Browser Use vs Peekaboo
Both are Grade A and 2.3 points apart, so choose on what you weigh most. Browser Use leads on maintenance and adoption, and rests on broader evidence; Peekaboo leads on supply-chain integrity and transparency. Note: Peekaboo's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
Choose Browser Use if maintenance and adoption matter most.
- +6.6Adoption: 2.1M weekly downloads against 2.3k
- +0.5Maintenance: last push today, against 1d ago
- A vs BEvidence coverage: 4 of 5 independent signal types, against 3
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Choose Peekaboo if supply-chain integrity and transparency matter most.
- +6.8Safety / Integrity: 100% of recent commits signed, against 11%
- +1.6Transparency: OSSF Scorecard 6.8 against 4.9
Where they differ
1 dimension identical: Identity 18.0 · Full evidence table
An independent, evidence-based trust comparison of Browser Use and Peekaboo, 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 Usebrowser-use/browser-use | Peekabooopenclaw/Peekaboo |
|---|---|---|
| HVTrust score | 87.4 | 89.7 |
| Evidence grade | A | A |
| Coverage grade | A | B |
| Overall rank | #68 | #35 |
| Rank in Browser & Computer Use | #8 | #6 |
| GitHub stars | 121.0k | 5.5k |
| Last updated | today | 1d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 4.9 / 10 | 6.8 / 10 |
| License | MIT | MIT |
| Downloads | 2.1M/wk | 2k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 14.2 | 21.0 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 12.7 | 14.3 |
| Maintenance / 20 | 20.0 | 19.5 |
| Adoption / 20 | 20.0 | 13.4 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 3 — Anthropic, Google Gemini, OpenAI | — |
| Requires API keys | Yes | No |
| Plugin surface | — | extensions |
| Provenance drift | Match | 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 →