> Arbiter
● Working alpha · Release preparation

Orchestrate every agent, terminal, and job. Know what the reboot interrupted.

Arbiter is the OS-level orchestration brain that sits above your LLM clients and beside your tools. It dispatches and supervises your agents, terminals, and long-running jobs. It applies configured routing and scheduling policy, then preserves a clear record of work interrupted by a crash or power cut.

Agnostic by design. Bring configured clients and supported providers, or none at all. Public binary release preparation is underway.

arbiter: session
 $ arbiter run "refactor the auth module" --client claude-code --worktree
run f3a1  queued
  run f3a1 routed → configured tier (policy selected)
run f3a1 deferred → off-peak window (acct-2 quota in 34m) ...
run f3a1 running worker 48211 · managed worktree
-- power cut · machine reboots -- $ arbiter hydrate
  run f3a1 suspended state preserved, operator action required
[ok] 1 interrupted run accounted for, 0 lost

Illustrative. Arbiter is a working alpha; recovery behavior depends on job safety.

The problem

AI work has become a sprawl, and no layer owns it.

LLM clients run one session well, but they don't orchestrate many across processes, machines, accounts, and time. Memory tools remember and code tools verify, but neither dispatches. The orchestration layer is simply missing, so today it's run by hand.

Too many windows

Many clients, each good at one session: Claude Code, Codex, Gemini, Cursor, Windsurf. Running ten of them means ten terminals and a mental map you have to hold yourself.

Too many accounts

Every provider has its own quotas and peak-hour throttling. Keeping work on whichever account still has headroom is a babysitting job nobody should have.

No crash recovery

Long jobs sprawl across terminals, branches, and machines. The moment the power blinks or you reboot, the in-flight work is gone and the day with it.

What Arbiter does

A local-first command center for supervised AI work.

Arbiter is the muscle and the dispatcher. It never runs the coding turns itself. It dispatches the clients that do, and owns everything around them: routing, accounts, scheduling, processes, and durable run accounting.

01

Dispatch & supervise

One command center for terminals, processes, git worktrees, work-groups, and sub-jobs, across Windows and modern Linux. Everything you launch, in one place to see and steer.

02

Cost-aware routing

Apply configured capability, cost, and safety rules to routing decisions. The learned optimization layer is still being hardened for release.

03

Schedule around throttling

Schedule configured work around availability windows and account constraints. Exact provider behavior depends on the clients and accounts you connect.

04

Drive it from anywhere

Use configured local and remote control surfaces, including supported messaging adapters, an HTTP control plane, editors, and MCP clients. Availability depends on your setup.

05

Survive the crash

A crash or reboot leaves an accounted record of interrupted work. Safe read and inference jobs may be retried; side-effecting work stays suspended for review.

06

Hold your accounts

Configured credential pools and scheduling policy help select available routes. Treat account rotation behavior as setup-dependent during alpha.

Watch it run

Eight minutes of the real thing.

No slideshow, no mockups. This is a running alpha daemon on a real machine: configured routing, live runs, approvals, and the local brain assisting the operation.

Silent screen capture, 8:02. Prefer YouTube? Watch it there.

The headline

It keeps an outage from becoming a mystery.

The thing that ends most long AI sessions is not a bug. It's an outage: a reboot, a dropped connection, a blink in the power, and a day of in-flight work evaporates because nothing was holding it.

Arbiter holds the durable record. After a restart, arbiter hydrate accounts for interrupted jobs, preserves their state, and marks them suspended for deliberate operator recovery. Safe read and inference jobs may be retried; side-effecting work stays held until an operator chooses what happens next.

  • Records interrupted work after reboots, crashes, and power loss
  • Preserves run state and work artifacts for review
  • Gives each interrupted run a known state
after a reboot
 $ arbiter status
3 runs were interrupted by an unclean shutdown.
$ arbiter hydrate
  run f3a1 suspended state preserved
  run 9c0e retried safe read task restarted
  run b27d suspended needs approval to retry
[ok] 1 safe retry · 2 held for review

Illustrative output.

Model routing

Make routing policy explicit.

Different jobs call for different capability and cost tradeoffs. Arbiter gives you a place to configure those choices, inspect routes, and keep safety policy in the decision path.

Configured routing policy

Set capability, cost, and safety policy for the jobs you dispatch. Arbiter records the route it selects.

Cost-aware by design

The routing layer is designed to weigh cost alongside capability. Its learned optimization remains under hardening during alpha.

Rules stay visible

Routing decisions are recorded, and configured safety rules can constrain which routes are allowed for sensitive work.

Agnostic by design

Plug in anything. Depend on nothing.

Arbiter is built to run with zero providers and zero sibling tools, and to get sharper as you add them. Swap any client or provider out and it still runs. If it only had value when you ran the whole stack, it would have failed its own test.

Arbiter

The orchestration brain

Dispatches, routes, schedules, and records the state of work it supervises. This app.

Your LLM clients

Dispatch targets

Claude Code, Codex, Gemini, Cursor, Windsurf, or your own. Bring any, or none.

Your providers

Accounts & quota

Configured accounts can be selected with routing and scheduling policy in mind.

Your tools

Optional delegates

Memory and code-analysis tools plug in when present, and are never required.

Standalone-first. Integrations are additive, never load-bearing. Arbiter is the dispatcher above them all, not a member of the set.

Where this is going

The things you'll be able to hand off.

One instruction, and Arbiter handles the dispatching, the accounts, the timing, and the recovery underneath it. These are the north-star behaviors the whole system is built toward.

Run this across off-peak hours on whichever account still has quota.
Spin up 10 workers on this monorepo, each on its own git worktree; recover them if I reboot.
Text me on Signal when the suite goes green, and let me stop any run from my phone.
Index the repo, warm it with the project's standards, then dispatch the fix to whichever client I prefer today.

The ecosystem

Better alone. Unfair together.

Five focused tools for shipping with AI agents. Each stands on its own; together they cover code, action, orchestration, memory, and proof.

● Working alpha · Release preparation

A working alpha is entering release preparation.

Arbiter is now in IP hardening, licensing, and public binary packaging preparation. The source remains private. Follow the engineering journal and the public release channel for verified progress and availability.

No signup funnel. Product status stays public through the journal and release channel.