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.
💬 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
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
Open-source framework for conversational voice AI agents
Choose TEN Framework if maintenance matters most.
- +13.2Maintenance: last push 2d ago, against 121d ago
Where they differ
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 | — |
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 →