Week 45, updated 2 Nov 2026

Automation & agent frameworks AutoGen

Is AutoGen safe?

Short answer: Caution. StackGrade's weekly scan of microsoft/autogen gives it a Caution label for 33 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 333 high-severity advisories in runtime dependencies, which don't change the label. Critical advisories are counted once per package; a known issue in a locked package version does not prove AutoGen is exploitable in your setup. Automated scan of commit d07c667 on 2 Nov 2026, not a manual audit.

Updated : the last week its score, rank or safety result changed.

Microsoft's programming framework for agentic AI and multi-agent apps.

  • 61,668 stars
  • pushed 28 Oct
  • MIT
  • Python

github.com/microsoft/autogen · microsoft.github.io/autogen

40score out of 100

#41of 52 overall#11in Automation & agent frameworks▲ 1 vs Week 44

  • Maintenance 30%12
  • Adoption 30%48
  • Docs 20%69
  • Community 20%–
W42W43W44W45

Score over the last 4 weeks: 37, 41, 39, 40.

Caution

33 critical-severity known vulnerabilities in runtime dependencies (OSV).

How this score works

Each part is a percentile among all 52 tracked tools, so 50 is average for this list. Community is not measured yet; the score uses the other 80%.

  • Maintenance: Last push 28 Oct 2026. Last 10 GitHub releases within 91 days, counted as 0 because the latest is older than 180 days, latest release 30 Sept 2025. Issue close time: fewer than 5 closed issues, so not used.
  • Adoption: 61,668 stars (70%), 9,349 forks (30%).
  • Docs: README 21,508 characters, 14 headings, 6 code blocks, install section: yes.

Methodology

#11 of 14 in Automation & agent frameworks

Ranked by score. The yellow row is this tool.

Automation & agent frameworks, Week 45score 0–100, safety
  1. 1n8n#3 overall70Caution
  2. 2AutoGPT#14 overall62Caution
  3. 3CrewAI#18 overall57Caution
  4. 4Dify#20 overall56Caution
  5. 5LangChain#23 overall54Caution
  6. 6Pydantic AI#31 overall46Caution
  7. 7Mastra#33 overall44No issues found
  8. 8LangGraph#34 overall44No issues found
  9. 9Agent Development Kit (ADK, Python)#36 overall43Caution
  10. 10OpenBot#39 overall41Caution
  11. 11AutoGen#41 overall40Caution
Show the other 3
  1. 12OpenAI Agents SDK (Python)#42 overall39Caution
  2. 13smolagents#47 overall30No dependencies scanned
  3. 14artemis#50 overall25Caution

Safety scan, 2 Nov 2026

Automated scan of commit d07c667, 978 files. Not a manual audit.

Caution

  • 33Critical dependency advisories333 high, 235 medium, 40 low. OSV, runtime dependencies only.
  • 0Install hooksNo npm install scripts found.
  • 0Remote-code patternsFor example eval(fetch(…)).
  • 32Agent files checked0 phrases flagged for review.
  • 1curl | sh installersIn docs or program code. Information only.
Why this label?

Why this label:

  • 33 critical-severity known vulnerabilities in runtime dependencies (OSV)

Known vulnerabilities in runtime dependencies (OSV): 33 critical, 333 high, 235 medium, 40 low, 2 unrated

  • form-data@4.0.3 (GHSA-fjxv-7rqg-78g4) in python/packages/autogen-studio/frontend/yarn.lock
  • immutable@3.7.6 (GHSA-wf6x-7x77-mvgw) in python/packages/autogen-studio/frontend/yarn.lock
  • proxy-addr@2.0.7 (GHSA-jqcg-44mw-7w3h) in python/packages/autogen-studio/frontend/yarn.lock
  • shell-quote@1.8.3 (GHSA-w7jw-789q-3m8p) in python/packages/autogen-studio/frontend/yarn.lock
  • certifi@2026.7.22 (PYSEC-2026-4320) in python/samples/core_streaming_handoffs_fastapi/requirements.txt

Also found (informational, does not change the label):

  • 333 high-severity known vulnerabilities in runtime dependencies (OSV)
  • Documents curl|sh style installer (1 occurrence, e.g. .azure/pipelines/templates/build.yaml)
  • Critical advisories counted once per package: 45 matches across 4 lockfiles

Notes:

  • Telemetry/analytics references in code: telemetry

Automated scan of commit d07c667 on 2 Nov 2026, not a manual audit. 978 files checked. What we check

Repo activity

From the GitHub API, fetched 2 Nov 2026.

  • 0Releases, 90 daysLatest python-v0.7.5, 30 Sept 2025
  • –Median issue closeFewer than 5 closed issues
  • 61.7kStars+103 since 26 Oct
  • 9.3kForks1,129 open issues
  • 2023Repo created18 Aug 2023
30 days ago2 Nov
0 releases in the last 30 days, one mark each (GitHub releases feed, last 10 entries).

0 releases in the last 30 days (GitHub releases feed, last 10 entries).

Questions about AutoGen

Answers use this week's StackGrade data.

Is AutoGen safe to use?

Caution. StackGrade's weekly scan of microsoft/autogen gives it a Caution label for 33 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 333 high-severity advisories in runtime dependencies, which don't change the label. Critical advisories are counted once per package; a known issue in a locked package version does not prove AutoGen is exploitable in your setup. Automated scan of commit d07c667 on 2 Nov 2026, not a manual audit.

How does StackGrade score AutoGen?

AutoGen scores 40 out of 100 in Week 45: #41 of 52 tracked tools overall and #11 in Automation & agent frameworks. The score combines maintenance (12), adoption (48) and docs (69) as percentiles among all 52 tracked tools; community (20% weight) is not measured yet, so the score uses the other 80%. It is not a hands-on test and it is separate from the safety label.

What are the alternatives to AutoGen?

The highest-scored other tools in Automation & agent frameworks this week: n8n (70, Caution), AutoGPT (62, Caution), CrewAI (57, Caution), Dify (56, Caution). StackGrade has not tested them hands-on.

What licence does AutoGen use?

The licence listed for microsoft/autogen is MIT. Read the licence text before commercial use.

Compare and use it

Used in 1 AI use case

All facts and sources
Type
Agent framework
License
MIT
Language
Python
Created
18 Aug 2023
Owner
microsoft (Organization)
Forks
9,349

GitHub description: “A programming framework for agentic AI”

Sources: github.com/microsoft/autogen, api.github.com/repos/microsoft/autogen, raw.githubusercontent.com/microsoft/autogen/main/README.md. Fetched 2 Nov 2026.

Know when AutoGen changes label

One email a week: the new top 10, the biggest score changes and every safety label that changed.

Free. Double opt-in: you confirm by email first, unsubscribe in one click.