How the fleet fits together.

Pooled machines

Install OmniConflux on each machine you want in the fleet and pair it once. Each machine reports what it can offer: CPU, memory, GPU memory, the agent tools installed on it and the local models it holds. One machine acts as the coordinator and hands out work to the machine that fits.

Local models

Local models run through Ollama or llama.cpp on your own hardware. GPU memory decides which model fits where, so a large model lands on the server and a small one can run on a laptop. Local work never leaves the machine it runs on.

Secure relay

Machines reach each other over SSH or an encrypted relay. Each machine dials out, so a box behind a home router does not need an open inbound port. The relay carries fleet traffic between your machines; it is not where your work is stored.

Sessions: pause, resume, fork

A session is an agent process, its worktree and its transcript. Pause stops the process and keeps the worktree. Resume starts it again from the transcript. Fork copies the worktree to a new branch and starts a second agent from the same point, so you can try two approaches side by side.

Git worktree isolation

Every agent works in its own git worktree on its own branch. No two agents write to the same checkout, and nothing reaches your main branch until the verifier approves it. Merges happen one at a time.

Rate-limit coordination

Agents that share one API key or one vendor login share one budget. The coordinator tracks that budget across the fleet and spreads requests out, so a rate-limit error makes the fleet back off together instead of every agent retrying at once. If you allow it, queued work can move to another vendor or a local model.

Keep reading

See how the verification engine reviews each change, and estimate what routing tasks by difficulty could save.

Questions

Which agents can run in the fleet?

Any command-line agent runs at the process level, including Claude Code, Codex CLI, Gemini CLI, Aider and OpenCode. Agents that speak MCP or ACP also get deeper control: state, handoff and approvals.

How do subscriptions work across machines?

A subscription runs through the vendor's own tool, on your machine, under your login, as the vendor allows. OmniConflux does not pool personal accounts or share one seat across many cloud agents.

Do agents share context across vendors?

They share work through git and files. We do not claim lossless context transfer between vendors; each agent reads the repository state it is given.

What about a managed fleet?

Self-serve is the default. If you want us to run machines for you, talk to us. A managed fleet runs on your API keys or enterprise tokens, never on personal subscription seats.