BrowserGym agents

🌎💪 BrowserGym, a Gym environment for web task automation

Browser & Computer Use Python Grade C Listed NOASSERTION
56.1/100
Rank #377 of 1204
Compare BrowserGym agents

Promising trust profile, but some evidence still deserves review.

Open compare tool Suggest correction
Listing state
Listed
Evidence coverage
Grade A · 4/5 signals
Last push
2026-07-17 · 23d ago
Recent change
Rank

Is BrowserGym agents safe? BrowserGym agents scores 56.1/100 (Grade C), ranked #377 of 1204 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; no OSSF Scorecard result yet; recent commits are unsigned; last pushed 2026-07-17. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Browser & Computer Use

Quick Trust Read

What Would Improve It
Add or improve OSSF Scorecard coverage so safety checks are easier to verify.
Recent Changes
2026-08-08
Rank Moved
Rank dropped 95 spots (#282 → #377)
2026-07-17
Activity Resumed
Activity resumed
2026-07-17
Grade Changed
Trust grade D → C
Maintainer Checklist
Add Scorecard coverage Expose the repository to OpenSSF Scorecard checks so supply-chain posture is easier to verify.
Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.
51.1
Activity sub-score · out of 100
#11

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade C reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-08-09 19:31 UTC · Repo last pushed 23 days ago

Activity & Reach

Stars
1.3k
Forks
189
Last Push
2026-07-17
23 days ago
Commits (4 wk)
0
Downloads (7d)
6,860
pypi
HN mentions (30d)
0
Open Issues
18
Rank Change
=
was #377

Analysis

HVTrust Dimensions vs Browser & Computer Use

56.1 / 100 · 100.0% confidence

BrowserGym agents Browser & Computer Use average (34 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
7.5 / 25
in line with avg 7.8
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
5.9 above avg 12.1
Transparency50% declared license · 50% OSSF Scorecard
8.5 / 17
2.7 below avg 11.2
Maintenance60% last-push freshness · 40% commit activity
10.5 / 20
1.5 below avg 12.0
AdoptionLog-scaled stars · package downloads
12.6 / 20
1.8 above avg 10.8

Activity Inputs

51.1 / 100
StarsRepository reach
18.7 / 30
FreshnessLast push recency
21.8 / 25
ActivityRecent commits
0.0 / 25
CommunityFork signal
10.6 / 20

Supply Chain Trust

Package Provenance
Verified
pypi attestation
OSSF Scorecard
Not available
Signed Commits
Unable to query

Is BrowserGym agents safe?

BrowserGym agents 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 BrowserGym agents publish package provenance?
Yes. BrowserGym agents's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does BrowserGym agents have an OpenSSF Scorecard?
No OpenSSF Scorecard data is currently published for BrowserGym agents. 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 BrowserGym agents actively maintained?
Maintained. Last push was 23 days ago.
What license does BrowserGym agents use?
BrowserGym agents ships under NOASSERTION. A declared, OSI-approved license is one of the transparency signals HVTrust scores.

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.

AI agent surface

MCP, providers, tool 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
medium confidence
Declared
MCP support appears present, but direct server implementation is less certain.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
1 detected
Public provider/service dependencies detected.
Credential signal: API keys or service config markers documented.
Tool / Plugin Surface
None detected
No clear plugin system or broad tool surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
low confidence
Unknown
Package source metadata is missing or inconclusive
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 BrowserGym agents'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.

2026-07-17
Activity Resumed
Activity resumed
2026-06-15
Activity Went Stale
No commits for 90 days
2026-06-05
Provider Added
Runtime surface grew — new detected provider dependency: OpenAI
2026-06-05
Mcp Status Changed
Detected MCP server support changed: none → declared

Maintain BrowserGym agents?

For maintainers

HVTrust scores BrowserGym agents 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

Signal history
Rank 10HVTrust 4Listed 1MCP 1Surface 1Stale 1Score 1Grade 1Fresh 1
2026-08-08
Rank Moved
Rank dropped 95 spots (#282 → #377)
2026-07-17
Activity Resumed
Activity resumed
2026-07-17
Grade Changed
Trust grade D → C
2026-07-17
Rank Moved
Rank rose 65 spots (#311 → #246)
2026-07-17
HVTrust Changed
HVTrust up 8.1pts (48.9 → 57.0)
2026-07-17
Activity Score Changed
Activity score up 17pts (37 → 54)
2026-07-15
Rank Moved
Rank dropped 22 spots (#287 → #309)
2026-07-14
Rank Moved
Rank dropped 13 spots (#274 → #287)
2026-07-13
Rank Moved
Rank dropped 34 spots (#240 → #274)
2026-06-24
Rank Moved
Rank dropped 28 spots (#195 → #223)
2026-06-23
Rank Moved
Rank dropped 12 spots (#183 → #195)
2026-06-20
Rank Moved
Rank dropped 13 spots (#153 → #166)
2026-06-20
HVTrust Changed
HVTrust down 4.7pts (57.0 → 52.3)
2026-06-18
Rank Moved
Rank dropped 13 spots (#136 → #149)
2026-06-15
Activity Went Stale
No commits for 90 days
2026-06-05
Provider Added
Runtime surface grew — new detected provider dependency: OpenAI
2026-06-05
Mcp Status Changed
Detected MCP server support changed: none → declared
2026-06-01
Rank Moved
Rank dropped 13 spots (#98 → #111)
2026-05-29
HVTrust Changed
HVTrust up 9.9pts (48.2 → 58.1)
2026-05-27
HVTrust Changed
HVTrust up 4.7pts (34.1 → 38.8)
2026-05-25
Newly Listed
First tracked at rank #139

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 56.1 Grade C
Markdown:
[![HVTrust](https://hvtracker.net/badge/browsergym-agents.svg)](https://hvtracker.net/agents/browsergym-agents)
HTML:
<a href="https://hvtracker.net/agents/browsergym-agents"><img src="https://hvtracker.net/badge/browsergym-agents.svg" alt="HVTrust"></a>

Other agents in Browser & Computer Use

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