ClawRouter vs Jan
Both are Grade C and 1.5 points apart, so choose on what you weigh most. ClawRouter leads on transparency; Jan leads on supply-chain integrity and adoption, and rests on broader evidence.
The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.
Choose ClawRouter if transparency matters most.
- +1.2Transparency: OSSF Scorecard 6.0 against 4.6
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
Choose Jan if supply-chain integrity and adoption matter most.
- +2.0Adoption: 45.5k GitHub stars against 6.7k
- +0.6Safety / Integrity: 100% of recent commits signed, against 53%
- B vs CEvidence coverage: 3 of 5 independent signal types, against 2
Where they differ
2 dimensions identical: Identity 10.8 · Maintenance 20.0 · Full evidence table
An independent, evidence-based trust comparison of ClawRouter and Jan, two LLM Gateways & Infra projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | ClawRouterBlockRunAI/ClawRouter | Janjanhq/jan |
|---|---|---|
| HVTrust score | 62.8 | 64.3 |
| Evidence grade | C | C |
| Coverage grade | C | B |
| Overall rank | #613 | #550 |
| Rank in LLM Gateways & Infra | #9 | #7 |
| GitHub stars | 6.7k | 45.5k |
| Last updated | today | today |
| Build provenance | No | No |
| OSSF Scorecard | 6.0 / 10 | 4.6 / 10 |
| License | MIT | NOASSERTION |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 10.2 | 10.8 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 13.6 | 12.4 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 9.2 | 11.2 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Declared |
| External providers | 1 — DeepSeek | — |
| Requires API keys | Yes | No |
| Plugin surface | — | extensions |
| Provenance drift | — | — |
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 →