updated 2026-10-09 08:15 UTC

AutoGen

Repository Website by microsoft

A programming framework for agentic AI

Agent Frameworks Python Listed CC-BY-4.0

Is AutoGen safe? Promising trust profile, but some evidence still deserves review.

OSSF Scorecard 5.6 / 10
Provenance Attested
Signed commits 100%
Last push 177d ago
Compare AutoGen

How does it stack up against its Agent Frameworks neighbours?

Pick any agent to compare →
Suggest a correction

In detail: AutoGen scores 69.5/100 (Grade B), ranked #349 of 1371 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 5.6/10; 100% of recent commits are signed; last pushed 2026-04-15. Every point is earned from checkable signals — never paid placement. How scoring works →

How AutoGen 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 AutoGen 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 Signed

    github.com/microsoft/autogen, CC-BY-4.0, last pushed 2026-04-15. 100% of the last 100 commits carry a verified signature, so changes trace to a verified account.

  2. Review and release Mixed

    OpenSSF Scorecard rates the repository's practices 5.6/10 (scanned Oct 9, 2026). The checks that decide who can get a change released:

    • Code Review6
    • Branch Protection5
    • Signed Releasesn/a
    • Dangerous Workflow10
    • Token Permissions0
    • Pinned Dependencies0
    All 14 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 5
    CII-Best-Practices 0
    Code-Review 6
    Dangerous-Workflow 10
    Fuzzing 0
    License 10
    Maintained 0
    Packaging 10
    Pinned-Dependencies 0
    SAST 10
    Security-Policy 10
    Signed-Releases -1
    Token-Permissions 0

  3. Published packages Partly attested

Changes to this chain

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

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 AutoGen’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 AutoGen compares in Agent Frameworks

  1. #23 Zeroclaw 70.4 +0.9
  2. #24 AgentScope 70.4 +0.9
  3. #25 AutoGen 69.5 this agent
  4. #26 Nx 69.1 −0.4
  5. #27 Google ADK (Go) 69.0 −0.5

Bars show each HVTrust score; the tick marks AutoGen’s 69.5.

Where the 69.5 comes from

HVTrust dimensions vs the Agent Frameworks average

69.5 / 100 · 100.0% confidence

AutoGen Agent Frameworks average (129 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
19.5 / 25
10.0 above avg 9.5
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
6.4 above avg 11.6
Transparency50% declared license · 50% OSSF Scorecard
13.3 / 17
1.3 above avg 12.0
Maintenance60% last-push freshness · 40% commit activity
0.2 / 20
13.4 below avg 13.6
AdoptionLog-scaled stars · package downloads
18.1 / 20
7.3 above avg 10.8

Quick Trust Read

What Would Improve It
Improve maintenance to lift the weakest part of the trust profile.
Recent Changes
2026-09-23
Rank Moved
Rank dropped 195 spots (#119 → #314)
2026-09-21
Rank Moved
Rank rose 187 spots (#306 → #119)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 5.6/10. Tighten the weakest checks to improve public safety evidence.
Refresh maintenance signals The repo was last pushed 177 days ago. Fresh activity helps separate stable projects from stale ones.
Compare with another agent Get email alerts for AutoGen View Agent Frameworks Report missing data
47.7
Activity sub-score · out of 100
#25
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 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 →

Signals refreshed 2026-10-09 08:15 UTC · Repo last pushed 177 days ago

Rank Trend

2026-09-29 2026-10-09

Activity & Reach

Stars
61.3k
Forks
9.3k
Last Push
2026-04-15
177 days ago
Commits (4 wk)
0
Downloads (7d)
89,655
pypi
HN mentions (30d)
3
Open Issues
558
Rank Change
▼5
was #344

Analysis

Activity Inputs

47.7 / 100
StarsRepository reach
28.7 / 30
FreshnessLast push recency
0.4 / 25
ActivityRecent commits
0.0 / 25
CommunityFork signal
18.4 / 20

Common questions about AutoGen

AutoGen 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 AutoGen publish package provenance?
Yes. AutoGen's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does AutoGen have an OpenSSF Scorecard?
AutoGen has an OpenSSF Scorecard score of 5.6/10. 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 AutoGen actively maintained?
Slowing down. Last push was 177 days ago — keep an eye on whether activity resumes.
What license does AutoGen use?
AutoGen ships under CC-BY-4.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are AutoGen's commits signed?
100% of the last 100 commits to AutoGen 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
AutoGen appears to expose MCP server capabilities.
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
high confidence
Extensions
Extension based plugin/integration surface detected.
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 AutoGen'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.

2026-07-14
Activity Went Stale
No commits for 90 days

Maintain AutoGen?

For maintainers

HVTrust scores AutoGen 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 9Stale 1
2026-09-23
Rank Moved
Rank dropped 195 spots (#119 → #314)
2026-09-21
Rank Moved
Rank rose 187 spots (#306 → #119)
2026-09-07
Rank Moved
Rank dropped 20 spots (#249 → #269)
2026-09-05
Rank Moved
Rank dropped 53 spots (#193 → #246)
2026-09-04
Rank Moved
Rank dropped 14 spots (#179 → #193)
2026-09-03
Rank Moved
Rank dropped 12 spots (#167 → #179)
2026-08-31
Rank Moved
Rank dropped 22 spots (#135 → #157)
2026-08-26
Rank Moved
Rank dropped 15 spots (#109 → #124)
2026-08-13
Rank Moved
Rank dropped 10 spots (#94 → #104)
2026-07-14
Activity Went Stale
No commits for 90 days
GitHub → Website → PyPI: autogen-agentchat

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 69.5 Grade B
Markdown:
[![HVTrust](https://hvtracker.net/badge/autogen.svg)](https://hvtracker.net/agents/autogen)
HTML:
<a href="https://hvtracker.net/agents/autogen"><img src="https://hvtracker.net/badge/autogen.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 v4.4 · Raw JSON