Is CrewAI safe to use?

CrewAI has an HVTrust score of 81.7/100 (Grade A), ranked #61 of 1204 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for CrewAI?

CrewAI scores 81.7/100 on HVTracker's evidence-weighted HVTrust scale. It has 56.9k GitHub stars and is categorized under Agent Frameworks.

CrewAI

CrewAIInc/crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers

Agent Frameworks Python Grade A Listed MIT

81.7/100

Rank #61 of 1204

Compare CrewAI

How does it stack up against its Agent Frameworks neighbours?

Pick any agent to compare →

Strong public trust posture, backed by multiple independent signals.

Open compare tool Suggest correction

Listing state

Listed

Evidence coverage

Grade A · 4/5 signals

Last push

2026-08-09 · 0d ago

Recent change

Tool Surface Changed +2

Is CrewAI safe? CrewAI scores 81.7/100 (Grade A), ranked #61 of 1204 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 7.9/10; 100% of recent commits are signed; last pushed 2026-08-09. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Agent Frameworks

#10 OpenAI Agents SDK — 84.7 (A) → #11 LangChain — 81.9 (A) → #13 Deep Agents — 78.2 (B) → #14 Agent Governance Toolkit — 76.1 (B) →

Quick Trust Read

What Would Improve It

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

Recent Changes

2026-08-07

Tool Surface Changed

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

2026-08-07

Provider Removed

Runtime surface shrank — no longer detected: Postgres

2026-08-07

Provider Added

Runtime surface grew — new detected provider dependencies: Google Gemini, Multi-provider (LiteLLM)

Maintainer Checklist

Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.

Compare with another agent Get email alerts for CrewAI View Agent Frameworks Report missing data

96.6

Activity sub-score · out of 100

#12

In Agent Frameworks

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A 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 →

Activity & Reach

Stars

56.9k

Forks

8.1k

Last Push

2026-08-09

today

Commits (4 wk)

Downloads (7d)

2,371,417

pypi

HN mentions (30d)

Open Issues

103

Rank Change

▲2

was #63

Analysis

HVTrust Dimensions vs Agent Frameworks

81.7 / 100 · 100.0% confidence

CrewAI Agent Frameworks average (117 agents)

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

14.9 / 25

6.7 above avg 8.2

Identity / Provenance60% listing status · 40% build provenance

10.8 / 18

0.8 below avg 11.6

Transparency50% declared license · 50% OSSF Scorecard

15.2 / 17

3.6 above avg 11.6

Maintenance60% last-push freshness · 40% commit activity

20.0 / 20

5.7 above avg 14.3

AdoptionLog-scaled stars · package downloads

19.9 / 20

8.5 above avg 11.4

Activity Inputs

96.6 / 100

StarsRepository reach

28.5 / 30

FreshnessLast push recency

25.0 / 25

ActivityRecent commits

24.9 / 25

CommunityFork signal

18.2 / 20

Supply Chain Trust

Package Provenance

None

No package attestations found

OSSF Scorecard

7.9 / 10

OpenSSF Scorecard · scanned Aug 9, 2026

Signed Commits

100%

of last 100 commits verified

Binary-Artifacts 10

Branch-Protection 8

CI-Tests 10

CII-Best-Practices 0

Code-Review 10

Contributors 10

Dangerous-Workflow 10

Dependency-Update-Tool 10

Fuzzing 0

License 10

Maintained 10

Packaging -1

Pinned-Dependencies 9

SAST 9

Security-Policy 10

Signed-Releases -1

Token-Permissions 0

Vulnerabilities 7

Is CrewAI safe?

Public supply-chain signals for CrewAI are strong: it has multiple independent trust indicators in place. This does not replace your own security review, but CrewAI carries less obvious unverified-evidence risk than projects with thin signals.

Does CrewAI publish package provenance?

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

Does CrewAI have an OpenSSF Scorecard?

CrewAI has an OpenSSF Scorecard score of 7.9/10. 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 CrewAI actively maintained?

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

What license does CrewAI use?

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

Are CrewAI's commits signed?

100% of the last 100 commits to CrewAI 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

high confidence

Implemented

CrewAI appears to expose MCP server capabilities.

Detailed evidence is not shown in the public view.

External Service Dependencies

high confidence

7 detected

Public provider/service dependencies detected.

Credential signal: API keys or service config markers documented.

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 CrewAI'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.

2026-08-07

Tool Surface Changed

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

2026-08-07

Provider Removed

Runtime surface shrank — no longer detected: Postgres

2026-08-07

Provider Added

Runtime surface grew — new detected provider dependencies: Google Gemini, Multi-provider (LiteLLM)

2026-06-05

Tool Surface Changed

Detected tool/plugin surface changed: none → marketplace

2026-06-05

Provider Added

Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, OpenAI, Postgres, Qdrant, Redis

2026-06-05

Mcp Status Changed

Detected MCP server support changed: none → implemented

Maintain CrewAI?

For maintainers

HVTrust scores CrewAI 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

2026-08-07

Tool Surface Changed

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

2026-08-07

Provider Removed

Runtime surface shrank — no longer detected: Postgres

2026-08-07

Provider Added

Runtime surface grew — new detected provider dependencies: Google Gemini, Multi-provider (LiteLLM)

2026-06-23

Grade Changed

Trust grade B → A

2026-06-21

Grade Changed

Trust grade A → B

2026-06-05

Tool Surface Changed

Detected tool/plugin surface changed: none → marketplace

2026-06-05

Provider Added

Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, OpenAI, Postgres, Qdrant, Redis

2026-06-05

Mcp Status Changed

Detected MCP server support changed: none → implemented

2026-05-29

HVTrust Changed

HVTrust up 9.9pts (68.0 → 77.9)

2026-05-28

Activity Score Changed

Activity score up 25pts (71 → 96)

2026-05-27

Scorecard Added

OSSF Scorecard: 8.0/10

2026-05-27

Grade Changed

Trust grade C → B

2026-05-27

HVTrust Changed

HVTrust up 20.6pts (53.3 → 73.9)

2026-05-25

Rank Moved

Rank dropped 15 spots (#18 → #33)

GitHub → PyPI: crewai

Embed Badge Badge guide for maintainers →

For maintainers

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

Other agents in Agent Frameworks

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 v4.2 · Raw JSON