LiveKit Agents
A framework for building realtime voice AI agents 🤖🎙️📹 open source
Visit LiveKit Agents ↗ GitHub ↗
Where it ranks
- Real-time voice agents: Pick (80.9/100)
Pricing
Open source framework. LiveKit Cloud: free $0/mo tier; paid from $50/mo.
Source: https://livekit.io/pricing, checked 2026-10-19
Public signals
| GitHub stars | 14.8ksource |
|---|---|
| Forks | 4.0k |
| Last push | Oct 19, 2026 |
| 7-day star change | unknown (needs 7 days of snapshots) |
| Latest stable release | livekit-agents@1.8.8 Oct 15, 2026 |
| Hacker News, last 30 days | 2 stories, 2 points · top: Do Jev Decision Models work for mine operations?query |
Matched by linked URL “livekit.io”. Title matches can include unrelated stories.
Recent releases
- livekit-agents@1.8.8 Oct 15, 2026
GPT-Live through LiveKit Inference You can now run GPT-Live with your LiveKit credentials instead of a separate OpenAI key. inference.DuplexModel handles its protocol, and you can adopt it directly with a model string: session = AgentSession ( llm = "openai/gpt-live-1" ) New prov - livekit-agents@1.8.7 Oct 14, 2026
Realtime E2E latency You can now measure realtime replies from the last detected user speech to first assistant playback when you configure local VAD. Read the latency from assistant message metrics: @ session . on ( "conversation_item_added" ) def on_message ( event ): if event - livekit-agents@1.8.6 Oct 9, 2026
What's Changed fix(sarvam): close the streams the STT collects by @dhruvladia-sarvam in #7058 fix(aws): keep realtime session active after stream restart by @uuzzrm in #6811 fix(telemetry): format a loop stall report without reading source files by @zdurm in #7616 update deps by