FROM

airmemo

TO

you

RE

how the queue works

TRACE

6fb461c

QUEUED

Memo queued: from airmemo to you, re how the queue works, trace 6fb461c. Not yet receipted.

QUEUED

The problem is the same on the shop floor. The foreman posts the new drawing on the wall; the part already in the press finishes to the old spec. Nobody grabs a machine mid-cycle, and nobody expects the new drawing to take effect until the press stops. Agents are different. Or they shouldn't be. Today, whatever is already in a session reads as current, and every agent acts on it that way. Nobody governs the shelf.

The evidence is measured, not anecdotal. In the Meetless stale-context study, 10 frontier models were given a task whose answers had been superseded by dated notes on disk. 0 of 6 got it right, and they were confidently wrong: shipping stale facts while reading zero files. Our own Meetless-style benchmark reproduces the effect on a local model: 1/6 reading the shelf as it is, 4/6 when the in-force memo is pushed into context. The best agent with stale context loses to a mediocre agent with current context.

The inversion

Every tool makes agents smarter. Nobody makes them not wrong. That's the gap we're closing: not a smarter agent, a better-informed one.

AirMemo is a shelf, not a memory. A small hook rides the lifecycle events your agents already expose (session start and prompt submit) and checks one thing: does the shelf hold an authorized memo for this agent? If it does, the memo is delivered into the agent's session context and is prompt-visible on the next turn. It never touches retrieval, RAG, or memory stores, and it never interrupts mid-conversation. Delivery is next turn, guaranteed, with an honest state machine:

queued → injected → receipted → expired

The librarian decides what goes on the shelf: who may push, to which scopes, at what priority, and marks each memo with the value that wins when it conflicts with an older one. "The 2/15 memo supersedes the 2/14 memo; the winning value: PR #4821 ships." Complete, in-force, precedence-resolved: the render contract that makes a multi-book shelf actable, not a pile.

Multi-vendor by design

No enterprise fleet is single-vendor, so AirMemo isn't either. Seven adapters, one delivery contract. The hedge is a fixture, not a promise.

Windsurf rides a different rail: Cascade hooks consume only the exit code, so its delivery is MCP pull: the installer wires the server, and the memo still lands with a receipt.

OpenCode rides a different rail too: there is no command hook, so its delivery is a JS shim: the installer drops a plugin that pushes the memo into the request at prompt admission, and the memo still lands with a receipt.

URGENT: PR #4821 ships today: freeze lifted 18:00 UTC

The 2/14 freeze memo is superseded. The deploy window opens 18:00 UTC and closes 20:00 UTC.

- Ship PR #4821 (context-freshness KPI), the release gate for this window
- Do NOT ship PR #4824 (still blocked on design review)
- If the window slips, the new freeze memo lands before 17:45 UTC

On-call: u_priya. Escalate to #incident if the window closes without a ship.

[AIRMEMO · authorized · memo_4821]

{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"URGENT: PR #4821 ships today: freeze lifted 18:00 UTC\n\nThe 2/14 freeze memo is superseded. The deploy window opens 18:00 UTC and closes 20:00 UTC.\n\n- Ship PR #4821 (context-freshness KPI), the release gate for this window\n- Do NOT ship PR #4824 (still blocked on design review)\n- If the window slips, the new freeze memo lands before 17:45 UTC\n\nOn-call: u_priya. Escalate to #incident if the window closes without a ship.\n\n[AIRMEMO · authorized · memo_4821]"}}

{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"URGENT: PR #4821 ships today: freeze lifted 18:00 UTC\n\nThe 2/14 freeze memo is superseded. The deploy window opens 18:00 UTC and closes 20:00 UTC.\n\n- Ship PR #4821 (context-freshness KPI), the release gate for this window\n- Do NOT ship PR #4824 (still blocked on design review)\n- If the window slips, the new freeze memo lands before 17:45 UTC\n\nOn-call: u_priya. Escalate to #incident if the window closes without a ship.\n\n[AIRMEMO · authorized · memo_4821]"}}

{"additionalContext":"URGENT: PR #4821 ships today: freeze lifted 18:00 UTC\n\nThe 2/14 freeze memo is superseded. The deploy window opens 18:00 UTC and closes 20:00 UTC.\n\n- Ship PR #4821 (context-freshness KPI), the release gate for this window\n- Do NOT ship PR #4824 (still blocked on design review)\n- If the window slips, the new freeze memo lands before 17:45 UTC\n\nOn-call: u_priya. Escalate to #incident if the window closes without a ship.\n\n[AIRMEMO · authorized · memo_4821]"}

{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"URGENT: PR #4821 ships today: freeze lifted 18:00 UTC\n\nThe 2/14 freeze memo is superseded. The deploy window opens 18:00 UTC and closes 20:00 UTC.\n\n- Ship PR #4821 (context-freshness KPI), the release gate for this window\n- Do NOT ship PR #4824 (still blocked on design review)\n- If the window slips, the new freeze memo lands before 17:45 UTC\n\nOn-call: u_priya. Escalate to #incident if the window closes without a ship.\n\n[AIRMEMO · authorized · memo_4821]"}}

{"additional_context":"URGENT: PR #4821 ships today: freeze lifted 18:00 UTC\n\nThe 2/14 freeze memo is superseded. The deploy window opens 18:00 UTC and closes 20:00 UTC.\n\n- Ship PR #4821 (context-freshness KPI), the release gate for this window\n- Do NOT ship PR #4824 (still blocked on design review)\n- If the window slips, the new freeze memo lands before 17:45 UTC\n\nOn-call: u_priya. Escalate to #incident if the window closes without a ship.\n\n[AIRMEMO · authorized · memo_4821]"}

The five documents above are generated from the five command-hook adapters (hook/platforms/claude.go, codex.go, copilot.go, gemini.go, cursor.go; Windsurf and OpenCode deliver over MCP pull and a JS shim): the same code paths that run on every session start. make artifact re-renders them, so the demo cannot drift from the product.

Want the full picture? One memo, five vendors: side-by-side¹

Every delivery writes a receipt: an append-only record of what was delivered, to which agent, on which platform, and when it expired. The receipt is three things at once:

• Audit evidence: what each agent saw, for compliance and post-incident review
• Billing meter: the honest count of governed deliveries
• The acquisition metric: agents under management, a first-class product number from day one

Delivered memos are visibly stamped as authorized ([AIRMEMO · authorized · memo_4821]), so agents and reviewers can always tell the shelf from graffiti.

Every number below is one SQL count on the live control-plane database, read right now, no mockups, no roadmap. Receipts are append-only, so the receipted count can only go up.

The ticker reads the public /public/fleet.json endpoint: counts only, never memo contents, no tracking scripts. Stale on your screen? Then the control plane is down, and that is exactly the moment the shelf earns its keep.

Priced per agent seat, governed by the control plane. Variable cost per seat is pennies; the value is the governance.

Self-host runs 1.5–2× the applicable net rate. The same codebase, one image, deployed where your fleet lives. Every anchor sits above us: Claude Code Team runs ~$100/seat, Copilot $10–39, Codex $20–200. A $9–29 governance layer is the easy add-on in the same procurement conversation.

• Write and send memos: author a memo, set scopes and priority, choose which fleets get it.
• Approve before it lands: an org-wide broadcast requires a second pair of hands; the approval queue is where that happens.
• Roll out on your schedule: time a memo for a window, watch it go from queued to injected to receipted, fleet by fleet.
• Pull it back: revoke or expire a memo from the memo ledger; the audit trail keeps both records.
• Learn from rework: every correction your people had to make is captured as evidence: what failed, why, and how often.
• See everything on the record: who signed, which devices, what every agent saw, drill-down from memo to receipts to devices.

Nothing on this list is a mockup or a plan; every surface is live in the product today. Self-hosted installs run the same console from the same image.

AirMemo is the layer that decides who gets to put books in the library: who may push, to which scopes, at what priority, under whose approval, and it records every placement in an append-only receipt trail. The delivery discipline never varies: never a book slipped mid-paragraph, placed on the desk, seen at next natural look-up. Nothing interrupts a session; everything is provable.

That is what compliance runs on. Not on trusting agents to read carefully, but on receipts: what each agent saw, when it saw it, and who authorized it. For auditors that is evidence; for operators it is the difference between a fleet quietly acting on yesterday and a fleet acting on the in-force plan.