AgentCall join-meeting Skill
Gives AI coding agents a voice, an avatar and a screenshare so they can join and take part in video meetings.
- Source repo
- pattern-ai-labs/agentcall
- Stars
- ★ 184
- Last updated
- 15d ago
- License
- MIT
- Primary language
- Python
- FA score
- 51/100 · Major gaps
At a glance
- How it runs
- Works with
- Portable with changesCodex · Claude Code
- Cost
- Free tier plus a paid hosted plan
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A development team running standup in Google Meet lets a coding agent report progress and, in the same breath, inspect the repo, run commands and push a fix.
- Not a fit if
- Teams needing fully offline or self-hosted deployment; core function relies on the AgentCall cloud
- Users unwilling to pay per-minute for meeting time beyond the free trial credits
- Production use requiring reliable Microsoft Teams support, which is still Beta
- Source review
- 51/100 · Major gaps
What does this agent do, and when should you use it?
join-meeting is an AgentCall skill that runs on top of an existing coding agent — Claude Code, Cursor, OpenAI Codex CLI, Gemini CLI, Windsurf, Junie, OpenClaw, GitHub Copilot and others — rather than being a standalone app. It lets that agent join Google Meet, Zoom and Microsoft Teams calls as a bot with voice conversation, an animated avatar camera feed, screenshare, real-time transcription and meeting chat. The skill needs Python 3.10+ or Node.js 18+ (aiohttp/websockets or ws) and talks to the AgentCall service over WebSocket using an API key that can be created for you on first run and is persisted to ~/.agentcall/config.json. Its distinguishing claim is that the agent keeps its full session context during the call, so it can search code, edit files, run commands and commit while it talks — the meeting is just another I/O channel.
Given a meeting URL, the skill launches a bot in one of three modes: audio (voice only), webpage-av (voice plus an animated avatar as the camera feed) or webpage-av-screenshare (voice, avatar and live screensharing of URLs, dashboards or slides). Speech output uses text-to-speech with 54 voices across 9 languages and a claimed sub-second latency; on the listening side the agent receives real-time transcripts of what participants say, and it can take screenshots of shared screens at any moment. Two voice strategies are offered: direct, where the agent controls TTS itself, and collaborative, where GetSun voice intelligence manages turn-taking for multi-party conversations. The skill also implements VAD gap buffering, barge-in prevention, auto-interruption detection, sentence-level tracking of what was interrupted, WebSocket reconnection with call-status checks, and crash recovery that rejoins an active call after the agent restarts. Meeting chat can be used to send URLs, code or text that is awkward to speak, and seven built-in templates (pattern, orb, ring, avatar, dashboard, blank, voice-agent) control what the bot displays.
- A development team running standup in Google Meet lets a coding agent report progress and, in the same breath, inspect the repo, run commands and push a fix.
- A support engineer drops the bot into a Zoom call so it can speak scripted answers and paste links or code into the meeting chat.
- Someone who needs meeting notes deploys an audio-mode bot that receives live transcripts and turns them into written records.
- A presenter uses webpage-av-screenshare so the agent can walk an audience through a dashboard, slide deck or web page while sharing its screen.
- In a multi-party call, collaborative voice strategy hands turn-taking to GetSun so the bot does not talk over people.
- When the network blips or the agent process restarts mid-call, reconnection and crash recovery bring it back into the ongoing meeting.
- Teams experimenting with Microsoft Teams (marked Beta) can run the same workflow there.
How do you install or deploy this agent?
Prerequisites: one of the supported coding agents, Python 3.10+ or Node.js 18+, and dependencies installed with pip install aiohttp websockets (Python) or npm install ws (Node.js). Then pick the install path for your agent. Claude Code: /plugin marketplace add pattern-ai-labs/agentcall followed by /plugin install join-meeting@agentcall. OpenClaw: openclaw skills install join-meeting. Cursor 2.5+: /add-plugin in the editor or browse cursor.com/marketplace. OpenAI Codex CLI: drop the skill into ~/.codex/skills/ or run $skill-installer. Gemini CLI: run gemini extensions install https://github.com/pattern-ai-labs/agentcall from your terminal. Junie: npx skills add pattern-ai-labs/agentcall --agent junie. Windsurf: place the folder in .windsurf/skills/. Single-session Claude Code: place it in .claude/skills/. For anything else, git clone https://github.com/pattern-ai-labs/agentcall.git and point the agent at agentcall/SKILL.md. On first run without a key the skill registers a free account via a one-time email code, or you can paste an existing key from https://app.agentcall.dev/api-keys; new accounts include free trial credits.
How do you use this agent?
Tell your agent: “Join this meeting: https://meet.google.com/abc-def-ghi”. Choose a mode (audio, webpage-av, webpage-av-screenshare) and a voice strategy (direct for one-on-one and support calls, collaborative for group meetings). The API key is asked once and stored in ~/.agentcall/config.json. SKILL.md documents modes, events, commands, templates and Claude Code integration; examples/ contains seven working examples; references/ covers the API plus collaborative mode, interruption handling, crash recovery and screenshare.
What are this agent's strengths and limitations?
- Covers three meeting platforms (Google Meet, Zoom, Microsoft Teams with Teams marked Beta) with three run modes and two voice strategies, so one skill spans note-taking through live presenting.
- The agent keeps full coding-session context during the call, so it can search code, edit files, run commands and commit while participating in the meeting.
- The concurrency plumbing is explicit: VAD gap buffering, barge-in prevention, auto-interruption detection, sentence tracking, WebSocket reconnection and crash recovery are all documented features.
- Distributed as an open Agent Skills SKILL.md with install paths for Claude Code, Cursor, Codex CLI, Gemini CLI, Windsurf, Junie, OpenClaw and GitHub Copilot, under a permissive MIT license.
- Core function depends on the hosted AgentCall service and an API key; there is no documented self-hosted path, so the service going down or pricing changing directly affects you.
- Not a standalone app — it requires a supported coding agent plus Python 3.10+ or Node.js 18+ and third-party dependencies (aiohttp/websockets or ws).
- Framework support is uneven: Aider is only partial (no subprocess) and Cursor needs tmux for a PTY, so some environments require extra setup.
- Microsoft Teams support is explicitly labelled Beta, so reliability there is unproven.
- Usage is metered by meeting time: the base plan covers 6 hours with 1 concurrent call, and paid usage is billed per minute.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| AgentCall join-meeting Skill This agent | 51 · Major gaps | Agent plugin / skillFreemium | ★ 184 | 15d ago | Python | Codex · Claude Code |
| Sapphire Blue AI | 69 · Some gaps | Web appFree + model costs | ★ 330 | 1d ago | Python | OpenAI API · Claude API |
| CyberVerse Digital Human Assistant | 49 · Major gaps | Self-hosted serviceFree + model costs | ★ 1.9k | 18d ago | Python | — |
| Switch AI Team Workspace | 70 · Some gaps | Desktop app | ★ 4.3k | today | Python | — |
How does FollowAgents rate this agent?
Why each dimension lost points
The README identifies API, WebSocket, tunnel, and optional registration endpoints, and describes API key locations, transmission, meeting data flows, and local configuration. This supports a relatively strong data flow disclosure score. Deductions: the skill permits the agent to access email, register, and save a key, and says meeting transcripts can steer the agent; permissions are delegated to the host framework. No per-action confirmation gate is shown for speaking, chat, or screen sharing. The key is sent in a WebSocket query parameter, and sensitive-data protection and dependency-security evidence is limited. Visible participation and leaving/cleanup are mentioned, but recovery and rollback detail is sparse. Repository authorship is stated, while publisher identity remains unknown.
Two bridge test files show command acknowledgments, errors for unknown commands, and some error-path behavior. Deductions: the README and skill describe many modes, frameworks, and features, but this packet contains only a small test sample and cannot corroborate overall stability. The README says missing dependencies prompt manual installation; the install notes provide commands but no pinned versions or evidence of dependency availability.
The materials identify coding agents that can spawn subprocesses and read stdout as the audience, and list supported frameworks, modes, voice strategies, and meeting scenarios. The skill also explains that transcripts can steer the agent and recommends host permission controls. Deductions: Aider support is partial and webpage modes require a local HTTP server, but platform-specific permission differences and unsupported scenarios are not comprehensively covered.
The README organizes installation, modes, features, endpoints, and documentation; it gives multi-platform setup steps, examples, and references. The license metadata and LICENSE file both state MIT. Deductions: no changelog or maintenance/update commitment appears in the supplied material; the product is named both join-meeting and AgentCall; known limitations are only lightly documented, and version information is mainly in plugin manifests.
The product offers meeting voice, transcription, screen viewing, sharing, and chat for agent collaboration, with actionable setup and invocation guidance. Deductions: it requires an account key, paid per-minute usage beyond the base plan, and an external API, so cost-benefit depends on usage. Evidence for output quality and feature effectiveness is mostly asserted in product materials and cannot be confirmed from this static packet.
The README gives specific endpoint and credential descriptions, the skill and plugin manifests partly align on capabilities, and the tests demonstrate a limited set of command behaviors. Deductions: key feature, privacy, and performance claims lack sufficient independent support in the supplied materials; the privacy policy is linked but not included, and the tests are only a sample. Static review cannot verify runtime behavior, so the rationale distinguishes documented behavior from unverified product claims.
- Meeting transcripts can influence agent behavior. Configure host-framework permission limits and be cautious about granting email, shell, file, and commit access.
- Meeting audio and transcripts stream to the AgentCall API. The README says they are not permanently stored; review the full privacy policy and assess suitability for sensitive meetings.
- The API key is sent as a WebSocket query parameter. Protect the local config file and check that the agent and runtime environment meet your organization’s requirements.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/agentcall)<a href="https://followagents.com/en/agents/agentcall"><img src="https://followagents.com/badge/agentcall.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Collaborative voice strategy in the bridges: --voice-strategy collaborative (with --trigger-words, --context, --barge-in-prevention, --voice, --voice-events). Speak with inject.verbatim / inject.natural; new events voice.text, call.degraded, call.recovered. Direct mode unchanged.View on GitHub ↗ -
Release notes excerpt
Mic command replies with meeting.mic.result (muted, noop, warning), so the agent knows whether the bot's mic is really on; command.error if no result within 5 s.View on GitHub ↗ -
Release notes excerpt
Bring your own voice (ElevenLabs) New example [examples/elevenlabs-voice](https://github.com/pattern-ai-labs/agentcall/tree/main/examples/elevenlabs-voice) (Python + Node.js): a bot that speaks with an ElevenLabs voice using your own API key (#3). ElevenLabs PCM 16 kHz is streamed into the call with paced audio.inject, with barge-in via audio.clear. New guide references/guides/bring-your-own-voice.md: audio format, pacing, barge-in and billing. Works with any provider that returns raw PCM. Audio mode only. …View on GitHub ↗
FAQ
Do I need to host a meeting bot myself?
What does it cost?
What credentials or permissions does it need?
What happens if the network drops or my agent restarts mid-call?
Which coding agents are supported?
Thanks — we use this to improve the page.