Skip to main content
Open-source meeting bots and real-time transcription — cloud or fully self-hosted.
A bot joins Google Meet, Zoom or Teams; you get the transcript live over the API. Apache-2.0 all the way down. (Jitsi: join + capture offline-proven, live validation pending — #883.)
These docs cover Vexa 0.12. Hosted vexa.ai runs the 0.12 meeting and transcription experience. The agent plane is currently self-hosted only — self-host Vexa to run the full stack.
When transcripts alone stop being enough, the same stack grows into meeting intelligence — we build it with the teams who run it.

​
Why

Knowledge as code

Meetings and docs become Markdown in a versioned workspace.

Meetings: rich but uncaptured

The richest context in any org, captured before it’s lost.

CLI agents proved the pattern

Claude Code’s proven pattern, made safe and scalable.

​
Two domains, together or apart

Meetings and agents are separate domains, each with its own API — run either on its own, or compose them.

Meetings

Plan, capture, and share meetings — calendar sync, auto-joining bots, real-time transcripts from Google Meet, Zoom, and Teams (plus Jitsi, live validation pending). Usable standalone as a meeting API.

Agents

Sandboxed, scalable agents over your workspace. Put them to work on any knowledge — with or without meetings.

​
Explore

Quickstart

Self-host the full stack with one make all. Up in minutes on a single Linux host.

Concepts

The primitives everything composes from — workspace, meeting, agent, container, identity, scheduler.

API reference

Dispatch agents, stream meetings, manage routines over HTTP.

Architecture

How dispatch, execution, streaming, and trust actually work.

​
What it does

  • Captures meetings natively — real-time transcripts from Google Meet, Zoom, and Teams, no plugins or recorders. Whisper included. Jitsi joins and captures (offline-proven), but live transcript validation is still pending — #883.
  • Meets you at your calendar — connect a secret ICS address and upcoming meetings import automatically; the bot auto-joins each one at start. Plan a meeting ahead and share its prep workspace with the people you’re meeting.
  • Turns knowledge into code — meetings and emails become a living, Markdown workspace that agents treat as their working directory.
  • Runs agents safely — every agent executes in an isolated, ephemeral container: no egress except through brokered tools, thousands in parallel, no lateral movement.
  • Cloud-native deployment — self-host the whole stack with Docker Compose on a single Linux host.
  • Stays in your environment — open-source, self-hostable, and able to run with no egress via bring-your-own inference and a bundled STT unit. Recordings and agent state never leave infrastructure you control.

​
Try it

The API comes up at http://localhost:18056 (gateway) and the terminal web workbench at http://localhost:13000. Full options — no egress, bring-your-own inference — in Deployment. Prefer to look before you build? Hosted vexa.ai runs Vexa 0.12 for meeting bots and transcription today — agents aren’t part of the hosted service yet. These docs describe the full 0.12 stack, agents included, that you self-host above. Don’t have a key yet? Hosted: sign in at vexa.ai/signin with a Google account and copy your key from your account page — free credit, no card required. Self-hosted: make all prints a key when the stack comes up.

​
Why Vexa

AI reshaped software development: a CLI agent on a Linux box is now enough to build software. Vexa scales that same execution model to knowledge work — meetings and emails as the source, agents as the workers, your infrastructure as the sandbox. And the codebase itself is built for that world. Every service is a modular monolith: a module owns exactly one concern and is the single source of truth for it; modules join only through sealed contracts that CI refuses to let drift; every unit ships its code, its adversarial tests, and the goldens that validate it — with fixtures collected from real meetings. That is what makes the system tractable for human contributors and for AI agents working on it — debug any module in isolation, or any chain of modules at the scale a bug lives at. The map: Modules & Seams.

Knowledge agent

Meeting copilot

AI routines

Knowledge chat

Integrations

Enterprise