Cua

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that

Browser & Computer Use HTML Grade B Listed MIT
Compare → Suggest correction
Listing state
Listed
HVTrust
68.7/100 · Grade B
Evidence coverage
Grade B · 3/5 signals
Last push
2026-07-11 · 0d ago
Recent change
No recent signal change

Is Cua safe? Cua scores 68.7/100 (Grade B), ranked #94 of 328 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 3.0/10; 65% of recent commits are signed; last pushed 2026-07-11. Every point is earned from checkable signals — never paid placement. How scoring works →

Quick Trust Read

Verdict
Promising trust profile, but some evidence still deserves review.
68.7/100 · Grade B
Strongest Signal
Maintenance
20.0/20
Weakest Signal
Safety / Integrity
7.0/25
What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 3.0/10. Tighten the weakest checks to improve public safety evidence.
Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.
90.2
Activity Score · out of 100
68.7
HVTrust Score · out of 100
#94
Global Rank · of 328
#5

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade B reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-07-11 05:00 UTC · Repo last pushed today

Rank Trend

2026-07-05 2026-07-11

Activity & Reach

Stars
19.6k
Forks
1.3k
Last Push
2026-07-11
today
Commits (4 wk)
223
Downloads (7d)
11,265
pypi
HN mentions (30d)
Open Issues
184
Rank Change
=
was #94

Analysis

HVTrust Dimensions

68.7 / 100 · 100.0% confidence
Safety / IntegrityOSSF, provenance, signatures
7.0 / 25
Identity / ProvenanceListing and build link
10.8 / 18
TransparencyLicense and public checks
11.1 / 17
MaintenanceFreshness and commits
20.0 / 20
AdoptionStars and downloads
15.7 / 20

Activity Inputs

90.2 / 100
StarsRepository reach
25.7 / 30
FreshnessLast push recency
25.0 / 25
ActivityRecent commits
25 / 25
CommunityFork signal
14.5 / 20

Supply Chain Trust

Package Provenance
None
No package attestations found
OSSF Scorecard
3.0 / 10
OpenSSF Scorecard · scanned Jul 11, 2026
Signed Commits
65%
of last 100 commits verified
Binary-Artifacts 9
Branch-Protection 5
CI-Tests 10
CII-Best-Practices 0
Code-Review 0
Contributors 10
Dangerous-Workflow 0
Dependency-Update-Tool 0
Fuzzing 0
License 10
Maintained 10
Packaging 10
Pinned-Dependencies 1
SAST 0
Security-Policy 0
Signed-Releases 0
Token-Permissions 0
Vulnerabilities 0

Is Cua safe?

Cua has a mixed signal profile. Some trust indicators are present, others are missing. Whether it is safe for your use case depends on which gaps matter to you — review the breakdown below before adopting in production.
Does Cua publish package provenance?
No published build provenance is currently detected for Cua. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does Cua have an OpenSSF Scorecard?
Cua has an OpenSSF Scorecard score of 3.0/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is Cua actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does Cua use?
Cua ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Cua's commits signed?
65% of the last 100 commits to Cua are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

Ranked neighbours in Browser & Computer Use

AI agent surface

Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
high confidence
Implemented
Cua appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
3 detected
Public provider/service dependencies detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
high confidence
3 tags
Broad capability areas detected.
  • browser
  • code
  • shell
Detailed evidence is not shown in the public view.
Package Provenance Drift
high confidence
Match
Published package metadata matches the tracked repo
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live
How this surface has changed

Detected changes to Cua's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.

2026-06-05
Provider Added
Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, OpenAI
2026-06-05
Mcp Status Changed
Detected MCP server support changed: none → implemented

Maintain Cua?

HVTrust scores Cua from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Reputation Timeline

Rank 2Listed 1HVTrust 1Grade 1Scorecard 1Score 1MCP 1Surface 1
2026-06-05
Provider Added
Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, OpenAI
2026-06-05
Mcp Status Changed
Detected MCP server support changed: none → implemented
2026-05-29
Rank Moved
Rank dropped 42 spots (#36 → #78)
2026-05-28
Activity Score Changed
Activity score up 25pts (64 → 90)
2026-05-27
Scorecard Added
OSSF Scorecard: 2.8/10
2026-05-27
Grade Changed
Trust grade D → C
2026-05-27
HVTrust Changed
HVTrust up 22.3pts (45.4 → 67.7)
2026-05-25
Rank Moved
Rank dropped 31 spots (#49 → #80)
2026-05-24
Newly Listed
First tracked at rank #49

Embed Badge Badge guide for maintainers →

HVTrust 68.7 Grade B
Markdown:
[![HVTrust](https://hvtracker.net/badge/cua.svg)](https://hvtracker.net/agents/cua)
HTML:
<a href="https://hvtracker.net/agents/cua"><img src="https://hvtracker.net/badge/cua.svg" alt="HVTrust"></a>

Other agents in Browser & Computer Use

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.2 · Raw JSON