# AgentCall

> Your AI Agent, in every meeting.

AgentCall is an agent skill that lets any AI agent join and participate in video meetings on Google Meet, Zoom, and Microsoft Teams. The agent talks, listens, presents, screenshares, and collaborates — like a real teammate.

## What It Does

AgentCall enables AI agents to:
- Talk: speak naturally in meetings with built-in voice generation, interruption handling, and barge-in prevention
- Listen: receive real-time transcription with speaker identification
- See: take screenshots of shared screens, slides, and presentations
- Present: screenshare dashboards, slides, and demos dynamically during calls
- Chat: send and read meeting chat messages (URLs, code, links)
- Work: search code, edit files, run commands, and build — all while staying in the meeting

## How It Works

1. Install the skill in your agent framework (one command)
2. Tell your agent: "Join this meeting: https://meet.google.com/abc"
3. Your agent joins and participates — talks, listens, codes, builds, answers, and multitasks

No code needed. The agent framework (Claude Code, Cursor, Codex, etc.) reads the skill and handles everything.

## Modes

- Audio: voice only, simplest — for standups, 1-on-1s, support calls
- Avatar: voice + animated visual presence — for team meetings, customer-facing calls
- Avatar + Screenshare: voice + avatar + screenshare — for presentations, training, reviews

## Voice Strategies

- Direct: agent controls TTS directly, best for 1-on-1 conversations
- Collaborative: GetSun voice intelligence handles real-time conversation timing (trigger words, barge-in prevention, interruptions), best for group meetings

## Pricing

Billed per minute. No minimums. No subscriptions.

Base rates (per hour):
- Audio mode: $0.35/hr
- Avatar mode: $0.45/hr
- Avatar + Screenshare mode: $0.50/hr

Add-on rates (per hour, on top of base):
- Transcription (STT): $0.12/hr (base plan)
- Voice intelligence (GetSun, collaborative mode only): $1.00/hr (base plan)
- Text-to-speech (Kokoro TTS, per generated audio): $8.00/hr (base plan)

Plans:
- Base: $0.35-$0.50/hr, 6 hours included, 1 concurrent call, all features
- Pro: $0.30-$0.45/hr, 10 concurrent calls
- Enterprise: $0.25-$0.40/hr, unlimited concurrent calls

Current rates: https://agentcall.dev/#pricing

## Supported Platforms

Meeting platforms: Google Meet, Zoom, Microsoft Teams

Agent frameworks: Claude Code, Cursor, OpenAI Codex, Gemini CLI, Windsurf, JetBrains Junie, OpenClaw, GitHub Copilot, Aider, and 30+ more that support the AgentSkill standard

Languages: Python 3.10+, Node.js 18+ (bridge scripts included)

## Getting Started

1. Sign up: https://app.agentcall.dev/login (Google OAuth, free)
2. Get API key: https://app.agentcall.dev/api-keys
3. Install the skill: https://github.com/pattern-ai-labs/agentcall
4. Tell your agent to join a meeting

## Key Features

- VAD gap buffering: combines fragmented transcripts into complete utterances
- Barge-in prevention: waits for silence before speaking
- Auto-interruption detection: stops speaking when someone talks over the bot (webpage modes)
- Sentence tracking: knows which sentence was interrupted and when
- WebSocket reconnection: auto-reconnects on network blips
- 5 built-in UI templates: orb, avatar, dashboard, blank, voice-agent
- Screenshots: capture what's on screen at any time
- API key persistence: saved to ~/.agentcall/config.json, asked once
- Stop Hook for Claude Code: prevents agent from exiting mid-call

## Links

- Website: https://agentcall.dev
- Dashboard: https://app.agentcall.dev
- GitHub: https://github.com/pattern-ai-labs/agentcall
- YouTube: https://www.youtube.com/@pattern-ai-labs
- Contact: hi@agentcall.dev | +1 (415) 430-7518

## Technical Details

- API: REST + WebSocket at api.agentcall.dev
- Auth: API key (ak_ac_ prefix) via Authorization header or ~/.agentcall/config.json
- Events: real-time via WebSocket (transcript.final, participant.joined, tts.done, call.ended, etc.)
- Commands: tts.speak, send_chat, raise_hand, screenshot, screenshare.start/stop, leave
- Bridge scripts: bridge.py / bridge.js (audio mode), bridge-visual.py / bridge-visual.js (avatar + screenshare)
- Skill file: SKILL.md (compatible with 30+ agent frameworks)

## About

Built by Pattern AI Labs.
Website: https://agentcall.dev
License: MIT (skill package)