TEN Agent
TEN Agent is a conversational AI powered by TEN, integrating Gemini 2.0 Multimodal Live API, OpenAI Realtime API, RTC, and more. It offers real-time capabilities to see, hear, and speak, along with advanced tools like weather checks, web search, and RAG. - 1313057/TEN-Agent
1313057
README
<div align="center">
<a href="https://trendshift.io/repositories/11978" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11978" alt="TEN-framework%2FTEN-Agent | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
<a href="https://github.com/TEN-framework/ten-agent/blob/main/README.md"><img alt="README in English" src="https://img.shields.io/badge/English-lightgrey"></a> <a href="https://github.com/ten-framework/ten-agent/blob/main/docs/readmes/README-CN.md"><img alt="简体中文操作指南" src="https://img.shields.io/badge/简体中文-lightgrey"></a> <a href="https://github.com/ten-framework/ten-agent/blob/main/docs/readmes/README-JP.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-lightgrey"></a> <a href="https://github.com/ten-framework/ten-agent/blob/main/docs/readmes/README-KR.md"><img alt="README in 한국어" src="https://img.shields.io/badge/한국어-lightgrey"></a> <a href="https://github.com/ten-framework/ten-agent/blob/main/docs/readmes/README-ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-lightgrey"></a> <a href="https://github.com/ten-framework/ten-agent/blob/main/docs/readmes/README-FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-lightgrey"></a> <a href="https://github.com/ten-framework/ten-agent/blob/main/docs/readmes/README-IT.md"><img alt="README in Italiano" src="https://img.shields.io/badge/Italiano-lightgrey"></a>
Getting Started <span> • </span> Create Extensions <span> • </span> TEN Framework Repository
</div>
<br>
<h2>🌟 Gemini Multimodal Live API Extension with RTC</h2>
<!--
-->
Try Google Gemini Multimodal Live API with realtime vision and realtime screenshare detection capabilities, it is a ready-to-use extension, along with powerful tools like Weather Check and Web Search integrated perfectly into TEN Agent.
<br> <h2>TEN Agent Usecases</h2>
<br> <h2>Ready-to-use Extensions</h2>
<br> <h2>TEN Agent Playground in Local Environment</h2>
Prerequisites
Category | Requirements |
---|---|
Keys | • Agora App ID and App Certificate (free minutes every month) <br>• OpenAI API key<br>• Deepgram ASR (free credits available with signup)<br>• FishAudio TTS (free credits available with signup) |
Installation | • Docker / Docker Compose<br>• Node.js(LTS) v18 |
Minimum System Requirements | • CPU >= 2 Core<br>• RAM >= 4 GB |
<br>
macOS: Docker setting on Apple Silicon
For Apple Silicon Macs, uncheck "Use Rosetta for x86/amd64 emulation" in Docker settings. Note: This may result in slower build times on ARM, but performance will be normal when deployed to x64 servers.
<br>
Next step
1. Create .env
file
cp ./.env.example ./.env
2. Setup Agora App ID and App Certificate in .env
AGORA_APP_ID=
AGORA_APP_CERTIFICATE=
3. Start agent development containers
docker compose up -d
4. Enter container
docker exec -it ten_agent_dev bash
5. Build agent
task use
6. Start the web server
task run
7. Edit playground settings
Open the playground at localhost:3000 to configure your agent.
- Select a graph type (e.g. Voice Agent, Realtime Agent)
- Choose a corresponding module
- Select an extension and configure its API key settings
Running Gemini Realtime Extension
Open the playground at localhost:3000.
- Select voice_assistant_realtime graph
- Choose Gemini Realtime module
- Select v2v extension and enter Gemini API key
<br> <h2>TEN Agent Components</h2>
<br> <h2>Stay Tuned</h2>
Before we get started, be sure to star our repository and get instant notifications for all new releases!
<br> <h2>Join Community</h2>
- Discord: Ideal for sharing your applications and engaging with the community.
- GitHub Discussion: Perfect for providing feedback and asking questions.
- GitHub Issues: Best for reporting bugs and proposing new features. Refer to our contribution guidelines for more details.
- X: Great for sharing your agents and interacting with the community.
<br> <h2>Star History</h2>
<br> <h2>Code Contributors</h2>
<br> <h2>Contribution Guidelines</h2>
Contributions are welcome! Please read the contribution guidelines first.
<br> <h2>License</h2>
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
AIO-MCP Server
🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from
React MCP
react-mcp integrates with Claude Desktop, enabling the creation and modification of React apps based on user prompts
Atlassian Integration
Model Context Protocol (MCP) server for Atlassian Cloud products (Confluence and Jira). This integration is designed specifically for Atlassian Cloud instances and does not support Atlassian Server or Data Center deployments.

Any OpenAI Compatible API Integrations
Integrate Claude with Any OpenAI SDK Compatible Chat Completion API - OpenAI, Perplexity, Groq, xAI, PyroPrompts and more.
MySQL Server
Allows AI assistants to list tables, read data, and execute SQL queries through a controlled interface, making database exploration and analysis safer and more structured.
Browser Use (used by Deploya.dev)
AI-driven browser automation server that implements the Model Context Protocol to enable natural language control of web browsers for tasks like navigation, form filling, and visual interaction.
Aindreyway Codex Keeper
Serves as a guardian of development knowledge, providing AI assistants with curated access to latest documentation and best practices.