Browser Harness

Browser Harness | Self-healing harness that enables LLMs to complete any task.

Browser & Computer Use Python Grade D Listed MIT
Compare → Suggest correction
Listing state
Listed
HVTrust
47.2/100 · Grade D
Evidence coverage
Grade C · 2/5 signals
Last push
2026-07-14 · 1d ago
Recent change
New

Is Browser Harness safe? Browser Harness scores 47.2/100 (Grade D), ranked #297 of 417 tracked open-source AI agent projects, on evidence coverage C (2 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; no OSSF Scorecard result yet; 52% of recent commits are signed; last pushed 2026-07-14. Every point is earned from checkable signals — never paid placement. How scoring works →

Quick Trust Read

Verdict
Thin or incomplete trust evidence. Review carefully before production use.
47.2/100 · Grade D
Strongest Signal
Identity / Provenance
18.0/18
Weakest Signal
Safety / Integrity
10.1/25
What Would Improve It
Add or improve OSSF Scorecard coverage so safety checks are easier to verify.
Recent Changes
2026-07-14
Newly Listed
First tracked at rank #297
Maintainer Checklist
Add Scorecard coverage Expose the repository to OpenSSF Scorecard checks so supply-chain posture is easier to verify.
85.9
Activity Score · out of 100
47.2
HVTrust Score · out of 100
#297
Global Rank · of 417
#14

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade D reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage C is separate — it grades how many independent signal types back the score (2 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-07-15 01:30 UTC · Repo last pushed yesterday

Rank Trend

2026-07-14 2026-07-15

Activity & Reach

Stars
16.0k
Forks
1.5k
Last Push
2026-07-14
yesterday
Commits (4 wk)
46
Downloads (7d)
HN mentions (30d)
Open Issues
15
Rank Change
=
was #297

Analysis

HVTrust Dimensions

47.2 / 100 · 67.0% confidence
Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
10.1 / 25
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
Transparency50% declared license · 50% OSSF Scorecard
8.5 / 17
Maintenance60% last-push freshness · 40% commit activity
18.6 / 20
Adoption60% stars · 40% downloads, log-scaled
10.1 / 20

Activity Inputs

85.9 / 100
StarsRepository reach
25.2 / 30
FreshnessLast push recency
24.9 / 25
ActivityRecent commits
20.9 / 25
CommunityFork signal
14.8 / 20

Supply Chain Trust

Package Provenance
Verified
pypi attestation
OSSF Scorecard
Not available
Signed Commits
52%
of last 100 commits verified

Is Browser Harness safe?

Public trust evidence for Browser Harness is thin: several supply-chain signals are missing or weak. This does not mean the project is unsafe — it means an outside observer cannot easily verify the usual integrity checks. Treat with extra scrutiny.
Does Browser Harness publish package provenance?
Yes. Browser Harness's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does Browser Harness have an OpenSSF Scorecard?
No OpenSSF Scorecard data is currently published for Browser Harness. Maintainers can enable the Scorecard GitHub Action to get a public score; without it, automated supply-chain hygiene is harder for outsiders to verify.
Is Browser Harness actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does Browser Harness use?
Browser Harness ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Browser Harness's commits signed?
52% of the last 100 commits to Browser Harness 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
None detected
No MCP server signal detected.
Detailed evidence is not shown in the public view.
External Service Dependencies
None detected
No clear third-party provider dependency detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
medium confidence
Declared
Declared plugin/integration surface detected.
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

Maintain Browser Harness?

HVTrust scores Browser Harness 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

Listed 1
2026-07-14
Newly Listed
First tracked at rank #297

Embed Badge Badge guide for maintainers →

HVTrust 47.2 Grade D
Markdown:
[![HVTrust](https://hvtracker.net/badge/browser-harness.svg)](https://hvtracker.net/agents/browser-harness)
HTML:
<a href="https://hvtracker.net/agents/browser-harness"><img src="https://hvtracker.net/badge/browser-harness.svg" alt="HVTrust"></a>

Other agents in Browser & Computer Use

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