Bolna vs Rasa
Both are Grade C and 2.0 points apart, so choose on what you weigh most. Bolna leads on supply-chain integrity and maintenance; Rasa leads on adoption and rests on broader evidence. Note: Bolna's evidence coverage is thinner (coverage C vs A) — its score rests on fewer independent signal types.
Conversational voice AI agents
Choose Bolna if supply-chain integrity and maintenance matter most.
- +14.6Maintenance: last push 3d ago, against 121d ago
- +2.3Safety / Integrity: 100% of recent commits signed, against 59%
💬 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 adoption matters most.
- +9.2Adoption: 21.4k GitHub stars against 831
- A vs CEvidence coverage: 4 of 5 independent signal types, against 2
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of Bolna and Rasa, 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 | Bolnabolna-ai/bolna | RasaRasaHQ/rasa |
|---|---|---|
| HVTrust score | 57.6 | 55.6 |
| Evidence grade | C | C |
| Coverage grade | C | A |
| Overall rank | #781 | #849 |
| Rank in Voice & Conversational | #8 | #10 |
| GitHub stars | 831 | 21.4k |
| Last updated | 3d ago | 121d ago |
| Build provenance | No | No |
| OSSF Scorecard | 5.5 / 10 | 5.3 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | — | 23k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 11.9 | 9.6 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 13.2 | 13.0 |
| Maintenance / 20 | 18.5 | 3.9 |
| Adoption / 20 | 7.0 | 16.2 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | — |
| External providers | 6 — ElevenLabs, Google Gemini, Groq, … | 3 — Amazon Bedrock, Postgres, Redis |
| Requires API keys | Yes | No |
| Plugin surface | — | plugins |
| 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 →