CAMEL vs Open Multi-Agent
Both are Grade C and 1.1 points apart, so choose on what you weigh most. CAMEL leads on transparency and adoption, and rests on broader evidence; Open Multi-Agent leads on supply-chain integrity and maintenance.
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Choose CAMEL if transparency and adoption matter most.
- +6.5Adoption: 18k GitHub stars against 7.1k
- +0.7Transparency: OSSF Scorecard 6.8 against 6.0
- A vs CEvidence coverage: 4 of 5 independent signal types, against 2
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
Choose Open Multi-Agent if supply-chain integrity and maintenance matter most.
- +5.8Maintenance: last push today, against 6d ago
- +1.4Safety / Integrity: 100% of recent commits signed, against 53%
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of CAMEL and Open Multi-Agent, two Multi-Agent Systems projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | CAMELcamel-ai/camel | Open Multi-Agentopen-multi-agent/open-multi-agent |
|---|---|---|
| HVTrust score | 64.0 | 62.9 |
| Evidence grade | C | C |
| Coverage grade | A | C |
| Overall rank | #577 | #617 |
| Rank in Multi-Agent Systems | #11 | #14 |
| GitHub stars | 18.0k | 7.1k |
| Last updated | 6d ago | today |
| Build provenance | No | No |
| OSSF Scorecard | 6.8 / 10 | 6.0 / 10 |
| License | Apache-2.0 | MIT |
| Downloads | 13k/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 11.1 | 12.5 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 14.3 | 13.6 |
| Maintenance / 20 | 13.0 | 18.8 |
| Adoption / 20 | 15.7 | 9.2 |
| Runtime capability surface (full matrix) | ||
| MCP server | Declared | Declared |
| External providers | 14 — Amazon Bedrock, Anthropic, Cohere, … | 3 — Anthropic, Google Gemini, OpenAI |
| Requires API keys | Yes | Yes |
| Plugin surface | — | — |
| 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 →