Sotopia agents

Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)

Research & Data Python Listed MIT

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

OSSF Scorecard 4.2 / 10
Provenance None
Signed commits 67%
Last push 126d ago
Advisories None known
Compare Sotopia agents
Suggest a correction

In detail: Sotopia agents scores 39.5/100 (Grade D), ranked #1187 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 4.2/10; 67% of recent commits are signed; no published advisory affects its latest release (sotopia); last pushed 2026-06-05. Every point is earned from checkable signals — never paid placement. How scoring works →

How Sotopia agents 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.

Chain of custody

Scanners check what the code says. This traces who ships Sotopia agents 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/sotopia-lab/sotopia, MIT, last pushed 2026-06-05. 67% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.

  2. Review and release Mixed

    OpenSSF Scorecard rates the repository's practices 4.2/10 (scanned Sep 29, 2026). The checks that decide who can get a change released:

    • Code Review6
    • Branch Protection4
    • Signed Releasesn/a
    • Dangerous Workflow10
    • Token Permissions0
    • Pinned Dependencies1
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 4
    CI-Tests 3
    CII-Best-Practices 0
    Code-Review 6
    Contributors 10
    Dangerous-Workflow 10
    Dependency-Update-Tool 10
    Fuzzing 0
    License 10
    Maintained 0
    Packaging -1
    Pinned-Dependencies 1
    SAST 0
    Security-Policy 0
    Signed-Releases -1
    Token-Permissions 0
    Vulnerabilities 0
  3. Published packages Not linked

    • PyPI sotopia Source link isn't a GitHub repo No build attestation

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

  4. What you install today No known advisories

    Latest release checked: sotopia 0.1.5. No published advisory affects it (OSV, checked 2026-10-09).

Changes to this chain

No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of Sotopia agents.

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 Sotopia agents’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.

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 Sotopia agents compares in Research & Data

  1. #20 TradingAgents-astock 49.0 +9.5
  2. #21 MiroThinker 41.6 +2.1
  3. #22 Sotopia agents 39.5 this agent
  4. #23 luxas 39.4 −0.1
  5. #24 deep-research 37.8 −1.7

Bars show each HVTrust score; the tick marks Sotopia agents’s 39.5.

Where the 39.5 comes from

HVTrust dimensions vs the Research & Data average

39.5 / 100 · 100.0% confidence

Sotopia agents Research & Data average (37 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
8.6 / 25
0.7 above avg 7.9
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
1.0 below avg 11.8
Transparency50% declared license · 50% OSSF Scorecard
12.1 / 17
0.8 above avg 11.3
Maintenance60% last-push freshness · 40% commit activity
3.6 / 20
9.1 below avg 12.7
AdoptionLog-scaled stars · package downloads
8.7 / 20
1.8 below avg 10.5

Quick Trust Read

What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-09-27
Rank Moved
Rank dropped 11 spots (#1153 → #1164)
2026-09-23
Rank Moved
Rank dropped 645 spots (#502 → #1147)
2026-09-22
Rank Moved
Rank dropped 119 spots (#383 → #502)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 4.2/10. 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.
Refresh maintenance signals The repo was last pushed 126 days ago. Fresh activity helps separate stable projects from stale ones.
30.7
Activity sub-score · out of 100
#22

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 08:15 UTC · Repo last pushed 126 days ago

Rank Trend

2026-09-29 2026-10-09

Activity & Reach

Stars
337
Forks
50
Last Push
2026-06-05
126 days ago
Commits (4 wk)
0
Downloads (7d)
98
pypi
HN mentions (30d)
6
Open Issues
5
Rank Change
▼1
was #1186

Analysis

Activity Inputs

30.7 / 100
StarsRepository reach
15.2 / 30
FreshnessLast push recency
7.5 / 25
ActivityRecent commits
0.0 / 25
CommunityFork signal
7.9 / 20

Common questions about Sotopia agents

Public trust evidence for Sotopia agents 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 Sotopia agents publish package provenance?
No published build provenance is currently detected for Sotopia agents. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does Sotopia agents have an OpenSSF Scorecard?
Sotopia agents has an OpenSSF Scorecard score of 4.2/10. 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 Sotopia agents actively maintained?
Slowing down. Last push was 126 days ago — keep an eye on whether activity resumes.
What license does Sotopia agents use?
Sotopia agents ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Sotopia agents's commits signed?
67% of the last 100 commits to Sotopia agents 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
7 detected
Public provider/service dependencies detected.
Credential signal: API keys or service config markers documented.
Tool / Plugin Surface
high confidence
1 tags
Broad capability areas detected.
  • 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 Sotopia 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.

2026-09-03
Activity Went Stale
No commits for 90 days

Maintain Sotopia agents?

For maintainers

HVTrust scores Sotopia 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 26HVTrust 1Stale 1
2026-09-27
Rank Moved
Rank dropped 11 spots (#1153 → #1164)
2026-09-23
Rank Moved
Rank dropped 645 spots (#502 → #1147)
2026-09-22
Rank Moved
Rank dropped 119 spots (#383 → #502)
2026-09-21
Rank Moved
Rank rose 762 spots (#1145 → #383)
2026-09-17
Rank Moved
Rank dropped 20 spots (#1134 → #1154)
2026-09-09
Rank Moved
Rank dropped 16 spots (#1108 → #1124)
2026-09-07
Rank Moved
Rank dropped 25 spots (#1076 → #1101)
2026-09-06
Rank Moved
Rank dropped 22 spots (#1054 → #1076)
2026-09-05
Rank Moved
Rank dropped 40 spots (#1014 → #1054)
2026-09-04
Rank Moved
Rank dropped 24 spots (#990 → #1014)
2026-09-03
Activity Went Stale
No commits for 90 days
2026-09-03
Rank Moved
Rank rose 15 spots (#1005 → #990)
2026-09-03
HVTrust Changed
HVTrust up 3.2pts (38.7 → 41.9)
2026-09-02
Rank Moved
Rank dropped 51 spots (#954 → #1005)
2026-09-01
Rank Moved
Rank dropped 38 spots (#916 → #954)
2026-08-31
Rank Moved
Rank dropped 31 spots (#885 → #916)
2026-08-30
Rank Moved
Rank dropped 38 spots (#847 → #885)
2026-08-29
Rank Moved
Rank dropped 43 spots (#804 → #847)
2026-08-28
Rank Moved
Rank dropped 26 spots (#778 → #804)
2026-08-27
Rank Moved
Rank dropped 23 spots (#755 → #778)
2026-08-26
Rank Moved
Rank dropped 102 spots (#653 → #755)
2026-08-16
Rank Moved
Rank dropped 16 spots (#623 → #639)
2026-08-10
Rank Moved
Rank dropped 18 spots (#593 → #611)
2026-08-08
Rank Moved
Rank dropped 207 spots (#387 → #594)
2026-07-29
Rank Moved
Rank dropped 10 spots (#354 → #364)
2026-07-15
Rank Moved
Rank dropped 26 spots (#319 → #345)
2026-07-14
Rank Moved
Rank dropped 18 spots (#301 → #319)
2026-07-13
Rank Moved
Rank dropped 34 spots (#267 → #301)

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 39.5 Grade D
Markdown:
[![HVTrust](https://hvtracker.net/badge/sotopia-agents.svg)](https://hvtracker.net/agents/sotopia-agents)
HTML:
<a href="https://hvtracker.net/agents/sotopia-agents"><img src="https://hvtracker.net/badge/sotopia-agents.svg" alt="HVTrust"></a>

Other agents in Research & Data

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