pipecat-examples vs agent-starter-react

Two of the top projects in Voice and realtime, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.

22nd of 16 in Voice and realtime

pipecat-examples

Runnable Pipecat voice agent examples for phone, web and deployment

33rd of 16 in Voice and realtime

agent-starter-react

Next.js voice assistant frontend for LiveKit Agents

Verdict

pipecat-examples ranks higher, 57 to 54. Of the 4 score parts we measure for both, pipecat-examples leads on 1, agent-starter-react on 1 and 2 are even.

  • Adoptionagent-starter-react leads by 14 points, 43 to 29.
  • FreshnessEven at 100.
  • Maintenancepipecat-examples leads by 24 points, 60 to 36: a wide gap.
  • Agent-readyEven at 0.

Pick pipecat-examples if you are

Pipecat developers needing telephony or client patterns

  • Telephony examples for Twilio, Telnyx, Plivo, Exotel and Daily SIP
  • simple-chatbot ships React, Swift, Kotlin and React Native clients

Pick agent-starter-react if you are

Teams shipping a web UI for a LiveKit voice agent

  • Transcript, media tiles, avatar video and visualizers already composed
  • Agents UI components are installed into components/ and editable in place
pipecat-examples vs agent-starter-react: score parts and facts
What we comparepipecat-examplesagent-starter-react
Score parts, out of 100
Adoption29, niche43, known
Freshness100, active100, active
Maintenance60, fair36, patchy
Agent-ready0, none0, none
Facts from GitHub and the README
Stars403964
LicenseBSD-2-Clause (permissive)MIT (permissive)
Last commitOct 2026Oct 2026
Last releaseNone publishedNone published
LanguagePythonTypeScript
DockerYesNo
GPUNot neededNot needed
arm64 or Apple SiliconNot statedNot stated

pipecat-examples

Pipecat apps in Python 3.11+, one directory each: phone bots for Twilio, Telnyx, Plivo, Exotel and Daily SIP, a simple-chatbot with React, Swift, Kotlin and React Native clients, websocket and p2p WebRTC transports, Gemini Live, local smart-turn, OpenTelemetry tracing and deploy recipes for Pipecat Cloud, Fly.io, Modal and Cerebrium. For teams on Pipecat who want a working pattern to copy.

Who it is for: Pipecat developers needing telephony or client patterns

Strengths

  • Telephony examples for Twilio, Telnyx, Plivo, Exotel and Daily SIP
  • simple-chatbot ships React, Swift, Kotlin and React Native clients
  • Deployment and OpenTelemetry (Langfuse, LangSmith, Jaeger) examples

Weaknesses

  • Each example has its own setup; no single app to fork
  • Needs API keys for STT, LLM and TTS services (OpenAI, Deepgram, Cartesia)
  • Beginner examples live in the main Pipecat repo, not here
  • Issues are tracked in the main Pipecat repo
  • Python, Pipecat service plugins (OpenAI, Deepgram, Cartesia, Gemini Live)
  • Needs OpenAI, Deepgram, Cartesia or similar API keys, Daily or a telephony provider for phone examples
  • Docker

agent-starter-react

Next.js app on LiveKit Agents UI components and the LiveKit JS SDK: welcome and session views, chat transcript, media tiles, camera, screen share, avatar rendering and five audio visualizer styles. A route at app/api/token issues LiveKit tokens from your project credentials. Frontend only; pair it with a LiveKit agent such as agent-starter-python or agent-starter-node.

Who it is for: Teams shipping a web UI for a LiveKit voice agent

Strengths

  • Transcript, media tiles, avatar video and visualizers already composed
  • Agents UI components are installed into components/ and editable in place
  • Token route included; development token server also supported
  • Matching Android, Swift, Flutter and React Native starters exist

Weaknesses

  • Needs a separate LiveKit agent and a LiveKit Cloud or self-hosted server
  • Token route has no authentication; add one before production
  • No tests or Docker
  • TypeScript
  • Needs LiveKit Cloud or self-hosted LiveKit server, a LiveKit agent
  • GitHub template
  • env example file

More in Voice and realtime

Building with these?

We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.