When to use NFLTR

NFLTR runs AI coding agents where your infrastructure lives: a Claude Code hub session spawns agents on the machines you join, steers, continues, and stops them, and receives every completion exactly once, over a hosted relay you don't have to operate. This page is the honest decision guide for whether it fits your workflow.

Use NFLTR when

• You want a goal in English ("prepare a launch readiness packet across docs, ops, and security evidence") to fan out into parallel agents the hub steers and reviews — not just a single agent looping in a chat.
• You want to watch each agent's task on its own, not buried in chat scroll. nfltr orch hub show and nfltr orch task show each one's status, events, and result.
• Work needs to run on different machines (e.g. one node has GPU access, another has production logs, a third is your laptop). Nodes connect outbound to the relay; no inbound firewall rules.
• You want provenance attributed truthfully — per-task model, machine, artifacts, and branch stay attached to the task that produced them.
• You want work to survive a closed terminal. Agents keep running when the hub exits, and reopening the project delivers every missed completion exactly once.

Don't use NFLTR when

• One agent in one chat session, on one machine, finishes the job end-to-end. The orchestration overhead isn't free.
• You need a low-latency HTTP proxy or tunnel — that's a different shape (look at ngrok, cloudflared, tailscale-funnel).
• Your machines can't open an outbound TLS connection to nfltr.xyz.
• The work has no useful split across agents or machines. NFLTR's value compounds when parallel agents, remote access, or durable hand-offs matter; without them one local session is simpler.

Decision shortcut

Follow the five-minute walkthrough: save your key, join one machine with nfltr node join, then give the hub a small goal with nfltr orch "<goal>" and see whether the loop matches how you want to work. The homepage demos show real runs.

Next steps

• Getting Started — hosted path from account to first goal
• Many agents across machines — watch, steer, continue, and stop
• Agent Orchestration — hosted product overview