LiveKit Agents
Website
A framework for building realtime voice AI agents 🤖🎙️📹
Is LiveKit Agents safe? Strong public trust posture, backed by multiple independent signals.
Compare LiveKit Agents
How does it stack up against its Voice & Conversational neighbours?
Pick any agent to compare →In detail: LiveKit Agents scores 91.7/100 (Grade A), ranked #11 of 1371 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 6.2/10; 100% of recent commits are signed; no published advisory affects its latest release (livekit-agents); last pushed 2026-10-09. Every point is earned from checkable signals — never paid placement. How scoring works →
What LiveKit Agents can reach, and who runs it
Checked 2026-10-06, each with its source. PUBLISHER is the company's or project's own statement, which we haven't verified; CHECKED is something we observed ourselves. These facts describe the product. They don't change its score.
Who runs it
- PUBLISHER The Agents framework is open source under Apache-2.0. Agents connect to LiveKit Cloud, the company's hosted service, or to a self-hosted LiveKit server.
Where your data goes
- PUBLISHER LiveKit Cloud doesn't keep media or transcripts by default: recordings are written to your own S3, GCS or Azure bucket, and prompts, audio and completions for AI inference aren't logged.
Security practice
- PUBLISHER States SOC 2 Type II, GDPR and CCPA compliance and EU–US Data Privacy Framework certification, and signs HIPAA BAAs on Scale and Enterprise plans. Reports are in its trust center, trust.livekit.io.
- CHECKED livekit.io publishes a security.txt ([email protected]), and GitHub private vulnerability reporting is enabled on the repository. Its maintainers have published 1 security advisory (medium), in the last 12 months.
How LiveKit Agents could raise its score
Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.
- Raise the OSSF Scorecard from 6.2 to 9.0lowest checks: CII-Best-Practices 0, Fuzzing 0, Security-Policy 0 +4.1 → 95.8 A · #1 of 13
Chain of custody
Scanners check what the code says. This traces who ships LiveKit Agents and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.
-
Source Signed
github.com/livekit/agents, Apache-2.0, last pushed 2026-10-09. 100% of the last 100 commits carry a verified signature, so changes trace to a verified account.
-
Review and release Mixed
OpenSSF Scorecard rates the repository's practices 6.2/10 (scanned Oct 6, 2026). The checks that decide who can get a change released:
- Code Review10
- Branch Protection4
- Signed Releasesn/a
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies4
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 4CI-Tests 10CII-Best-Practices 0Code-Review 10Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 10Fuzzing 0License 10Maintained 10Packaging 10Pinned-Dependencies 4SAST 6Security-Policy 0Signed-Releases -1Token-Permissions 0Vulnerabilities 0 -
Published packages Linked and attested
- PyPI livekit-agents Source link points back to this repo Build provenance attested
-
What you install today No known advisories
Latest release checked: livekit-agents 1.8.5. No published advisory affects it (OSV, checked 2026-10-09).
Changes to this chain
No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of LiveKit Agents.
Evidence behind this score
Coverage B: 3 of 5 independent evidence types found.
- GitHub repository data
- Package downloads
- Supply-chain checks
- Public actions (missing)
- Community mentions (missing)
Verify this score yourself
Every build re-issues LiveKit Agents’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.
What this score doesn’t check
It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.
How LiveKit Agents compares in Voice & Conversational
- #1 LiveKit Agents 91.7 this agent
- #2 Qwen Audio Agent 86.1 −5.6
- #3 Pipecat 85.0 −6.7
- #4 AstrBot 65.6 −26.1
- #5 Speech To Speech 63.6 −28.1
Bars show each HVTrust score; the tick marks LiveKit Agents’s 91.7.
Where the 91.7 comes from
HVTrust dimensions vs the Voice & Conversational average
91.7 / 100 · 100.0% confidenceLiveKit Agents Voice & Conversational average (13 agents)
Quick Trust Read
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
91.7 / 100Common questions about LiveKit Agents
Does LiveKit Agents publish package provenance?
Does LiveKit Agents have an OpenSSF Scorecard?
Is LiveKit Agents actively maintained?
What license does LiveKit Agents use?
Are LiveKit Agents's commits signed?
Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.
Compare LiveKit Agents head-to-head
AI agent surface
MCP, providers, tool surface
These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →
- MCP signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Maintain LiveKit Agents?
For maintainers
HVTrust scores LiveKit Agents from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/livekit-agents)
<a href="https://hvtracker.net/agents/livekit-agents"><img src="https://hvtracker.net/badge/livekit-agents.svg" alt="HVTrust"></a>
Other agents in Voice & Conversational
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON