Browser Harness vs BrowserOS
Browser Harness leads on trust: 90.5/100 (Grade A) against 66.5/100 (Grade B), a 24.0-point gap. Browser Harness leads on provenance and adoption, and rests on broader evidence; BrowserOS leads on maintenance.
Let Claude Code, Codex or Cursor use your real Chrome, logged in as you. One prompt to set up. Open source, MIT.
Choose Browser Harness if provenance and adoption matter most.
- +8.7Adoption: 19k GitHub stars against 14.3k
- +7.2Identity / Provenance: package provenance attested, against none
- +6.0Safety / Integrity: OSSF Scorecard 6.1 against 5.0
- +0.9Transparency: OSSF Scorecard 6.1 against 5.0
🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.
Choose BrowserOS if maintenance matters most.
- +0.8Maintenance
Where they differ
An independent, evidence-based trust comparison of Browser Harness and BrowserOS, two Browser & Computer Use projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | Browser Harnessbrowser-use/browser-harness | BrowserOSbrowseros-ai/BrowserOS |
|---|---|---|
| HVTrust score | 90.5 | 66.5 |
| Evidence grade | A | B |
| Coverage grade | B | C |
| Overall rank | #25 | #477 |
| Rank in Browser & Computer Use | #5 | #14 |
| GitHub stars | 19.0k | 14.3k |
| Last updated | today | today |
| Build provenance | Yes | No |
| OSSF Scorecard | 6.1 / 10 | 5.0 / 10 |
| License | MIT | AGPL-3.0 |
| Downloads | 2.2M/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 17.2 | 11.2 |
| Identity & provenance / 18 | 18.0 | 10.8 |
| Transparency / 17 | 13.7 | 12.8 |
| Maintenance / 20 | 19.2 | 20.0 |
| Adoption / 20 | 18.7 | 10.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 1 — Anthropic | 1 — Amazon Bedrock |
| Requires API keys | No | No |
| Plugin surface | plugins | 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 →