updated 2026-10-09 12:08 UTC

MetaGPT

Repository Website by FoundationAgents

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Multi-Agent Systems Python Listed MIT

Is MetaGPT safe? Thin or incomplete trust evidence. Review carefully before production use.

OSSF Scorecard 2.3 / 10
Provenance None
Signed commits 33%
Last push 261d ago
Compare MetaGPT

How does it stack up against its Multi-Agent Systems neighbours?

Pick any agent to compare →
Suggest a correction

In detail: MetaGPT scores 37.8/100 (Grade D), ranked #1227 of 1371 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 2.3/10; 33% of recent commits are signed; last pushed 2026-01-21. Every point is earned from checkable signals — never paid placement. How scoring works →

How MetaGPT could raise its score

Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.

Already done? Suggest a correctionAdd the trust badge

Chain of custody

Scanners check what the code says. This traces who ships MetaGPT and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.

  1. Source Partly signed

    github.com/FoundationAgents/MetaGPT, MIT, last pushed 2026-01-21. 33% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.

  2. Review and release Weak

    OpenSSF Scorecard rates the repository's practices 2.3/10 (scanned Oct 5, 2026). The checks that decide who can get a change released:

    • Code Review5
    • Branch Protection0
    • Signed Releasesn/a
    • Dangerous Workflow0
    • Token Permissions0
    • Pinned Dependencies0
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 0
    CI-Tests 1
    CII-Best-Practices 0
    Code-Review 5
    Contributors 10
    Dangerous-Workflow 0
    Dependency-Update-Tool 0
    Fuzzing 0
    License 10
    Maintained 0
    Packaging -1
    Pinned-Dependencies 0
    SAST 0
    Security-Policy 10
    Signed-Releases -1
    Token-Permissions 0
    Vulnerabilities 0

  3. Published packages Not linked

    • PyPI metagpt Source link points to this repo's current name No build attestation

    Without a build attestation, nothing proves the published files were built from this repository.

Changes to this chain

  • 2026-10-02 Provenance drift warning cleared (now: unknown)

Evidence behind this score

Coverage A: 4 of 5 independent evidence types found.

  • GitHub repository data
  • Package downloads
  • Supply-chain checks
  • Public actions (missing)
  • Community mentions

Verify this score yourself

Every build re-issues MetaGPT’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.

Signed credential (JSON) How to verify

What this score doesn’t check

It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.

How MetaGPT compares in Multi-Agent Systems

  1. #33 swarmclaw 37.9 +0.1
  2. #34 tribe 37.8 ±0
  3. #35 MetaGPT 37.8 this agent
  4. #36 GPTSwarm 37.4 −0.4
  5. #37 DeepResearchAgent 32.0 −5.8

Bars show each HVTrust score; the tick marks MetaGPT’s 37.8.

Where the 37.8 comes from

HVTrust dimensions vs the Multi-Agent Systems average

37.8 / 100 · 100.0% confidence

MetaGPT Multi-Agent Systems average (43 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
4.5 / 25
3.9 below avg 8.4
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
0.5 below avg 11.3
Transparency50% declared license · 50% OSSF Scorecard
10.5 / 17
1.5 below avg 12.0
Maintenance60% last-push freshness · 40% commit activity
0 / 20
12.9 below avg 12.9
AdoptionLog-scaled stars · package downloads
15.4 / 20
5.3 above avg 10.1

Quick Trust Read

What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-10-09
Rank Moved
Rank dropped 10 spots (#1217 → #1227)
2026-10-02
Drift Warning Cleared
Provenance drift warning cleared (now: unknown)
2026-10-02
Rank Moved
Rank rose 65 spots (#1282 → #1217)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 2.3/10. 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.
Refresh maintenance signals The repo was last pushed 261 days ago. Fresh activity helps separate stable projects from stale ones.
Compare with another agent Get email alerts for MetaGPT View Multi-Agent Systems Report missing data
47.5
Activity sub-score · out of 100
#35
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 D 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 2026-10-09 12:08 UTC · Repo last pushed 261 days ago — may be stale

Rank Trend

2026-09-29 2026-10-09

Activity & Reach

Stars
70.8k
Forks
9.0k
Last Push
2026-01-21
261 days ago
Commits (4 wk)
0
Downloads (7d)
671
pypi
HN mentions (30d)
58
Open Issues
11
Rank Change
▼10
was #1217

Analysis

Activity Inputs

47.5 / 100
StarsRepository reach
29.1 / 30
FreshnessLast push recency
0.0 / 25
ActivityRecent commits
0.0 / 25
CommunityFork signal
18.4 / 20

Common questions about MetaGPT

Public trust evidence for MetaGPT 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 MetaGPT publish package provenance?
No published build provenance is currently detected for MetaGPT. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does MetaGPT have an OpenSSF Scorecard?
MetaGPT has an OpenSSF Scorecard score of 2.3/10. 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 MetaGPT actively maintained?
Stale. The repository has not been pushed to in 261 days. Consider whether the project is still being maintained.
What license does MetaGPT use?
MetaGPT ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are MetaGPT's commits signed?
33% of the last 100 commits to MetaGPT 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
None detected
No MCP server signal detected.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
6 detected
Public provider/service dependencies detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
high confidence
3 tags
Broad capability areas detected.
  • browser
  • code
  • database
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 MetaGPT'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.

2026-10-02
Drift Warning Cleared
Provenance drift warning cleared (now: unknown)

Maintain MetaGPT?

For maintainers

HVTrust scores MetaGPT 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
Rank 27HVTrust 1Drift 1
2026-10-09
Rank Moved
Rank dropped 10 spots (#1217 → #1227)
2026-10-02
Drift Warning Cleared
Provenance drift warning cleared (now: unknown)
2026-10-02
Rank Moved
Rank rose 65 spots (#1282 → #1217)
2026-10-02
HVTrust Changed
HVTrust up 4.9pts (32.8 → 37.7)
2026-09-23
Rank Moved
Rank dropped 642 spots (#625 → #1267)
2026-09-22
Rank Moved
Rank dropped 214 spots (#411 → #625)
2026-09-21
Rank Moved
Rank rose 854 spots (#1265 → #411)
2026-09-09
Rank Moved
Rank dropped 10 spots (#1251 → #1261)
2026-09-08
Rank Moved
Rank dropped 10 spots (#1241 → #1251)
2026-09-07
Rank Moved
Rank dropped 12 spots (#1229 → #1241)
2026-09-06
Rank Moved
Rank dropped 18 spots (#1211 → #1229)
2026-09-05
Rank Moved
Rank dropped 25 spots (#1186 → #1211)
2026-09-04
Rank Moved
Rank dropped 16 spots (#1170 → #1186)
2026-09-03
Rank Moved
Rank dropped 42 spots (#1128 → #1170)
2026-09-02
Rank Moved
Rank dropped 64 spots (#1064 → #1128)
2026-09-01
Rank Moved
Rank dropped 39 spots (#1025 → #1064)
2026-08-31
Rank Moved
Rank dropped 34 spots (#991 → #1025)
2026-08-30
Rank Moved
Rank dropped 50 spots (#941 → #991)
2026-08-29
Rank Moved
Rank dropped 49 spots (#892 → #941)
2026-08-28
Rank Moved
Rank dropped 32 spots (#860 → #892)
2026-08-27
Rank Moved
Rank dropped 22 spots (#838 → #860)
2026-08-26
Rank Moved
Rank dropped 106 spots (#732 → #838)
2026-08-16
Rank Moved
Rank dropped 12 spots (#714 → #726)
2026-08-10
Rank Moved
Rank dropped 38 spots (#679 → #717)
2026-08-08
Rank Moved
Rank dropped 264 spots (#414 → #678)
2026-07-29
Rank Moved
Rank dropped 12 spots (#397 → #409)
2026-07-15
Rank Moved
Rank dropped 24 spots (#367 → #391)
2026-07-14
Rank Moved
Rank dropped 21 spots (#346 → #367)
2026-07-13
Rank Moved
Rank dropped 36 spots (#310 → #346)
GitHub → Website → PyPI: metagpt

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 37.8 Grade D
Markdown:
[![HVTrust](https://hvtracker.net/badge/metagpt.svg)](https://hvtracker.net/agents/metagpt)
HTML:
<a href="https://hvtracker.net/agents/metagpt"><img src="https://hvtracker.net/badge/metagpt.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 v4.4 · Raw JSON