Is Agenta safe to use?

Agenta has an HVTrust score of 70.8/100 (Grade B), ranked #127 of 1308 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for Agenta?

Agenta scores 70.8/100 on HVTracker's evidence-weighted HVTrust scale. It has 4.5k GitHub stars and is categorized under Observability & Evaluation.

Agenta

Agenta-AI/agenta

Agenta is a workspace where you and your team build agents and automations.

Observability & Evaluation TypeScript Grade B Listed NOASSERTION

70.8/100

Rank #127 of 1308

Compare Agenta

How does it stack up against its Observability & Evaluation neighbours?

Pick any agent to compare →

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

2026-08-25 · 0d ago

Recent change

Rank +1

Is Agenta safe? Agenta scores 70.8/100 (Grade B), ranked #127 of 1308 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 6.7/10; 30% of recent commits are signed; last pushed 2026-08-25. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Observability & Evaluation

#7 LangWatch — 75.7 (B) → #8 Arize Phoenix — 74.6 (B) → #10 DeepEval — 70.7 (B) → #11 Giskard — 70.2 (B) →

Quick Trust Read

What Would Improve It

Publish package provenance or release attestations for stronger supply-chain evidence.

Recent Changes

2026-08-23

Rank Moved

Rank dropped 11 spots (#118 → #129)

2026-08-22

Rank Moved

Rank rose 11 spots (#129 → #118)

2026-08-13

Rank Moved

Rank dropped 13 spots (#123 → #136)

Maintainer Checklist

Raise Scorecard signals Current OSSF Scorecard is 6.7/10. 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.

Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.

Compare with another agent Get email alerts for Agenta View Observability & Evaluation Report missing data

84.9

Activity sub-score · out of 100

In Observability & Evaluation

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 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 →

Rank Trend

2026-08-11 2026-08-25

Activity & Reach

Stars

4.5k

Forks

639

Last Push

2026-08-25

today

Commits (4 wk)

2390

Downloads (7d)

5,962

pypi

HN mentions (30d)

2134

Open Issues

163

Rank Change

▲9

was #136

Analysis

HVTrust Dimensions vs Observability & Evaluation

70.8 / 100 · 100.0% confidence

Agenta Observability & Evaluation average (23 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits

9.9 / 25

1.0 below avg 10.9

Identity / Provenance60% listing status · 40% build provenance

10.8 / 18

2.2 below avg 13.0

Transparency50% declared license · 50% OSSF Scorecard

14.2 / 17

2.3 above avg 11.9

Maintenance60% last-push freshness · 40% commit activity

20.0 / 20

5.1 above avg 14.9

AdoptionLog-scaled stars · package downloads

13.8 / 20

in line with avg 14.0

Activity Inputs

84.9 / 100

StarsRepository reach

21.9 / 30

FreshnessLast push recency

25.0 / 25

ActivityRecent commits

25 / 25

CommunityFork signal

13.0 / 20

Supply Chain Trust

Package Provenance

None

No package attestations found

OSSF Scorecard

6.7 / 10

OpenSSF Scorecard · scanned Jul 19, 2026 (refresh pending)

Signed Commits

30%

of last 100 commits verified

Binary-Artifacts 10

Branch-Protection 3

CI-Tests 10

CII-Best-Practices 0

Code-Review 4

Contributors 10

Dangerous-Workflow -1

Dependency-Update-Tool 10

Fuzzing 0

License 9

Maintained 10

Packaging -1

Pinned-Dependencies -1

SAST 9

Security-Policy 0

Signed-Releases -1

Token-Permissions -1

Vulnerabilities 10

Is Agenta safe?

Agenta 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 Agenta publish package provenance?

No published build provenance is currently detected for Agenta. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.

Does Agenta have an OpenSSF Scorecard?

Agenta has an OpenSSF Scorecard score of 6.7/10. 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 Agenta actively maintained?

Actively maintained. The repository was pushed to within the last 1 day(s).

What license does Agenta use?

Agenta ships under NOASSERTION. A declared, OSI-approved license is one of the transparency signals HVTrust scores.

Are Agenta's commits signed?

30% of the last 100 commits to Agenta 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.

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

3 detected

Public provider/service dependencies detected.

Credential signal: No explicit API-key/config marker detected.

Tool / Plugin Surface

high confidence

Extensions

Extension based plugin/integration surface detected.

database

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 Agenta'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.

2026-08-12

Tool Surface Changed

Detected tool/plugin surface changed: declared → extension-based

2026-07-22

Provider Removed

Runtime surface shrank — no longer detected: Amazon Bedrock, Google Gemini

2026-07-17

Provider Added

Runtime surface grew — new detected provider dependency: Google Gemini

Maintain Agenta?

For maintainers

HVTrust scores Agenta 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.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history

2026-08-23

Rank Moved

Rank dropped 11 spots (#118 → #129)

2026-08-22

Rank Moved

Rank rose 11 spots (#129 → #118)

2026-08-13

Rank Moved

Rank dropped 13 spots (#123 → #136)

2026-08-12

Tool Surface Changed

Detected tool/plugin surface changed: declared → extension-based

2026-08-08

Rank Moved

Rank dropped 22 spots (#113 → #135)

2026-07-28

Rank Moved

Rank rose 10 spots (#101 → #91)

2026-07-23

Rank Moved

Rank dropped 17 spots (#92 → #109)

2026-07-22

Provider Removed

Runtime surface shrank — no longer detected: Amazon Bedrock, Google Gemini

2026-07-22

Rank Moved

Rank rose 10 spots (#102 → #92)

2026-07-20

Rank Moved

Rank rose 12 spots (#119 → #107)

2026-07-19

Scorecard Added

OSSF Scorecard: 6.7/10

2026-07-19

Grade Changed

Trust grade D → B

2026-07-19

Rank Moved

Rank rose 237 spots (#356 → #119)

2026-07-19

HVTrust Changed

HVTrust up 27.4pts (41.3 → 68.7)

2026-07-17

Provider Added

Runtime surface grew — new detected provider dependency: Google Gemini

2026-07-15

Rank Moved

Rank dropped 30 spots (#318 → #348)

2026-07-14

Rank Moved

Rank dropped 23 spots (#295 → #318)

2026-07-13

Rank Moved

Rank dropped 29 spots (#266 → #295)

2026-06-24

Rank Moved

Rank dropped 33 spots (#245 → #278)

2026-06-23

Rank Moved

Rank dropped 19 spots (#226 → #245)

2026-06-22

Rank Moved

Rank dropped 10 spots (#216 → #226)

2026-06-21

Rank Moved

Rank dropped 14 spots (#202 → #216)

2026-06-18

Rank Moved

Rank dropped 14 spots (#179 → #193)

2026-06-02

Rank Moved

Rank dropped 13 spots (#154 → #167)

2026-06-01

Rank Moved

Rank dropped 17 spots (#137 → #154)

2026-05-29

HVTrust Changed

HVTrust up 7.4pts (30.8 → 38.2)

GitHub → PyPI: agenta

Embed Badge Badge guide for maintainers →

For maintainers

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

Other agents in Observability & Evaluation

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.3 · Raw JSON