> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vexa.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Vexa

> Sandboxed AI agents that grow corporate knowledge from your meetings and docs — open-source, self-hosted, air-gappable.

<div style={{ fontSize: "2rem", fontWeight: 600, lineHeight: 1.25, margin: "0.5rem 0 1.5rem" }}>
  Sandboxed agents that grow corporate knowledge from your meetings and docs.
</div>

Real-time transcripts from Google Meet, Zoom, and Teams (Whisper included), fed to agents that build knowledge as code — fully self-hosted.

<Note>
  **These docs cover Vexa 0.12.** The hosted [vexa.ai](https://vexa.ai) runs the 0.10 line today and will be updated to 0.12 soon — to try 0.12 now, [self-host it](#try-it) below.
</Note>

Vexa tightens the loop every organization runs on: **sense → think → act**. Meetings and docs are
the data; agents turn data into signal, and signal into action that changes the world. The faster that
loop turns, the smarter the org gets.

## Why

<CardGroup cols={3}>
  <Card title="Knowledge as code" icon="file-code" href="/concepts">
    Meetings and docs become Markdown in a versioned workspace.
  </Card>

  <Card title="Meetings: rich but uncaptured" icon="microphone" href="/core/meetings">
    The richest context in any org, captured before it's lost.
  </Card>

  <Card title="CLI agents proved the pattern" icon="terminal" href="/concepts">
    Claude Code's proven pattern, made safe and scalable.
  </Card>
</CardGroup>

## Two domains, together or apart

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

<CardGroup cols={2}>
  <Card title="Meetings" icon="video" href="/core/meetings">
    Plan, capture, and share meetings — calendar sync, auto-joining bots, real-time transcripts from
    Google Meet, Zoom, and Teams. Usable standalone as a meeting API.
  </Card>

  <Card title="Agents" icon="robot" href="/core/agents">
    Sandboxed, scalable agents over your workspace. Put them to work on any knowledge — with or without
    meetings.
  </Card>
</CardGroup>

## Explore

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/deployment">
    Self-host the full stack with one `make all`. Up in minutes on a single Linux host.
  </Card>

  <Card title="Concepts" icon="cube" href="/concepts">
    The primitives everything composes from — workspace, meeting, agent, container, identity, scheduler.
  </Card>

  <Card title="API reference" icon="code" href="/api/agent">
    Dispatch agents, stream meetings, manage routines over HTTP.
  </Card>

  <Card title="Architecture" icon="sitemap" href="/architecture/execution">
    How dispatch, execution, streaming, and trust actually work.
  </Card>
</CardGroup>

## What it does

* **Captures meetings natively** — real-time transcripts from [Google Meet, Zoom, and Teams](/core/meetings), no plugins or recorders. **Whisper included**.
* **Meets you at your calendar** — [connect a secret ICS address](/how-to/calendar-sync) and upcoming meetings import automatically; the bot [auto-joins](/core/meetings#auto-join--scheduled-means-the-bot-comes) each one at start. [Plan a meeting](/how-to/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](/concepts#workspace) that agents treat as their working directory.
* **Runs agents safely** — every [agent](/core/agents) executes in an isolated, ephemeral [container](/concepts#container): no egress except through brokered tools, thousands in parallel, no lateral movement.
* **Cloud-native deployment** — self-host the whole stack with [Docker Compose](/deployment) on a single Linux host.
* **Stays in your environment** — open-source, self-hostable, air-gappable, with [bring-your-own inference](/deployment#air-gapped). Recordings and agent state never leave infrastructure you control.

## Try it

```bash theme={null}
git clone https://github.com/Vexa-ai/vexa.git && cd vexa
make all      # full stack via Docker Compose — seeds .env, brings everything up, prints your API key + URLs
make bot      # build the meeting bot from source — needed before a bot can join a meeting
```

The API comes up at `http://localhost:18056` (gateway) and the terminal web
workbench at `http://localhost:13000`. Full options — air-gapped, bring-your-own
inference — in [Deployment](/deployment).

**Prefer to look before you build?** Hosted [vexa.ai](https://vexa.ai) runs the 0.10 line today; it moves to 0.12 soon. These docs describe the 0.12 stack you self-host above.

## 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.

<CardGroup cols={3}>
  <Card title="Knowledge agent" icon="brain" href="/how-to/chat-workspace" horizontal />

  <Card title="Meeting copilot" icon="video" href="/how-to/live-copilot" horizontal />

  <Card title="AI routines" icon="clock" href="/how-to/daily-brief" horizontal />

  <Card title="Knowledge chat" icon="comments" href="/how-to/chat-workspace" horizontal />

  <Card title="Integrations" icon="plug" href="/how-to/email-triage" horizontal />

  <Card title="Enterprise" icon="building" href="/how-to/workspace-files" horizontal />
</CardGroup>
