Week 45, updated 2 Nov 2026

Automation & agent frameworks artemis

Is artemis safe?

Short answer: Caution. StackGrade's weekly scan of google/artemis gives it a Caution label for 7 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 61 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 artemis is exploitable in your setup. Automated scan of commit 351ca84 on 2 Nov 2026, not a manual audit.

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

Google's tool that turns natural-language instructions into Android automation.

  • 16,143 stars
  • pushed 1 Oct
  • Apache-2.0
  • Python

github.com/google/artemis

25score out of 100

#50of 52 overall#14in Automation & agent frameworks▲ 1 vs Week 44

  • Maintenance 30%14
  • Adoption 30%6
  • Docs 20%69
  • Community 20%–
W42W43W44W45

Score over the last 4 weeks: 24, 23, 24, 25.

Caution

7 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 1 Oct 2026. No GitHub releases, no release pace measured. Median 77.4 h to close an issue (9 closed issues).
  • Adoption: 16,143 stars (70%), 1,762 forks (30%).
  • Docs: README 17,747 characters, 24 headings, 8 code blocks, install section: yes.

Methodology

#14 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
  12. 12OpenAI Agents SDK (Python)#42 overall39Caution
  13. 13smolagents#47 overall30No dependencies scanned
  14. 14artemis#50 overall25Caution

Safety scan, 2 Nov 2026

Automated scan of commit 351ca84, 719 files. Not a manual audit.

Caution

  • 7Critical dependency advisories61 high, 46 medium, 7 low. OSV, runtime dependencies only.
  • 0Install hooksNo npm install scripts found.
  • 0Remote-code patternsFor example eval(fetch(…)).
  • 130Agent files checked0 phrases flagged for review.
  • 4curl | sh installersIn docs or program code. Information only.
Why this label?

Why this label:

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

Known vulnerabilities in runtime dependencies (OSV): 7 critical, 61 high, 46 medium, 7 low

  • certifi@2026.7.22 (PYSEC-2026-4320) in uv.lock
  • pillow@12.3.0 (PYSEC-2026-4330) in uv.lock
  • pillow@12.3.0 (PYSEC-2026-4332) in uv.lock
  • pillow@12.3.0 (PYSEC-2026-4339) in uv.lock
  • pillow@12.3.0 (GHSA-332p-7hrc-92wf) in uv.lock

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

  • 61 high-severity known vulnerabilities in runtime dependencies (OSV)
  • Program code runs a curl|sh style installer (4 occurrences, e.g. scripts/install_deps.ps1)
  • Skill scripts contact: www.apache.org, 127.0.0.1, localhost

Notes:

  • 21 affected packages only in dev/test/docs manifests, not counted
  • Telemetry/analytics references in code: telemetry

Automated scan of commit 351ca84 on 2 Nov 2026, not a manual audit. 719 files checked. What we check

Repo activity

From the GitHub API, fetched 2 Nov 2026.

  • 0GitHub releasesNo release in the public feed.
  • 3dMedian issue closeOver 9 closed issues
  • 16.1kStars+1,300 since 26 Oct
  • 1.8kForks180 open issues
  • 2026Repo created13 Aug 2026

Questions about artemis

Answers use this week's StackGrade data.

Is artemis safe to use?

Caution. StackGrade's weekly scan of google/artemis gives it a Caution label for 7 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 61 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 artemis is exploitable in your setup. Automated scan of commit 351ca84 on 2 Nov 2026, not a manual audit.

How does StackGrade score artemis?

artemis scores 25 out of 100 in Week 45: #50 of 52 tracked tools overall and #14 in Automation & agent frameworks. The score combines maintenance (14), adoption (6) 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 artemis?

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 artemis use?

The licence listed for google/artemis is Apache-2.0. Read the licence text before commercial use.

Compare and use it

All facts and sources
Type
AI tool
License
Apache-2.0
Language
Python
Created
13 Aug 2026
Owner
google (Organization)
Forks
1,762

GitHub description: “ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.”

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

Know when artemis 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.