Skip to main content
This walkthrough takes you from a clean machine to two first wins: a bot capturing a live meeting transcript, and an agent answering from your workspace. You’ll self-host the whole stack with one command.

​
Prerequisites

  • A Linux host (Ubuntu 24.04 recommended), git, and Docker.
  • A transcription (STT) token — get one free at vexa.ai/account, or self-host transcription on a GPU. Without it, bots join and record but produce no transcript.

​
1. Install and start

curl -fsSL https://get.docker.com | sh
git clone https://github.com/Vexa-ai/vexa-core.git && cd vexa-core
make all          # full Docker Compose stack — seeds .env, builds, and prints your API key
make bot          # build the meeting bot from source — needed before a bot can join (§2′)
make all brings up the whole stack and prints an API key + your URLs when it finishes: 
  Vexa is up.
    Terminal UI : http://localhost:13000
    API gateway : http://localhost:18056
    API key     : vxa_…
SurfaceURL
Terminal (web workbench UI)http://localhost:13000
API gatewayhttp://localhost:18056
make all seeds .env from .env.example on first run and mints a self-host API key for you (via deploy/compose/bin/provision-token). To add transcription (STT) and an LLM provider, fill the credentials block in .env. To mint additional scoped keys yourself, see Authentication.

​
2. First win — capture a meeting (UI)

1

Open the terminal

Go to http://localhost:13000. You’re already signed in to a self-host account.
2

Send a bot to a meeting

Start a Google Meet, Zoom, or Teams call, copy the join URL, and add it from the UI. A bot joins the call as a participant — no plugin, no host setup.
3

Watch the transcript stream

Speak. Speaker-attributed segments appear live, draft-then-confirmed, as the meeting runs.

​
2′. Same thing over the API

Use the key make all printed, then send a bot and read the transcript: 
# the key make all printed (or: make -s provision-token ADMIN_TOKEN=<your ADMIN_TOKEN>)
export API_KEY=vxa_...
export API_BASE=http://localhost:18056

# send a bot — native_meeting_id is the id from the join URL (e.g. abc-defg-hij)
curl -X POST "$API_BASE/bots" \
  -H "X-API-Key: $API_KEY" -H "Content-Type: application/json" \
  -d '{"platform":"google_meet","native_meeting_id":"abc-defg-hij","bot_name":"Vexa"}'

# read the transcript (poll while the meeting runs)
curl -H "X-API-Key: $API_KEY" \
  "$API_BASE/transcripts/google_meet/abc-defg-hij"
Full surface — translation, WebSocket streaming, recordings, stopping the bot — in the Meetings API.

​
3. Second win — ask your workspace a question

Every captured meeting compiles into your workspace — a Markdown knowledge base an agent reads and writes like a developer in a repo. Chat with it: 
curl -N -X POST "$API_BASE/agent/chat" \
  -H "X-API-Key: $API_KEY" -H "Content-Type: application/json" \
  -d '{"prompt":"What did we decide in my last meeting?"}'
The response streams back as Server-Sent Events — message-delta frames carry the reply, commit frames mark anything the agent recorded. See the Agent API.

​
Next steps

Get a report after every meeting

A routine that writes notes, decisions, and follow-ups when a call ends.

Brief me every morning

An unattended agent on a cron schedule.

Authentication

Mint, scope, and rotate API keys for the full stack.

Deploy to production

Docker Compose self-host, configuration, and air-gapped transcription.