Open-source framework for all AI agents.

Three steps, you can get TEN up and running.

Step ⓵ - Prerequisites

• Agora App ID and App Certificate (free minutes every month)
• OpenAI API key (any LLM that is compatible with OpenAI)
• Deepgram ASR (free credits available with signup)
• ElevenLabs TTS (free credits available with signup)

• Docker / Docker Compose
• Node.js(LTS) v18

• CPU >= 2 Core
• RAM >= 4 GB

macOS: Docker setting on Apple Silicon

Uncheck "Use Rosetta for x86/amd64 emulation" in Docker settings, it may result in slower build times on ARM, but performance will be normal when deployed to x64 servers.

Step ⓶ - Build agent in VM

Clone down the repo,`cd` to `ai-agents` and create `.env` file from `.env.example`

cd ai_agents
cp ./.env.example ./.env

Setup Agora App ID, App Certificate, Deepgram API Key and ElevenLabs API Key in `.env`

# Agora App ID
# Agora App Certificate(only required if enabled in the Agora Console)
AGORA_APP_ID=
AGORA_APP_CERTIFICATE=

# Extension: elevenlabs_tts
# ElevenLabs TTS key
ELEVENLABS_TTS_KEY=

# OpenAI API key
OPENAI_API_KEY=

# Extension: deepgram_asr
# Deepgram ASR key
DEEPGRAM_API_KEY=

Start agent development containers

docker compose up -d

Enter container

docker exec -it ten_agent_dev bash

Build agent with the default `graph` ( ~5min - ~8min)

check the /examples folder for more examples

# use the default agent
cd agents/examples/voice-assistant

# you can also change the command to setup other examples
cd agents/examples/<example_name>

task install

Start the app

task run
# the frontend will be running on http://localhost:3000

Step ⓷ - Customize your agent with TMAN Designer

Open localhost:49483.
Right-click to load the corresponding graph (e.g., Voice Assistant).
Enter API keys and set preferences for each extension if you have not set them in .env in previous steps.
Right-click and select Manage Apps to start the Apps Manager.
Click Run App to start TEN Agent.

Getting Started