Agents
Agents that work inside your workspace.
Akua Agents run in the dashboard on the same API as the CLI. Connect keeps credentials and grants out of the prompt, skills teach the agent your workspace, and sandboxes give it a safe place to work.
The question
Can an agent take production down?
It can only touch what you connect and grant, and sensitive tool calls wait for your approval in the dashboard.
What is in it
Agents, piece by piece.
What each part does, and whether you can use it today.
Agent skills
LiveBundled task skills the agent loads for common jobs in your workspace.
Dashboard agent
LiveOpenCode chat in the dashboard, with approval for sensitive tool calls.
Code Mode
Betaakua.request() typed bridge with server-injected auth.
Agent identities
SoonDurable configured persona + capability bundle.
Agent sessions
SoonWorkspace-scoped conversation / task instances.
Agent turns & events
SoonOne submitted instruction; append-only normalized stream.
Approval gates
SoonHuman approval for writes / deploys / shell / network / secret access.
Ambient agents
SoonContinuous watchers that proactively open investigations.
Hosted coding sandboxes
SoonCodex CLI / Claude Code / Akua CLI inside isolated runtimes.
What it costs
The platform is a flat fee. Compute is at cost.
Free to start with one managed cluster and one machine. Pro is €20 per workspace and month. Your own cloud key removes every limit, and Akua never marks up compute.
Start with agents
on your own terms.
Free to begin, on Akua-managed machines or your own cloud key.