Metadata-Version: 2.5
Name: meetstream-agent-kit
Version: 0.3.0
Summary: Bring your own agent into your meetings: Claude Code, Codex, Hermes and more answer out loud in Google Meet, Zoom and Teams through MeetStream MIA.
Project-URL: Homepage, https://meetstream.ai
Project-URL: Source, https://github.com/meetstream-ai/agent-kit
Project-URL: Issues, https://github.com/meetstream-ai/agent-kit/issues
Project-URL: Changelog, https://github.com/meetstream-ai/agent-kit/blob/main/CHANGELOG.md
Author: MeetStream
License-Expression: Apache-2.0
License-File: LICENSE
Keywords: acp,agent,claude-code,codex,mcp,meeting,meetstream,mia
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Operating System :: MacOS
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Communications :: Conferencing
Classifier: Typing :: Typed
Requires-Python: >=3.10
Description-Content-Type: text/markdown

<div align="center">

# MeetStream Agent Kit

**Bring your own agent into your meetings.**

Claude Code, Codex, Hermes, Copilot CLI and more answer out loud in Google Meet, Zoom and Microsoft Teams,<br>
with your own login, your own model and your own files.

[![PyPI](https://img.shields.io/pypi/v/meetstream-agent-kit?color=f97316)](https://pypi.org/project/meetstream-agent-kit/)
[![Python](https://img.shields.io/pypi/pyversions/meetstream-agent-kit)](https://pypi.org/project/meetstream-agent-kit/)
[![CI](https://github.com/meetstream-ai/agent-kit/actions/workflows/ci.yml/badge.svg)](https://github.com/meetstream-ai/agent-kit/actions/workflows/ci.yml)
[![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE)

<img src="https://raw.githubusercontent.com/meetstream-ai/agent-kit/main/docs/images/mia-in-a-meeting.webp" alt="A MeetStream agent answering a question out loud in a Google Meet call" width="860">

</div>

MIA, MeetStream's meeting agent, joins the call, listens, and speaks. The
**Agent Kit bridge** runs on your computer and lets **your own agent CLI** write
what MIA says. Your agent keeps its model, its prompts, its tools and your
files. MIA keeps the meeting side: joining the call, speech-to-text and voice.
MeetStream never sees your agent's login and charges no model tokens.

<picture>
  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/meetstream-ai/agent-kit/main/docs/images/agents-dark.png">
  <img src="https://raw.githubusercontent.com/meetstream-ai/agent-kit/main/docs/images/agents-light.png" alt="Works with Claude Code, Codex, Hermes, Copilot CLI, Muse Code, OpenClaw, Antigravity and any CLI, in Google Meet, Zoom and Microsoft Teams" width="100%">
</picture>

## Contents

- [How it works](#how-it-works)
- [Quick start](#quick-start)
- [Install](#install)
- [Supported agents](#supported-agents)
- [Access levels](#access-levels)
- [Activation code](#activation-code)
- [Security](#security)
- [Troubleshooting](#troubleshooting)
- [Commands](#commands)
- [Development](#development)

## How it works

```mermaid
flowchart LR
  P([People in the meeting]) <-->|voice| MIA[MIA<br/>joins the call, hears, speaks]
  MIA -->|each turn, over HTTPS| T[Your tunnel]
  T --> B[Agent Kit bridge<br/>127.0.0.1 on your computer]
  B <-->|one warm session per meeting| A[Your agent CLI<br/>Claude Code, Codex, Hermes...]
```

1. **When MIA joins a call**, the bridge starts one long-lived session of your
   agent for that meeting, so no one waits for it to start up later.
2. **When someone talks to MIA**, the words go to your agent as text. Its answer
   streams back, and MIA speaks the first sentence while your agent is still
   writing the rest.
3. **When someone interrupts**, the bridge stops your agent at once and keeps the
   conversation, so the next question still has the context.

Your agent can also use the meeting itself through MCP tools: post in the chat,
share its screen, and more, whatever your MIA agent allows.

## Quick start

You need macOS or Linux, Python 3.10 or newer, one [supported agent](#supported-agents)
installed and signed in, and a [MeetStream](https://meetstream.ai) account.

**1. Install it and run it.**

```bash
uv tool install meetstream-agent-kit
meetstream-agent-kit
```

It asks a few questions: which agent should answer (it lists the ones it finds
on your computer and checks they are signed in), the folder it works in, the
most access this computer allows, and how MeetStream reaches your computer:

- **Cloudflare quick tunnel:** no account needed. The address changes each time it starts.
- **ngrok:** needs a free ngrok account. A free static domain keeps one address.
- **An address you already have**, for example a named Cloudflare tunnel.

It then runs one short test turn with your agent and asks **Start now?** On yes,
it starts the bridge and the tunnel and prints the two things to paste:

```text
Paste these in the MeetStream dashboard:
  Pairing token  (Integrations > Models > Local agent, shown once):  msak_…
  Bridge URL     (Agents > your agent > Model > Your agent):          https://….trycloudflare.com
```

Next time, run `meetstream-agent-kit` and press Enter to start with the same answers.

**2. Save the token in MeetStream.** In the dashboard, open **Integrations > Models > Local agent**, paste the token and save it.

<picture>
  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/meetstream-ai/agent-kit/main/docs/images/dashboard-pair-dark.png">
  <img src="https://raw.githubusercontent.com/meetstream-ai/agent-kit/main/docs/images/dashboard-pair-light.png" alt="MeetStream dashboard: Integrations, Models, Local agent, with the pairing steps and the token field" width="100%">
</picture>

**3. Point your MIA agent at it.** Open the agent in the dashboard, go to
**Model**, choose **Your agent** as the provider, and paste the Bridge URL.

<picture>
  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/meetstream-ai/agent-kit/main/docs/images/dashboard-your-agent-dark.png">
  <img src="https://raw.githubusercontent.com/meetstream-ai/agent-kit/main/docs/images/dashboard-your-agent-light.png" alt="MeetStream dashboard: a MIA agent's Model tab with Your agent selected, the bridge URL, access level, activation code and Test connection" width="100%">
</picture>

**That's it.** Leave that window open. Every meeting this MIA agent
joins now talks to your agent. Not sure everything is ready? Run
`meetstream-agent-kit doctor`.

> [!TIP]
> Prefer to run the pieces yourself? `meetstream-agent-kit pair`, then
> `meetstream-agent-kit serve --agent claude --tunnel cloudflare` (or `--tunnel ngrok`,
> or no `--tunnel` and your own `cloudflared tunnel --url http://127.0.0.1:8787`).

## Install

**With [uv](https://docs.astral.sh/uv/)** (recommended):

```bash
uv tool install meetstream-agent-kit
```

Upgrade with `uv tool upgrade meetstream-agent-kit`. Or run it without
installing: put `uvx` in front of any command, for example
`uvx meetstream-agent-kit doctor`.

**With pipx**: `pipx install meetstream-agent-kit`.

**As a single file**, with nothing but Python: each
[release](https://github.com/meetstream-ai/agent-kit/releases/latest) has a
`meetstream-agent-kit.pyz`, its SHA-256 checksum and build provenance.

```bash
curl -fsSLO https://github.com/meetstream-ai/agent-kit/releases/latest/download/meetstream-agent-kit.pyz
curl -fsSLO https://github.com/meetstream-ai/agent-kit/releases/latest/download/SHA256SUMS
shasum -a 256 --check --ignore-missing SHA256SUMS
python3 meetstream-agent-kit.pyz --help
```

The bridge uses the Python standard library only. There are no dependencies to
audit, and nothing else is installed.

## Supported agents

| Agent | `--agent` | Warm session | Meeting tools | Sign in again with |
|---|---|---|---|---|
| Claude Code | `claude` | yes | yes | `claude auth login` |
| Codex CLI | `codex` | yes (`codex app-server`) | yes | `codex login` |
| Hermes Agent | `hermes` | yes (ACP) | yes | `hermes setup` |
| GitHub Copilot CLI | `copilot` | yes (ACP) | yes | `copilot login` |
| Muse Code | `muse` | yes (ACP) | yes | sign in when `muse` asks |
| OpenClaw | `openclaw` | yes (ACP) | text only | `openclaw models auth login` |
| Antigravity CLI | `agy` | yes | text only | `agy acp --login` |
| Any other CLI | `--command '...'` | one run per turn | text only | |

A warm session keeps one agent process for the whole meeting, so answers start
in about a second instead of paying the agent's start-up time on every turn.
For any other CLI, `--command 'mytool --flag {prompt}'` puts the question in
place of `{prompt}`, or on stdin when `{prompt}` is missing.

## Access levels

What your agent may do on your computer during a meeting. The levels mean the
same for every agent; the bridge maps each one to that agent's own controls.

| Level | Your agent may | Claude Code | Codex | ACP agents |
|---|---|---|---|---|
| **Read-only** (default) | read and search the work folder | Read, Grep, Glob only | read-only sandbox | permission requests denied |
| **Ask me first** (`confirm`) | act after you answer y/N in the bridge terminal; no answer in 20 s means no | asks per tool | on-request approvals | permission requests asked |
| **Full** | act without asking | edits and shell | workspace-write sandbox | permission requests allowed |

**Your computer has the final say.** `serve --max-access` sets the highest
level this computer allows. The setting in the MeetStream dashboard can lower
it for an agent, never raise it, so a leaked MeetStream key or a dashboard
change can never give anyone more access than you allowed here.

**Full** runs only when MIA guarantees that just you can talk to your agent
(the activation code below, or a verified id); otherwise it drops to
**Ask me first**. Antigravity and custom commands cannot ask before acting, so
**Ask me first** runs them read-only. A custom `--command` always has your own
permissions.

## Activation code

Turn on **Activation code** in the dashboard and your agent answers nobody
until you prove you are there. At the start of each meeting the bridge shows a
6-digit code on your computer, in the terminal and as a desktop notification.
Paste it in the meeting chat, and from then on only you can talk to your agent.

- MeetStream never sees the code before it is pasted, so nobody can claim your agent for you.
- A new code appears after 5 minutes or 3 wrong tries; 12 wrong codes lock the meeting.
- When you leave the call, your agent locks again.

## Security

- The bridge listens on 127.0.0.1 only. Your tunnel is the only way in.
- Every request from MIA needs your pairing token. The token is shown once and
  only its SHA-256 hash is stored, in `~/.config/meetstream-agent-kit`
  (mode 0600). `meetstream-agent-kit revoke <id>` makes it fail at once.
- Meeting tools are served to your agent on a separate secret for each meeting,
  which never appears on a command line.
- Everything said or typed in the meeting reaches your agent as untrusted text,
  with rules not to follow instructions from other participants.
- Tokens, secrets and request headers are never logged.

Found a problem? See [SECURITY.md](SECURITY.md).

## Troubleshooting

`meetstream-agent-kit doctor` checks this computer and prints the fix for every problem:

```text
$ meetstream-agent-kit doctor --agent claude
MeetStream Agent Kit 0.3.0 doctor
  ✓ python: Python 3.12.8
  ✓ config: /Users/you/.config/meetstream-agent-kit
  ✓ workdir: /Users/you/code/my-project
  ✓ agent: Claude Code: /Users/you/.local/bin/claude
  ✓ login: Claude Code ok
  ✓ pairing: 1 pairing(s)
  ✗ port: port 8787 is used by another program
      fix: Start the bridge with another --port (and point your tunnel at it), or free port 8787.
1 problem(s) to fix.
```

| You see | Fix |
|---|---|
| `port 8787 is used by another program` | `serve --port 8788`, and point your tunnel at that port |
| `the bridge is already running on port 8787` | use that one, or stop it first |
| `Claude Code not found` | install it (`npm install -g @anthropic-ai/claude-code`), or pass `--binary` |
| `login: expired` | run the sign-in command from [Supported agents](#supported-agents); MIA picks it up within 30 seconds |
| MIA says your agent is not reachable | check that `serve` and the tunnel are both running, and that MIA has the tunnel's current address |

## Commands

| Command | What it does |
|---|---|
| *(no command)* or `setup` | guided setup: a few questions, a test turn, then start the bridge and tunnel and print the token and Bridge URL |
| `pair [--agent NAME] [--label TEXT]` | create a pairing token (shown once) and check your agent's login |
| `list` | list pairings |
| `revoke ID` | revoke a pairing; its token stops working at once |
| `serve [options]` | run the bridge for MIA |
| `doctor [options]` | check this computer and explain each fix |
| `bench [options]` | time cold and warm turns for your agent |

`serve`, `doctor` and `bench` take `--agent`, `--command`, `--binary`,
`--workdir`, `--owner`, `--model`, `--effort` and `--timeout`. `serve` also
takes `--port`, `--max-access` (`readonly`, `confirm` or `full`), `--no-prime`,
and `--tunnel` (`cloudflare`, `ngrok`, `url` or `none`) with `--tunnel-url` for
an ngrok static domain or your own address. `MEETSTREAM_AGENT_KIT_HOME` moves the config folder. Every
command has `--help`.

The HTTP protocol between MIA and the bridge is in [docs/protocol.md](docs/protocol.md).

## Development

```bash
git clone https://github.com/meetstream-ai/agent-kit.git && cd agent-kit
uv sync                     # Python and dev tools, pinned by uv.lock
uv run pytest               # tests; a stub agent stands in, no model or login needed
uv run ruff check . && uv run ruff format --check . && uv run mypy
uv build                    # wheel and sdist in dist/
uv run python scripts/build_pyz.py   # the single-file build
```

Releases are cut from a `v*` tag: CI tests, builds, attests and publishes to
PyPI with trusted publishing (no stored token), then attaches the files to the
GitHub release.

## License

[Apache-2.0](LICENSE). MeetStream and MIA are trademarks of MeetStream. Other
product names and logos belong to their owners and are shown only to name the
agents and platforms this bridge works with.
