LiveKit Agents vs Pipecat
LiveKit Agents (LiveKit) and Pipecat (Daily) side by side on public data, as of Nov 20, 2026.
LiveKit Agents has 3.2x the weekly package downloads of Pipecat (1.2M against 391K). LiveKit Agents and Pipecat are close on GitHub stars (15.3K and 17.3K). Over the last 30 days downloads moved +22% for LiveKit Agents and +40% for Pipecat. LiveKit Agents shipped 15 stable releases in the past 90 days. Pipecat shipped 10 stable releases in the past 90 days.
Side-by-side numbers
| Metric | LiveKit Agents | Pipecat |
|---|---|---|
| Gid Score | 52 | 47 |
| Usage data as of | Nov 19 | Nov 19 |
| Rank by Gid Score | #36 | #52 |
| Downloads, last 7 days | 1.2M | 391K |
| Downloads, 7-day change | down 3.5% | up 6.0% |
| Downloads, 30-day change | up 22.4% | up 40.0% |
| VS Code installs | — | — |
| Marketplace rating | — | — |
| GitHub stars | 15.3K | 17.3K |
| Homebrew installs, 30 days | — | — |
| Hacker News mentions, 30 days | 8 | 2 |
| Latest stable release | 1.8.13 · 2d ago | 1.16.0 · 8d ago |
| Stable releases, 90 days | 15 | 10 |
| Terminal-Bench (best run) | — | — |
| Price | Free (OSS) | Free (OSS) |
| License | Apache-2.0 | BSD-2-Clause |
| First released | November 2023 | May 2024 |
| Interfaces | Python library, Node.js library | Python library |
| Models | — | — |
A dash means there is no public data for that metric as of Nov 20, 2026.
Trends
LiveKit Agents
A framework for building realtime voice and video AI agents on LiveKit's WebRTC infrastructure. LiveKit's docs also describe Agent Builder, for prototyping and deploying agents in the browser without writing code.
Pricing: LiveKit Agents is open source and free to use; you pay only for the models and infrastructure it runs on.
Latest release 1.8.13:
- VLM Run: new livekit-plugins-vlmrun plugin for vision-language chat and System One decisions, including qwen/qwen3.8-27b.
- AssemblyAI STT 3.7 Realtime Agent: supported through LiveKit Inference as assemblyai/assemblyai-stt-3-7-realtime-agent.
- Sarvam: STTRealtime now supports saaras:v4.
- Boson AI: replace livekit-plugins-boson with livekit-plugins-boson-ai, import livekit.plugins.boson_ai, and change the [boson] extra to [boson-ai]. The avatar plugin is unchanged.
Pipecat
An open-source Python framework for voice and multimodal conversational agents, maintained by Daily and the community.
Pricing: Pipecat is open source and free to use; you pay only for the models and infrastructure it runs on.
Latest release 1.16.0:
- Added a normalization field to CartesiaTTSService.Settings and CartesiaHttpTTSService.Settings, passing Cartesia's text normalization mode ("auto", "off", or a locale code such as "en-GB") through…
- Added SarvamHttpSTTService, which sends each VAD speech segment to Sarvam's REST speech-to-text API (saaras:v4 by default, or saaras:v3) and yields the transcription from run_stt().
- Added max_speakers and filter_profanity to AssemblyAISTTService.Settings, passing AssemblyAI's speaker-label cap and profanity filter through to the streaming session.
- CartesiaSTTService.Settings now exposes Cartesia's min_volume and max_silence_duration_secs, which control the silence that triggers automatic transcript finalization on ink-whisper models.
LiveKit Agents vs Pipecat: common questions
Which is more popular, LiveKit Agents or Pipecat?
LiveKit Agents has a Gid Score of 52 against 47 for Pipecat. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.