Is Agency Swarm safe to use?

Agency Swarm has an HVTrust score of 65.6/100 (Grade B), ranked #202 of 1204 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for Agency Swarm?

Agency Swarm scores 65.6/100 on HVTracker's evidence-weighted HVTrust scale. It has 4.5k GitHub stars and is categorized under Multi-Agent Systems.

Agency Swarm

VRSEN/agency-swarm

Reliable Multi-Agent Orchestration Framework

Multi-Agent Systems Python Grade B Listed MIT

65.6/100

Rank #202 of 1204

Compare Agency Swarm

How does it stack up against its Multi-Agent Systems 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

2026-08-03 · 6d ago

Recent change

Rank +2

Is Agency Swarm safe? Agency Swarm scores 65.6/100 (Grade B), ranked #202 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 4.4/10; 33% of recent commits are signed; last pushed 2026-08-03. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Multi-Agent Systems

#2 Solace Agent Mesh — 78.5 (B) → #3 CAMEL — 69.0 (B) → #5 Multica — 64.9 (C) → #6 Ruflo — 64.5 (C) →

Quick Trust Read

What Would Improve It

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

Recent Changes

2026-08-08

Rank Moved

Rank dropped 36 spots (#163 → #199)

2026-08-07

Provider Removed

Runtime surface shrank — no longer detected: Anthropic, Azure OpenAI, Google Gemini

2026-08-07

Provider Added

Runtime surface grew — new detected provider dependency: Multi-provider (LiteLLM)

Maintainer Checklist

Raise Scorecard signals Current OSSF Scorecard is 4.4/10. 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 AIPass Get email alerts for Agency Swarm View Multi-Agent Systems Report missing data

79.3

Activity sub-score · out of 100

In Multi-Agent Systems

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 →

Activity & Reach

Stars

4.5k

Forks

1.1k

Last Push

2026-08-03

6 days ago

Commits (4 wk)

Downloads (7d)

10,838

pypi

HN mentions (30d)

Open Issues

Rank Change

▼3

was #199

Analysis

HVTrust Dimensions vs Multi-Agent Systems

65.6 / 100 · 100.0% confidence

Agency Swarm Multi-Agent Systems average (32 agents)

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

7.2 / 25

in line with avg 6.8

Identity / Provenance60% listing status · 40% build provenance

10.8 / 18

in line with avg 11.2

Transparency50% declared license · 50% OSSF Scorecard

12.2 / 17

1.0 above avg 11.2

Maintenance60% last-push freshness · 40% commit activity

17.7 / 20

4.8 above avg 12.9

AdoptionLog-scaled stars · package downloads

14.2 / 20

4.1 above avg 10.1

Activity Inputs

79.3 / 100

StarsRepository reach

21.9 / 30

FreshnessLast push recency

24.2 / 25

ActivityRecent commits

19.1 / 25

CommunityFork signal

14.1 / 20

Supply Chain Trust

Package Provenance

None

No package attestations found

OSSF Scorecard

4.4 / 10

OpenSSF Scorecard · scanned Aug 9, 2026

Signed Commits

33%

of last 100 commits verified

Binary-Artifacts 10

Branch-Protection 0

CI-Tests 7

CII-Best-Practices 0

Code-Review 0

Contributors 6

Dangerous-Workflow 10

Dependency-Update-Tool 10

Fuzzing 0

License 10

Maintained 10

Packaging 10

Pinned-Dependencies 0

SAST 0

Security-Policy 0

Signed-Releases -1

Token-Permissions 0

Vulnerabilities 0

Is Agency Swarm safe?

Agency Swarm 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 Agency Swarm publish package provenance?

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

Does Agency Swarm have an OpenSSF Scorecard?

Agency Swarm has an OpenSSF Scorecard score of 4.4/10. 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 Agency Swarm actively maintained?

Actively maintained. The repository was pushed to within the last 6 day(s).

What license does Agency Swarm use?

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

Are Agency Swarm's commits signed?

33% of the last 100 commits to Agency Swarm 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.

Compare Agency Swarm head-to-head

Agency Swarm vs AIPass → Agency Swarm vs Solace Agent Mesh → Agency Swarm vs CAMEL →

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

Agency Swarm appears to expose MCP server capabilities.

Detailed evidence is not shown in the public view.

External Service Dependencies

high confidence

2 detected

Public provider/service dependencies detected.

Credential signal: API keys or service config markers documented.

Tool / Plugin Surface

medium confidence

Marketplace

Marketplace 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

How this surface has changed

Detected changes to Agency Swarm'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

Provider Removed

Runtime surface shrank — no longer detected: Anthropic, Azure OpenAI, Google Gemini

2026-08-07

Provider Added

Runtime surface grew — new detected provider dependency: 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: Anthropic, Azure OpenAI, Google Gemini, OpenAI

2026-06-05

Mcp Status Changed

Detected MCP server support changed: none → implemented

Maintain Agency Swarm?

For maintainers

HVTrust scores Agency Swarm 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

2026-08-08

Rank Moved

Rank dropped 36 spots (#163 → #199)

2026-08-07

Provider Removed

Runtime surface shrank — no longer detected: Anthropic, Azure OpenAI, Google Gemini

2026-08-07

Provider Added

Runtime surface grew — new detected provider dependency: Multi-provider (LiteLLM)

2026-07-24

Grade Changed

Trust grade B → C

2026-07-13

Rank Moved

Rank dropped 17 spots (#116 → #133)

2026-06-20

Grade Changed

Trust grade B → C

2026-06-10

Grade Changed

Trust grade C → B

2026-06-10

Rank Moved

Rank rose 16 spots (#116 → #100)

2026-06-10

HVTrust Changed

HVTrust up 4.1pts (61.7 → 65.8)

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: Anthropic, Azure OpenAI, Google Gemini, OpenAI

2026-06-05

Mcp Status Changed

Detected MCP server support changed: none → implemented

2026-06-01

Rank Moved

Rank dropped 12 spots (#86 → #98)

2026-05-29

Rank Moved

Rank dropped 39 spots (#51 → #90)

2026-05-28

Activity Score Changed

Activity score up 20pts (61 → 82)

2026-05-27

Scorecard Added

OSSF Scorecard: 3.7/10

2026-05-27

Grade Changed

Trust grade C → B

2026-05-27

HVTrust Changed

HVTrust up 24.1pts (42.8 → 66.9)

2026-05-25

Newly Listed

First tracked at rank #106

GitHub → PyPI: agency-swarm

Embed Badge Badge guide for maintainers →

For maintainers

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

Other agents in Multi-Agent Systems

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