Registry › Compare › LiveKit Agents vs TEN Framework

LiveKit Agents vs TEN Framework

LiveKit Agents leads on trust: 92.2/100 (Grade A) against 57.8/100 (Grade C), a 34.4-point gap. LiveKit Agents leads on supply-chain integrity and adoption, and rests on broader evidence.

A LiveKit Agents 92.2

A framework for building realtime voice AI agents 🤖🎙️📹

livekit/agents · #10 overall · #1 Voice & Conversational · coverage B (3/5)

Choose LiveKit Agents if supply-chain integrity and adoption matter most.

+10.6Safety / Integrity: OSSF Scorecard 6.5 against 4.0
+8.4Adoption: 15.1k GitHub stars against 11.2k
+7.2Identity / Provenance: package provenance attested, against none
+3.0Maintenance

C TEN Framework 57.8

Open-source framework for conversational voice AI agents

TEN-framework/ten-framework · #765 overall · #9 Voice & Conversational · coverage C (2/5)

TEN Framework doesn't lead on any scored dimension in this pair.

Where they differ

20.6

Safety / IntegrityLiveKit Agents +10.6

10.0

18.0

Identity / ProvenanceLiveKit Agents +7.2

10.8

14.0

TransparencyLiveKit Agents +2.1

11.9

20.0

MaintenanceLiveKit Agents +3.0

17.0

18.1

AdoptionLiveKit Agents +8.4

9.7

+1.5

Runtime calibrationLiveKit Agents +3.1

-1.6

Full evidence table

An independent, evidence-based trust comparison of LiveKit Agents and TEN Framework, two Voice & Conversational projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal	LiveKit Agentslivekit/agents	TEN FrameworkTEN-framework/ten-framework
HVTrust score	92.2	57.8
Evidence grade	A	C
Coverage grade	B	C
Overall rank	#10	#765
Rank in Voice & Conversational	#1	#9
GitHub stars	15.1k	11.2k
Last updated	today	today
Build provenance	Yes	No
OSSF Scorecard	6.5 / 10	4.0 / 10
License	Apache-2.0	NOASSERTION
Downloads	1.1M/wk	—
Trust dimensions (points earned)
Safety / integrity / 25	20.6	10.0
Identity & provenance / 18	18.0	10.8
Transparency / 17	14.0	11.9
Maintenance / 20	20.0	17.0
Adoption / 20	18.1	9.7
Runtime capability surface (full matrix)
MCP server	Implemented	—
External providers	1 — OpenAI	1 — OpenAI
Requires API keys	Yes	Yes
Plugin surface	plugins	extensions
Provenance drift	Match	—

Open in the live compare tool → LiveKit Agents profile TEN Framework profile More Voice & Conversational →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →