updated 2026-10-10 04:09 UTC

TinyTroupe

Repository by microsoft

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

Multi-Agent Systems Jupyter Notebook Listed MIT

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

OSSF Scorecard 5.5 / 10
Provenance None
Signed commits 21%
Last push 99d ago
Advisories None known
Compare TinyTroupe

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

Pick any agent to compare →
Suggest a correction

In detail: TinyTroupe scores 51.3/100 (Grade C), ranked #934 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 5.5/10; 21% of recent commits are signed; no published advisory affects its latest release (tinytroupe); last pushed 2026-07-03. Every point is earned from checkable signals — never paid placement. How scoring works →

How TinyTroupe 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 TinyTroupe 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/microsoft/TinyTroupe, MIT, last pushed 2026-07-03. 21% 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 5.5/10 (scanned Oct 8, 2026). The checks that decide who can get a change released:

    • Code Review7
    • Branch Protection5
    • Signed Releasesn/a
    • Dangerous Workflow10
    • Token Permissions0
    • Pinned Dependencies1
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 5
    CI-Tests 6
    CII-Best-Practices 0
    Code-Review 7
    Contributors 10
    Dangerous-Workflow 10
    Dependency-Update-Tool 0
    Fuzzing 0
    License 10
    Maintained 0
    Packaging -1
    Pinned-Dependencies 1
    SAST 9
    Security-Policy 10
    Signed-Releases -1
    Token-Permissions 0
    Vulnerabilities 10

  3. Published packages Linked, not attested

    • PyPI tinytroupe Source link points back to this 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: tinytroupe 0.0.1. No published advisory affects it (OSV, checked 2026-10-10).

Changes to this chain

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

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 TinyTroupe’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 TinyTroupe compares in Multi-Agent Systems

  1. #26 BettaFish 51.7 +0.4
  2. #27 MiroFish 51.6 +0.3
  3. #28 TinyTroupe 51.3 this agent
  4. #29 mateclaw 50.7 −0.6
  5. #30 ChatDev 49.7 −1.6

Bars show each HVTrust score; the tick marks TinyTroupe’s 51.3.

Where the 51.3 comes from

HVTrust dimensions vs the Multi-Agent Systems average

51.3 / 100 · 100.0% confidence

TinyTroupe Multi-Agent Systems average (43 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
7.9 / 25
0.5 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
13.2 / 17
1.2 above avg 12.0
Maintenance60% last-push freshness · 40% commit activity
5.4 / 20
7.5 below avg 12.9
AdoptionLog-scaled stars · package downloads
11.0 / 20
0.8 above avg 10.2

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 17 spots (#916 → #933)
2026-10-01
Activity Went Stale
No commits for 90 days
2026-09-30
Rank Moved
Rank dropped 10 spots (#880 → #890)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 5.5/10. 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 99 days ago. Fresh activity helps separate stable projects from stale ones.
Compare with another agent Get email alerts for TinyTroupe View Multi-Agent Systems Report missing data
47.9
Activity sub-score · out of 100
#28
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 C 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 2026-10-10 04:09 UTC · Repo last pushed 99 days ago

Rank Trend

2026-09-29 2026-10-10

Activity & Reach

Stars
7.6k
Forks
687
Last Push
2026-07-03
99 days ago
Commits (4 wk)
0
Downloads (7d)
16
pypi
HN mentions (30d)
0
Open Issues
14
Rank Change
▼1
was #933

Analysis

Activity Inputs

47.9 / 100
StarsRepository reach
23.3 / 30
FreshnessLast push recency
11.2 / 25
ActivityRecent commits
0.0 / 25
CommunityFork signal
13.2 / 20

Common questions about TinyTroupe

Public trust evidence for TinyTroupe 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 TinyTroupe publish package provenance?
No published build provenance is currently detected for TinyTroupe. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does TinyTroupe have an OpenSSF Scorecard?
TinyTroupe has an OpenSSF Scorecard score of 5.5/10. 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 TinyTroupe actively maintained?
Slowing down. Last push was 99 days ago — keep an eye on whether activity resumes.
What license does TinyTroupe use?
TinyTroupe ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are TinyTroupe's commits signed?
21% of the last 100 commits to TinyTroupe 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
1 detected
Public provider/service dependencies detected.
Credential signal: API keys or service config markers documented.
Tool / Plugin Surface
None detected
No clear plugin system or broad tool 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 TinyTroupe'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.

2026-10-01
Activity Went Stale
No commits for 90 days

Maintain TinyTroupe?

For maintainers

HVTrust scores TinyTroupe 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 31Stale 1
2026-10-09
Rank Moved
Rank dropped 17 spots (#916 → #933)
2026-10-01
Activity Went Stale
No commits for 90 days
2026-09-30
Rank Moved
Rank dropped 10 spots (#880 → #890)
2026-09-24
Rank Moved
Rank dropped 11 spots (#862 → #873)
2026-09-23
Rank Moved
Rank dropped 541 spots (#321 → #862)
2026-09-22
Rank Moved
Rank dropped 12 spots (#309 → #321)
2026-09-21
Rank Moved
Rank rose 551 spots (#860 → #309)
2026-09-11
Rank Moved
Rank dropped 14 spots (#822 → #836)
2026-09-08
Rank Moved
Rank dropped 15 spots (#795 → #810)
2026-09-07
Rank Moved
Rank dropped 38 spots (#757 → #795)
2026-09-06
Rank Moved
Rank dropped 29 spots (#728 → #757)
2026-09-05
Rank Moved
Rank dropped 72 spots (#656 → #728)
2026-09-04
Rank Moved
Rank dropped 24 spots (#632 → #656)
2026-09-03
Rank Moved
Rank dropped 32 spots (#600 → #632)
2026-09-02
Rank Moved
Rank dropped 30 spots (#570 → #600)
2026-09-01
Rank Moved
Rank dropped 21 spots (#549 → #570)
2026-08-31
Rank Moved
Rank dropped 28 spots (#521 → #549)
2026-08-29
Rank Moved
Rank dropped 27 spots (#495 → #522)
2026-08-27
Rank Moved
Rank dropped 13 spots (#477 → #490)
2026-08-26
Rank Moved
Rank dropped 54 spots (#423 → #477)
2026-08-24
Rank Moved
Rank dropped 19 spots (#406 → #425)
2026-08-22
Rank Moved
Rank rose 18 spots (#426 → #408)
2026-08-19
Rank Moved
Rank dropped 12 spots (#410 → #422)
2026-08-17
Rank Moved
Rank rose 11 spots (#420 → #409)
2026-08-16
Rank Moved
Rank dropped 11 spots (#409 → #420)
2026-08-13
Rank Moved
Rank dropped 16 spots (#391 → #407)
2026-08-12
Rank Moved
Rank rose 12 spots (#403 → #391)
2026-08-10
Rank Moved
Rank dropped 18 spots (#385 → #403)
2026-08-08
Rank Moved
Rank dropped 92 spots (#289 → #381)
2026-07-15
Rank Moved
Rank dropped 12 spots (#242 → #254)
2026-07-14
Rank Moved
Rank dropped 14 spots (#228 → #242)
2026-07-13
Rank Moved
Rank dropped 30 spots (#198 → #228)
GitHub → PyPI: tinytroupe

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 51.3 Grade C
Markdown:
[![HVTrust](https://hvtracker.net/badge/tinytroupe.svg)](https://hvtracker.net/agents/tinytroupe)
HTML:
<a href="https://hvtracker.net/agents/tinytroupe"><img src="https://hvtracker.net/badge/tinytroupe.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