Automatic Capacity management

Recover your AI credits before they expire on schedule. Guaranteed.

Copilot, Claude Code, Cursor, and Codex are bought side by side and wasted side by side. Spillway Ops routes the unused allocation to the developers who need it.

Drop your email for early access notice and product updates in between.

fig. 1 — credit spillway, one billing cycle ■ recovered
  1. 01

    Capture unused capacity

    Unused allocation flows into a shared, short-lived overflow pool before expiration.

  2. 02

    Automatic refills

    Spillway flow is redistributed automatically as people approach their vendor limit by a configurable policy engine.

  3. 03

    Fair, not flat

    Only measured, unused volume feeds the pool. Per-user draws are capped, and baselines can differ by role so heavy-need engineers get headroom.

Connections

Every connection reads usage metadata and sets per-user limits through the vendor's own admin API. No repo access, no prompt contents, no code.

  • GitHub Copilot

    Connected in early access

  • Claude Code

    In development

  • Cursor

    Planned

  • OpenAI Codex

    Planned

Field data

32.3%

of GitHub licenses sit unused — Zylo research

$29 → $750

per dev/mo after June’s pooled-credit change — reported case

28 days

is all GitHub’s usage dashboard shows — GitHub docs

Questions, answered

How does it work?

Reads usage metadata and sets per-user limits through vendor admin APIs — no repo access, no prompt contents, no code.

Which tools does it cover?

GitHub Copilot, Claude Code, Cursor, and OpenAI Codex, each at its own stage. We are looking for design partners to accelerate the implementation for all of these options.

Can someone hoard the overflow pool?

No. The pool is short-lived by design and per-user draw is capped. It’s a buffer, not a second budget.

How do refills actually happen?

Automatically, as people approach their cap. Small draws are frictionless and larger ones go through a visible request board.

Why not just set per-user budgets?

You can, and GitHub’s budgets are worth setting. A cap decides when a developer stops, not who has headroom, so blocked engineers and forfeited credits happen in the same month. We wrote up what each control does and where it stops .

Reading

Long-form notes on how each vendor meters, caps and forfeits credits, and what an administrator can do about it.

Copilot · Billing GitHub Copilot premium requests and AI credits, explained What changed on September 1, 2026, and what to check before the October invoice. Copilot · Budget GitHub Copilot budget controls: working with per-user caps How each control works, how far it reaches, and what a cap actually moves. Claude Code · Billing Claude Code usage limits and credits on Team and Enterprise plans, explained How the session and weekly limits work, and what changed on September 14, 2026. Claude Code · Budget Claude Code spend limits: working with per-member caps The seat allowance, usage credits, spend limits and the Enterprise APIs, one at a time. Cursor · Billing Cursor usage limits, included usage and on-demand pricing on Teams and Enterprise, explained The two included pools, on-demand at list prices, the Token Rate, and what changed on June 1, 2026. Codex · Billing OpenAI Codex usage limits, credits and plans on Business and Enterprise, explained The five-hour and weekly windows, workspace credits per million tokens, and what changed on April 2 and August 24, 2026.

The clock is ticking

Unused credits expire at the end of every cycle. Yours are expiring right now.

Be first to know when early access opens. We will also send an occasional product update.