01
Agents read. But they’re not in the room.
Every decision worth knowing was said before it was written. Most were never written at all. Agents that only read are working from yesterday.
This is Yggy.
What if your agents had all the context?
Give real-world context from meetings, calls and rooms to the enterprise agents you’re building. Ship in 5 minutes.
$ npx aefer init
import { Aefer } from "@aefer/sdk";
const aefer = new Aefer();
// send the _æfer bot to a Zoom, Meet or Teams link
const bot = await aefer.bots.join({
url: "https://meet.google.com/kbr-qwtd-zpa",
name: "Harbor Notetaker",
announce: true,
});
$ npx aefer desktop link
// the _æfer desktop app: meetings, calls, screen
// and ambient audio
await aefer.desktop.capture({
user: "ana@acme.com",
meetings: true,
calls: true,
screen: true,
ambient: true,
consent: 'everyone-told',
});
$ npx aefer mobile link
// phone calls and in-person talks, from the app
await aefer.mobile.capture({
user: "laia@acme.com",
sources: ["phone", "in-person"],
consent: 'everyone-told',
});
aefer.on("meeting.finished", (m) =>
agent.remember(m.transcript));
$ npx aefer rooms pair
// a small _æfer device on the meeting-room table
const room = await aefer.rooms.register({
name: "Room 3B",
deviceCode: "AEF-4821",
light: "on-while-listening",
});
aefer.on("meeting.finished", (m) =>
agent.remember(m.transcript));
$ npx aefer sources add notetaker
// bring in the notetaker a team already uses
await aefer.sources.add({
type: "notetaker",
user: "ana@acme.com",
rules: "company", // your rules apply
});
aefer.on("note.imported", (n) =>
agent.remember(n.text));
02
Yggy loves privacy.
Yggy is _æfer’s ears. It listens only where your company and each person allow it.
Your context. Your rules.
Your agents get the work. Nobody gets watched.
Laia’s Tuesday
Product reviewkept
Call with Acmekept
Pricing doc, with her agentkept
work filter
Call with her mumleft out
Direct message to Joannever read
Booking a dentistleft out
| _æfer always | _æfer never |
|---|---|
| Sticks to meetings and workA work filter keeps personal moments out. | Reads private chats or direct messages |
| Tells everyone in the call that notes are on | Listens in the background without people knowing |
| Lets each person say no, pause, review or remove what they share | Keeps what someone asked it not to keep |
| Keeps user rules on, whatever the admin sets | Lets anyone switch them offNot an admin, not a manager. |
| Follows your company’s rules for who is recorded, who sees it and where it’s storedThe most specific rule wins. | Shares with anyone your rules leave out |
03
Accuracy = autonomy
Agents only act on their own when they can trust what they read. One wrong name, and disaster follows.
04
For the teams deploying AI at work.
You’re building agents for a company – yours or a client’s. _æfer gives them what was said there, through one API, so you can spend your time on the agent.
Stupid simple to install.
- 010:00Paste
One prompt into your coding agent.
- 020:12Wire
It reads the docs and writes the code.
- 033:52Approve
You say yes to the key.
- 044:51Done
_æfer is in your product.
Context infrastructure for enterprise agents.
Capture the meetings, calls and rooms your rules allow, so agents can act on them. Ship in 5 minutes.