Changelog2026-10-02New

Agents on Claude (Beta)

Agents are in Beta. An Agent is a system prompt plus the Claude access it runs on; an AgentRun is one conversation with it, working in its own sandbox.

• The right model for each prompt. On Nodus’s Claude, every prompt is routed to Haiku, Sonnet, Opus or Fable, and that model answers the whole turn, including its commands. If routing is unavailable, Sonnet answers. Each turn records the model that served it and what it cost.
• Runs survive restarts. A run that is interrupted continues where it stopped and never repeats a model call or command it already made.
• Choose inference access. Use managed Claude or bring your API key. Set spec.perRunMaxCostUSD to limit managed model spending.
• Follow-ups from the CLI. nodus create agentrun NAME --agent claude-assistant --prompt "..." starts a run, and nodus agentrun send, steps and answer message it and read what it did.

Fan-out, groups and evals are not available yet. See Agents.