{"name":"joinly: Make Your Meetings Accessible to AI Agents","description":"joinly.ai is an open-source connector middleware designed to integrate AI agents into video calls. It enables agents to actively participate, interact in real-time, and perform tasks during meetings across platforms like Google Meet, Zoom, and Microsoft Teams. The project emphasizes a privacy-first approach, offering self-hosting capabilities and flexibility with various LLM, TTS, and STT providers.","github":"https://github.com/joinly-ai/joinly","url":"https://osrepos.com/repo/joinly-ai-joinly","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/joinly-ai-joinly","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/joinly-ai-joinly.md","json":"https://osrepos.com/repo/joinly-ai-joinly.json","topics":["agentic-ai","ai-agent","ai-tool","conversational-ai","llm","meeting-agent","meeting-assistant","python"],"keywords":["agentic-ai","ai-agent","ai-tool","conversational-ai","llm","meeting-agent","meeting-assistant","python"],"stars":null,"summary":"joinly.ai is an open-source connector middleware designed to integrate AI agents into video calls. It enables agents to actively participate, interact in real-time, and perform tasks during meetings across platforms like Google Meet, Zoom, and Microsoft Teams. The project emphasizes a privacy-first approach, offering self-hosting capabilities and flexibility with various LLM, TTS, and STT providers.","content":"## Introduction\n\njoinly.ai is a powerful open-source connector middleware that empowers AI agents to seamlessly join and actively engage in video conferences. It transforms your meetings by allowing AI agents to perform tasks, respond in real-time via voice or chat, and interact naturally with participants. Built with a focus on flexibility and privacy, joinly.ai supports various LLM providers, Text-to-Speech (TTS), and Speech-to-Text (STT) services, making it a versatile tool for enhancing productivity and automation in virtual meetings.\n\nKey features include live interaction capabilities, a built-in conversational flow to handle interruptions and multi-speaker scenarios, and cross-platform compatibility with major video conferencing tools. It is 100% open-source, self-hostable, and privacy-first, giving users full control over their data and AI integrations.\n\n## Installation\n\nGetting started with joinly.ai is straightforward using Docker. This quick guide will help you run a basic conversational agent client.\n\n**Prerequisites:** Ensure you have [Docker installed](https://docs.docker.com/engine/install/) on your system.\n\n1.  **Create an `.env` file:** In a new directory, create an `.env` file with your desired LLM provider's API key. For example, using OpenAI:\n\n    dotenv\n    # .env\n    JOINLY_LLM_MODEL=gpt-4o\n    JOINLY_LLM_PROVIDER=openai\n    OPENAI_API_KEY=your-openai-api-key\n    \n\n2.  **Pull the Docker image:**\n\n    bash\n    docker pull ghcr.io/joinly-ai/joinly:latest\n    \n\n3.  **Launch joinly in a meeting:** Start your meeting on Zoom, Google Meet, or Microsoft Teams. Then, run the following command from the directory containing your `.env` file, replacing `<MeetingURL>` with your meeting link:\n\n    bash\n    docker run --env-file .env ghcr.io/joinly-ai/joinly:latest --client <MeetingURL>\n    \n\nFor more advanced configurations, including GPU support or running an external client, refer to the official documentation.\n\n## Examples\n\njoinly.ai showcases its capabilities through practical demonstrations where AI agents perform real-world tasks within meetings:\n\n*   **GitHub Demo:** An AI agent answers questions by accessing web information and then creates an issue in a GitHub repository, all live during a meeting.\n*   **Notion Demo:** An agent connects to Notion via the MCP (Meeting Control Protocol) and edits page content in real-time during a meeting.\n\nThese examples highlight the potential for automation and intelligent assistance that joinly.ai brings to collaborative environments.\n\n## Why Use joinly?\n\njoinly.ai offers compelling reasons for integration into your workflow:\n\n*   **Live Interaction:** Agents can execute tasks and respond instantly, either by voice or chat, enhancing real-time collaboration.\n*   **Natural Conversations:** Its built-in logic manages interruptions and multi-speaker interactions, ensuring a smooth conversational flow.\n*   **Broad Compatibility:** Works across popular platforms like Google Meet, Zoom, and Microsoft Teams, providing flexibility.\n*   **Customizable AI Stack:** Supports various LLM providers, including local options like Ollama, and allows you to choose your preferred TTS/STT services (Whisper, Deepgram, ElevenLabs, Kokoro).\n*   **Open-Source and Privacy-First:** Being 100% open-source and self-hostable, it prioritizes user privacy and control over data.\n*   **Extensible:** The MCP server provides a rich set of tools for agents, including joining/leaving meetings, speaking text, sending chat messages, getting chat history, transcripts, and even video snapshots.\n\n## Links\n\n*   **GitHub Repository:** [https://github.com/joinly-ai/joinly](https://github.com/joinly-ai/joinly){:target=\"_blank\"}\n*   **Official Website:** [https://joinly.ai/](https://joinly.ai/){:target=\"_blank\"}\n*   **Discord Community:** [https://discord.com/invite/AN5NEBkS4d](https://discord.com/invite/AN5NEBkS4d){:target=\"_blank\"}\n*   **GitHub Discussions:** [https://github.com/joinly-ai/joinly/discussions](https://github.com/joinly-ai/joinly/discussions){:target=\"_blank\"}\n*   **joinly Cloud:** [https://cloud.joinly.ai](https://cloud.joinly.ai){:target=\"_blank\"}","metrics":{"detailViews":1,"githubClicks":3},"dates":{"published":null,"modified":"2026-01-12T00:00:41.000Z"}}