the same rules as the person who owns it, and it only reaches what you connect.
Its own key
Every model call goes through Keera Gateway with the agent's own key, in its owner's name. Model access, budgets and the audit log apply as they do to people.
A sandbox of its own
Keera Agents runs on your existing Kubernetes cluster. Each agent gets a sandboxed container or a micro VM of its own, and what it runs stays inside.
No secrets inside
The agent's sandbox holds no password for your chats, drives or repositories. Keera Agents makes those calls and checks first that the agent may.
You decide who asks
Only its owner, everyone in the organisation, or the people you list. Anyone else gets a short no. When the owner leaves, the agent stops.
Questions about Keera Agents
What teams ask us before they hand work to an agent.
What does Keera Agents keep of my data?
What the work needs: the agent's memory and files in its workspace, and each task's log for 90 days, so a person can check its work. Keera Gateway never stores or trains on the prompt or the answer; it keeps only the request - who, when, which model - in your audit log. Deleting an agent deletes its workspace.
What can an agent in Keera Agents reach?
Only what you connect: models and MCP servers through Keera Gateway, the chats it is in, its folders, and pushes to branches that start with keera/. Its sandbox holds no password or token for those services. Keera Agents makes those calls itself, after checking that the agent may.
How does Keera Agents fit with Keera Gateway?
Keera Agents is built on the gateway. Each agent calls models with its own key, in its owner's name, so model access, budgets, filters and the audit log apply to it as to a person. Each task shows in the gateway as one session.
How is Keera Agents different from Hermes Agent or OpenClaw?
Hermes Agent and OpenClaw are open-source assistants for one person, on their own computer or server, with that person's keys and accounts. They do that well. Keera Agents runs agents for a whole business: each has an owner, a rule for who may give it work, and no passwords for your services in its sandbox. Every model call goes through Keera Gateway, within budget and into your audit log.
Questions, comments, quotes
Have a question or a comment? Need a quote for on-premise or an SLA? Write to us.