- feat(smallestai): add TTS continuations protocol support
- baseten: inline mid-conversation instructions for Qwen/Qwen3.8-27B
- fix: drain inference STT transcripts before closing
- feat(azure): Add Azure Voice Live Realtime API support
- Revert "worker: read agent name from livekit.toml as last fallback (#7295)"
- docs: versions change only in release PRs
LiveKit Agents by LiveKit
Pulse Score
50 / 100
Rank #39 of 157
Downloads, last 7 days
988K
up 12.9% vs previous week
Downloads, last 30 days
3.5M
— vs previous 30 days
GitHub stars
14.6K
about +33 a day
Latest release
1.8.4
5d ago · 4 in 30 days
Price
Free (OSS)
checked Oct 5, 2026
Overview
A framework for building realtime voice and video AI agents on LiveKit's WebRTC infrastructure.
LiveKit Agents was downloaded 988K times from PyPI in the week ending Oct 4, 2026, up 12.9% on the week before. Its download count moved to a different level overnight on Aug 28, 2026. A jump like that comes from automated installs switching on or off or from a change in how the registry counts, so growth rates across that date are not shown. The GitHub repository has 14.6K stars, 631 of them added in the last 30 days. The latest stable release is 1.8.4, published Oct 1, 2026; there were 4 stable releases in the past 30 days. It was mentioned in 11 Hacker News posts and comments over the last 30 days.
LiveKit Agents usage and attention over time
Download the raw daily series: livekit-agents.csv
Install LiveKit Agents
| PyPI | pip install livekit-agents |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Key facts
| Maker | LiveKit |
|---|---|
| Type | Voice agent framework |
| License | Apache-2.0 |
| Interfaces | Python library, Node.js library |
| Main language | Python |
| Open issues and PRs | 950 |
Pricing
LiveKit Agents is open source and free to use; you pay only for the models and infrastructure it runs on.
, checked Oct 5, 2026. Prices change often; confirm before you buy.
Pulse Score breakdown
Adoption67
Community49
Attention12
Momentum52
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
What changed: recent LiveKit Agents releases
13 stable releases in the last 90 days · Full changelog
- chore: refine pii review instructions
- bithuman: resolve the SDK on Python 3.10 and 3.14 again
- add pid to log lines from parent process
- fix(tts): forward inner frames as-is in FallbackAdapter and StreamAdapter
- bithuman: type-check against bithuman 2.11
- docs: add gemini-3.8-live models to google README model list
- Run loop blocking detection. The agent now detects code that blocks the
- Faster agent startup. The prefork server preloads libraries before
- Improved agent lifecycle tracing. Traces now cover the full agent
- feat(speechify): send Speechify-Caller-Version attribution header
- fix(llm): reposition mid-conversation instructions for Gemini gateway and Mistral
- feat(voice): log which participant RoomIO links to
- chore: isolate ruff dependencies in ci
- fix(telemetry): describe option objects in the session report
- chore: remove commented-out keepalive stub from Deepgram V2 STT
- docs: remove stale example references after examples revamp
- fix(openai): don't replace a TTS prewarm that is still in flight
- fix: drain unused adapter metrics streams
- Conversation content is no longer emitted as span events — genai.system.message,
- Realtime inference moved off agentturn onto a new realtimeinference child span,
- genai.provider.name is normalized to the registry spelling. Providers outside the
- A custom llmnode is no longer credited with the configured model and provider
- When the project mandates redaction, content attributes are now stripped in-process
- genai.usage.inputcachedtokens is emitted again on the pipeline path (reversing
- fix(voice): agent and user state while a tool runs
- chore: teach reviews to catch untagged PII logs
- feat(agents): serialize the inline AgentTasks awaited from one turn
- fix(openai): read TTS response by content-type, not model name
- fix: avoid duplicate agent speech end
- feat(speechify): stream with timestamps via /v1/audio/stream/with-timestamps
LiveKit Agents alternatives
| # | Agent | Pulse | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | Last 90 days | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 18 |
ElevenLabs AgentsElevenLabs |
59 | 2.2M | up 4.2% | up 30.8% | — | — | — | Free + $0.08/extra minute | ||
| 38 |
Retell AIRetell AI |
50 | 617K | up 15.6% | up 15.8% | — | — | — | Free + $0.055/min | ||
| 41 |
VapiVapi, Inc. |
50 | 570K | up 19.8% | up 13.1% | — | — | — | Free + $0.05/min | ||
| 70 |
PipecatDaily |
39 | 260K | up 8.9% | down 17.5% | — | 16.2K+38/day | 1.12.010d ago | Free (OSS) | ||
| 129 |
SynthflowSynthflow AI |
16 | — | — | — | — | — | — | Custom | — | |
| 136 |
Bland AIBland |
12 | — | — | — | — | — | — | Free + $0.14/min | ||
| No agents match that filter. | |||||||||||
Head to head: LiveKit Agents vs ElevenLabs Agents · LiveKit Agents vs Retell AI · LiveKit Agents vs Vapi · LiveKit Agents vs Pipecat
LiveKit Agents FAQ
How much does LiveKit Agents cost?
LiveKit Agents is open source and free to use; you pay only for the models and infrastructure it runs on.
Is LiveKit Agents open source?
Yes. LiveKit Agents is open source, released under the Apache-2.0 license.
How popular is LiveKit Agents?
LiveKit Agents was downloaded 988K times from PyPI in the week ending Oct 4, 2026, up 12.9% on the week before. Its download count moved to a different level overnight on Aug 28, 2026. A jump like that comes from automated installs switching on or off or from a change in how the registry counts, so growth rates across that date are not shown. The GitHub repository has 14.6K stars, 631 of them added in the last 30 days.
What is the latest version of LiveKit Agents?
The latest stable release we track is 1.8.4, published on Oct 1, 2026.
What are the alternatives to LiveKit Agents?
The closest alternatives in the same category by Pulse Score are ElevenLabs Agents, Retell AI, Vapi, Pipecat.
Where these numbers come from
PyPI: livekit-agents. GitHub: livekit/agents. See data sources for how each one is collected.