cd /news/ai-agents/agentcall-bring-your-agents-to-multi… · home › topics › ai-agents › article
[ARTICLE · art-172479] src=github.com ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

AgentCall – Bring your agents to multilingual online meetings using skill

Pattern AI Labs released AgentCall, a skill that lets AI coding agents including Claude Code, Cursor 2.5+, OpenAI Codex CLI, Gemini CLI, Windsurf, GitHub Copilot and Junie join Google Meet, Zoom and Microsoft Teams meetings as voice-enabled bots. The skill offers text-to-speech in 54 voices across 9 languages with under 1 second of latency, real-time transcription, screenshots of shared screens, an animated avatar camera feed, screenshare, meeting chat, and three modes (audio, webpage-av, webpage-av-screenshare) plus direct, collaborative and realtime voice strategies. AgentCall requires Python 3.10+ or Node.js 18+, a free account with trial credits, and runs on the open Agent Skills standard supported by 30+ frameworks.

key takeaway

AgentCall's realtime strategy lets the bot's own voice answer within about a second in multiple languages and call back to the coding agent via agent.request for facts and tools, with up to 10,000 characters of context passed to the voice layer.

read6 min views8 publishedNov 19, 2026
AgentCall – Bring your agents to multilingual online meetings using skill
Image: Michielbdejong (auto-discovered)

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.

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.

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
  1. Python 3.10+ orNode.js 18+
  2. Dependencies :pip install aiohttp websockets (Python) ornpm install ws (Node.js)
  3. 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 fromhttps://app.agentcall.dev/api-keys ). New accounts include free trial credits.

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

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

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

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

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

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

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/

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

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
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
  • 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

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)

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.

  • 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)

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.

MIT — use, modify, redistribute freely.

Built by AgentCall (Pattern AI Labs)

── more in #ai-agents 4 stories · sorted by recency
── more on @agentcall 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/agentcall-bring-your…] indexed:0 read:6min 2026-11-19 · —