Platform quickstart

Set up a working Conversational AI Platform agent in under five minutes. This page walks you through installing Agora Skills to give your AI coding assistant the official Platform quickstarts and Agora CLI workflows. You then use the CLI to sign in, clone the official Platform starter, and run it locally. You can follow the CLI steps yourself or paste the sample prompt and let your assistant handle setup for you.

If you are new to Agora, read Core concepts first to understand how RTC, Signaling, channels, UIDs, and tokens fit together.

Set up your toolsCopy Anchor Link

Install Agora Skills to let your AI coding assistant set up the starter for you, or install the Agora CLI to run each command yourself.

Install Agora SkillsCopy Anchor Link

Agora Skills teach your AI coding assistant how to work with Conversational AI Platform projects using official starter repos and the Agora CLI, including signing in, project binding, generating environment files, and running diagnostics. Install the Agora CLI yourself, or ask your assistant to run the installer for you.

npx skills add AgoraIO/skills

Paste the following prompt into your assistant's chat. You can replace Python with TypeScript or Go depending on your language preference:

Set up and run the Agora Conversational AI Platform Python starter project locally.

Your assistant installs the CLI, signs you in, scaffolds the official Platform starter, and guides you through the remaining steps.

Install the Agora CLICopy Anchor Link

The Agora CLI is a native Go binary available at AgoraIO-Community/cli.

curl -fsSL https://dl.agora.io/cli/install.sh | sh
agora --help

irm https://dl.agora.io/cli/install.ps1 | iex
agora --help

powershell -ExecutionPolicy Bypass -File .\install.ps1

Sign in, scaffold, and runCopy Anchor Link

Sign in with the Agora CLI, clone the Platform starter project, and configure it for your chosen language.

1. Sign in to Agora Console.

   Copy Text

   agora login

2. Use agora init to clone the official Platform starter for your chosen template, bind it to your Agora project, and write the runtime-specific environment file.

   PythonTypeScriptGo

   Copy Text

   agora init my-platform-python-demo --template platform-python
   cd my-platform-python-demo
   # Set up the web client and Python backend.
   bun run setup
   # Start the web client and Python backend.
   bun run dev

   Copy Text

   agora init my-platform-nextjs-demo --template platform-nextjs
   cd my-platform-nextjs-demo
   pnpm install
   pnpm dev

   Copy Text

   agora init my-platform-go-demo --template platform-go
   cd my-platform-go-demo
   make setup
   make dev

3. Open http://localhost:3000 and click Start conversation.

If the agent does not join or transcripts do not appear, run agora project doctor to check credential validity, Platform access, and network reachability.

What just happenedCopy Anchor Link

The CLI cloned the selected Platform starter, connected it to your Agora project, and wrote the environment configuration required to run the demo locally.

The demo runs a local browser app and server-side agent controls:

• Browser app: Joins an RTC channel, sends your microphone audio to the agent, plays the agent's spoken responses, and shows the conversation transcript.
• Server-side controls: Create a saved agent in your project, generate tokens, and start or stop sessions that run the agent.

The starter saves the agent configuration in your project once. Each time you click Start conversation, it starts a new session that refers to the saved agent by its ID.

Agora provides the real-time path between the user and the agent. The user and agent join the same Agora channel, and Agora transports low-latency audio and session events between them.

The agent uses managed mode. Agora provides access to the models, and the starter doesn't need provider API keys. The models handle the speech pipeline:

1. ASR converts user speech to text.
2. The LLM reasons over the conversation and generates a response.
3. TTS converts the response back to speech.

Next stepsCopy Anchor Link

Build and customizeCopy Anchor Link

• Manage agent sessions: Create agents, and start and stop sessions with the REST API.
• Customize models: Use managed mode, or bring your own provider keys stored in secret sets.
• Improve conversation quality: Tune latency, audio settings, interruptions, and turn taking.
• Optimize audio setup: Set audio profiles, scenarios, and capture behavior for your target clients.
• Review the API reference: Check Platform REST API parameters when you move beyond the starter.

Observe and troubleshootCopy Anchor Link

• Observe runtime behavior: Monitor notification events, session status, and failures.
• Debug agent failures: Correlate client callbacks with notification events.

Prepare for productionCopy Anchor Link

• Review security and privacy: Check authentication, encryption, compliance, and operational safeguards.