Registry › Compare › Rasa vs TEN Framework

Rasa vs TEN Framework

Both are Grade C and 2.3 points apart, so choose on what you weigh most. Rasa leads on transparency and adoption, and rests on broader evidence; TEN Framework leads on maintenance. Note: TEN Framework's evidence coverage is thinner (coverage C vs A) — its score rests on fewer independent signal types.

C Rasa 55.6

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

RasaHQ/rasa · #849 overall · #10 Voice & Conversational · coverage A (4/5)

Choose Rasa if transparency and adoption matter most.

  • +6.5Adoption: 21.4k GitHub stars against 11.2k
  • +1.1Transparency: OSSF Scorecard 5.3 against 4.0
  • A vs CEvidence coverage: 4 of 5 independent signal types, against 2
C TEN Framework 57.9

Open-source framework for conversational voice AI agents

TEN-framework/ten-framework · #771 overall · #7 Voice & Conversational · coverage C (2/5)

Choose TEN Framework if maintenance matters most.

  • +13.2Maintenance: last push 2d ago, against 121d ago

Where they differ

9.6
Safety / IntegrityTEN Framework +0.4
10.0
13.0
TransparencyRasa +1.1
11.9
3.9
MaintenanceTEN Framework +13.2
17.1
16.2
AdoptionRasa +6.5
9.7
+2.1
Runtime calibrationRasa +3.7
-1.6

1 dimension identical: Identity 10.8 · Full evidence table

An independent, evidence-based trust comparison of Rasa 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 RasaRasaHQ/rasa TEN FrameworkTEN-framework/ten-framework
HVTrust score 55.6 57.9
Evidence grade C C
Coverage grade A C
Overall rank #849 #771
Rank in Voice & Conversational #10 #7
GitHub stars 21.4k 11.2k
Last updated 121d ago 2d ago
Build provenance No No
OSSF Scorecard 5.3 / 10 4.0 / 10
License Apache-2.0 NOASSERTION
Downloads 23k/wk —
Trust dimensions (points earned)
Safety / integrity / 25 9.6 10.0
Identity & provenance / 18 10.8 10.8
Transparency / 17 13.0 11.9
Maintenance / 20 3.9 17.1
Adoption / 20 16.2 9.7
Runtime capability surface (full matrix)
MCP server — —
External providers 3 — Amazon Bedrock, Postgres, Redis 1 — OpenAI
Requires API keys No Yes
Plugin surface plugins extensions
Provenance drift Match —
Open in the live compare tool → Rasa 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 →