Agentcall Agent Skill

join-meeting

Let any AI agent join and participate in video meetings via voice.

An AgentCall skill that enables AI coding agents (Claude Code, Cursor, Codex, Gemini CLI, OpenClaw, Windsurf, Junie, and 30+ more) to join Google Meet, Zoom, and Microsoft Teams as a bot with voice conversation, visual avatar, screenshare, and real-time transcription.

What It Does

Your AI agent joins a meeting as a participant and can:

• Talk — respond via text-to-speech (54 voices, 9 languages, <1s latency)
• Listen — receive real-time transcripts of what participants say
• See — take screenshots of shared screens, slides, presentations
• Show — display an animated avatar as the bot's camera feed
• Present — screenshare URLs, dashboards, slides dynamically during the call
• Chat — send and receive meeting chat messages
• Collaborate — use GetSun voice intelligence for natural multi-party conversations
• Realtime — the bot's own voice answers by itself within about a second, in many languages, and hands you anything it can't do (look-ups in your systems, chat posts, research, tasks)

The agent keeps its full session context — it can search code, edit files, run commands, and commit changes while talking in the meeting. The meeting is just another I/O channel.

Quick Start

Prerequisites

This is a skill, not a standalone app — it runs on top of a coding agent. You'll need:

1. A coding agent — one of:
   • Claude Code (Anthropic)
   • OpenClaw
   • Cursor 2.5+
   • OpenAI Codex CLI
   • Gemini CLI
   • Windsurf (Cascade)
   • GitHub Copilot (JetBrains / VS Code)
   • Junie
2. Python 3.10+ or Node.js 18+
3. Dependencies: pip install aiohttp websockets (Python) or npm install ws (Node.js)
4. An AgentCall account — free, and the agent can create it for you. On first run with no key, the skill registers you via a one-time email code (or paste an existing key from https://app.agentcall.dev/api-keys). New accounts include free trial credits.

Install

Pick your agent. For anything not listed, see From GitHub (any agent).

Claude Code

/plugin marketplace add pattern-ai-labs/agentcall
/plugin install join-meeting@agentcall

OpenClaw

openclaw skills install join-meeting

Cursor 2.5+

Use /add-plugin in the editor, or browse cursor.com/marketplace.

OpenAI Codex CLI

Drop the skill into ~/.codex/skills/, or run $skill-installer from your Codex session. (SKILL.md is read directly.)

Gemini CLI

gemini extensions install https://github.com/pattern-ai-labs/agentcall

(Run from your terminal, not from inside the interactive CLI.)

From GitHub (any agent)

git clone https://github.com/pattern-ai-labs/agentcall.git

Then point your agent at agentcall/SKILL.md (the open Agent Skills standard, supported by 30+ frameworks):

• Windsurf — drop folder into .windsurf/skills/
• GitHub Copilot (JetBrains) — reference from ~/.copilot/agents/*.agent.md
• Junie — npx skills add pattern-ai-labs/agentcall --agent junie
• Claude Code (single-session, no install) — drop folder into .claude/skills/

See it in action

Join a Meeting

Tell your agent: "Join this meeting: https://meet.google.com/abc-def-ghi"

Modes

Mode	What the bot has	Use case
audio	Voice only	Simplest — voice conversations, note-taking
webpage-av	Voice + animated avatar	Visual presence in meetings
webpage-av-screenshare	Voice + avatar + screenshare	Presentations, sharing content

Voice Strategies

Strategy	How it works	Best for
direct	Agent controls TTS directly	1-on-1 conversations, customer support
collaborative	GetSun voice intelligence handles timing	Group meetings, natural conversation flow
realtime	The bot's own voice listens and answers by itself; it asks the agent (agent.request) for facts, tools and tasks	Meetings with people — fastest, most natural replies, multilingual; up to 10,000 characters of context (facts, tone, what to hand to the agent). Keep the default voice for the best performance

Features

• VAD gap buffering — combines fragmented transcripts into complete utterances
• Barge-in prevention — waits for silence before speaking
• Auto-interruption — detects when someone talks over the bot (webpage modes)
• Sentence tracking — knows which sentence was interrupted and when
• WebSocket reconnection — auto-reconnects on network blips with call status check
• Crash recovery — reconnects to active calls after agent restart
• Fast join (reservations) — Pro / Enterprise can reserve up to 4 bots for a 15-minute window ; a reserved bot skips the machine start (reserve.*, --reservation-id)
• 7 built-in templates — pattern, orb, ring, avatar, dashboard, blank, voice-agent
• Screenshots — capture what's on screen at any time
• Chat I/O — send URLs, code, text that's hard to speak
• API key persistence — saved to ~/.agentcall/config.json, asked once

Agent Frameworks

Works with any agent that can spawn a subprocess and read stdout:

Framework	Status
Claude Code / Agent SDK	Full support (+ Stop Hook for persistent calls)
OpenAI Codex	Full support
Cursor	Full support (tmux for PTY)
Windsurf (Cascade)	Full support
Gemini CLI	Full support
JetBrains Junie	Full support
OpenClaw	Full support
GitHub Copilot	Full support
Aider	Partial (no subprocess)

Network endpoints & credentials

The skill's scripts make outbound connections to these endpoints only:

Endpoint	Used by	Purpose
https://api.agentcall.dev	scripts/*/agentcall.*, join.*, bridges	Create and end calls, read call state and transcripts
wss://api.agentcall.dev/v1/calls/{id}/ws	bridges	Live meeting events in; agent commands (speak, chat, screenshare) out
wss://api.agentcall.dev/internal/tunnel/connect	tunnel.* (webpage modes only)	Outbound tunnel that lets the meeting bot load your local UI page, which is served on 127.0.0.1 only. No inbound port is opened on your machine
https://api.agentcall.dev/v1/auth/email-otp/*	register.* (optional)	One-time email code to create an account and mint an API key
https://api.agentcall.dev/v1/reservations	reserve.* (optional)	Book, list, check and cancel bot reservations (fast join)
https://raw.githubusercontent.com/pattern-ai-labs/agentcall/main/.claude-plugin/plugin.json	check_update.* (optional)	Reads the published version string to tell you an update exists. Cached for 7 days; sends no data

https://app.agentcall.dev appears only as a link for you to create or manage keys — the scripts never call it. The API base can be overridden with the AGENTCALL_API_URL environment variable (or api_url in the config file).

Credentials: one AgentCall API key (ak_ac_…), read from the AGENTCALL_API_KEY environment variable or the api_key field of ~/.agentcall/config.json. It is sent only to api.agentcall.dev — as an Authorization header, and as an api_key query parameter on the WebSocket connection. No other credentials, environment variables, or files are read.

Local files: ~/.agentcall/config.json (API key, optional api_url; written by register.*, merging existing fields) and ~/.agentcall/update-check.json (version-check cache).

Install behaviour: no install or postinstall scripts and no downloaded binaries. scripts/run.sh uses an existing Python or Node runtime; if dependencies are missing it prints the pip install / npm install command for you to run rather than running it.

Meeting data: the bot is a visible, named participant. Meeting audio and transcripts stream through api.agentcall.dev in real time and are not permanently stored — see the Privacy Policy.

Documentation

• SKILL.md — Complete reference (modes, events, commands, patterns, Claude Code integration)
• examples/ — 8 working examples (notetakers, support agent, meeting assistants, coding companion, ElevenLabs voice)
• references/ — API reference + guides (realtime mode, collaborative mode, interruption handling, crash recovery, screenshare, reservations)

Pricing

Base plan: 6 hours of meeting time, 1 concurrent call. All features included. Paid: per-minute billing. The realtime voice is a per-minute add-on (team meetings and one-on-one calls are priced separately). See agentcall.dev/pricing for details.

License

MIT — use, modify, redistribute freely.

---

Built by AgentCall (Pattern AI Labs)