Daily Edition Sources +4

The Company Can Host the Agent. The AI Account Can Still Be Yours.

QM is separating the place an agent is operated from the account that pays for and authorizes one person’s model turn—while deliberately leaving background work on organization credentials.

Photocopied marker diagram showing a human turn flowing through a personal AI account into a company-hosted agent, while an automation lane remains connected to organization credentials.
Diagram Punkhosting the agent and choosing the model account are separate decisions.
repo yc-software/qm evidence
4 source signals 1 repo commit 23e5373
Evidence: commit 23e5373 / August 31, 2026 / Daily Edition
Open Edition Evidence below

On yc-software/qm, a public commit adds individual model authorization. When an organization enables it, a human must connect a Claude, ChatGPT, or API-key account before chatting; the human turn then routes through that connection rather than the organization’s shared model credential.

That is more than a model picker. It separates two things agent software often collapses: the company may host the service and operating controls, while the person at the keyboard supplies the account that drives a model turn. For teams balancing subscriptions, reimbursement, auditability, and shared API budgets, that is an operating choice—not a cosmetic preference.

The account chooses a path, not just a label

The inspected routing module does not treat all connections alike. Anthropic OAuth selects the Claude harness; OpenAI OAuth normally selects a Codex harness, with a Pi organization able to keep its own harness while using the subscription provider; a pasted API key follows the Pi route for the named provider. In other words, the account connection can determine the harness and model path, not merely decorate an organization-owned default.

QM also tries to make the custody boundary structural. Its public tests create credentials by user and provider, retrieve only derived OAuth material for a turn, and check that a Codex child auth file carries an access token and account identifier without the refresh token. That is a stronger design than swapping one shared credential file before each request and hoping concurrent turns put it back correctly. It is still host-managed custody: the service’s keychain owns encryption and refresh, so no reader should translate this code into a promise that the organization never holds sensitive material.

Not every task gets a personal bill

The important correction arrives in the orchestrator gate. The individual path runs only when the origin is a human turn and the organization toggle is enabled. If no connected account resolves, the turn is refused with a connection prompt rather than silently borrowing the organization credential. But automation and ambient work are not put through that branch. A scheduled report, cron-triggered job, or other background action remains a separate organization-level policy question.

That distinction is the story’s useful consequence. A company can let a person bring a subscription account to an interactive agent without pretending that every task, retry, monitor, or scheduled action has become personal. The public receipts are main-branch code and focused tests, not release or deployment evidence. The next signal worth watching is a public operational guide that tells administrators how the personal-account boundary appears in logs, billing, retention, and a failed or retried background task.

Evidence Trail

Receipts below the story

The article above is the public narrative. This section keeps the source trail and limits on the same page.

Edition
DateAugust 31, 2026
LaneDaily Edition
Confidence78%
Sources4
Reposyc-software/qm

Primary Evidence

Evidence Limits

  • These are public source and test receipts from a merged main-branch change. They do not establish release availability, a production deployment, provider terms, employer policy, or end-to-end behavior for every OAuth failure and background task.
  • The sources show a per-person credential route for human turns, not a claim that QM is a zero-knowledge host or that scheduled and ambient automation use the same route.
Letters & Corrections

Send a note to the desk

Corrections, missing context, or a follow-up lead.