Week 45, updated 2 Nov 2026

Automation & agent frameworks Mastra

Is Mastra safe?

Short answer: No issues found. StackGrade's weekly scan of mastra-ai/mastra found no issues: no critical-severity dependency advisories, no downloading install hooks, no remote-code patterns and no agent instruction file that changes the label. It does list 6 high-severity advisories in runtime dependencies, which don't change the label. 3 phrases in agent instruction files were flagged for human review (unclear). Automated scan of commit e1e64f0 on 2 Nov 2026, not a manual audit.

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

TypeScript framework for AI applications and agents.

  • 29,265 stars
  • pushed 2 Nov
  • Apache-2.0 (ee/ excluded)
  • TypeScript

github.com/mastra-ai/mastra · mastra.ai

44score out of 100

#33of 52 overall#7in Automation & agent frameworks▲ 1 vs Week 44

  • Maintenance 30%83
  • Adoption 30%15
  • Docs 20%29
  • Community 20%–
W42W43W44W45

Score over the last 4 weeks: 43, 44, 43, 44.

No issues found

All checks clean in the scan of 2 Nov 2026.

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 2 Nov 2026. Last 10 GitHub releases within 1 day (about 270 per 30 days), latest release 30 Oct 2026. Issue close time: fewer than 5 closed issues, so not used.
  • Adoption: 29,265 stars (70%), 3,066 forks (30%).
  • Docs: README 7,195 characters, 9 headings, 2 code blocks, install section: yes.

Methodology

#7 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
Show the other 7
  1. 8LangGraph#34 overall44No issues found
  2. 9Agent Development Kit (ADK, Python)#36 overall43Caution
  3. 10OpenBot#39 overall41Caution
  4. 11AutoGen#41 overall40Caution
  5. 12OpenAI Agents SDK (Python)#42 overall39Caution
  6. 13smolagents#47 overall30No dependencies scanned
  7. 14artemis#50 overall25Caution

Safety scan, 2 Nov 2026

Automated scan of commit e1e64f0, 20,743 files. Not a manual audit.

No issues found

  • 0Critical dependency advisories6 high, 6 medium, 1 low. OSV, runtime dependencies only.
  • 1Install hooksnpm scripts that run on install; none downloads remote content.
  • 0Remote-code patternsFor example eval(fetch(…)).
  • 1142Agent files checked3 phrases flagged for review.
  • 0curl | sh installersIn docs or program code. Information only.
Why this label?

No issues found by the automated scan.

Known vulnerabilities in runtime dependencies (OSV): 0 critical, 6 high, 6 medium, 1 low

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

  • 3 injection-related phrases in instruction files, flagged for human review (often defensive guidance), e.g. .mastracode/commands/gh-triage.md
  • 6 high-severity known vulnerabilities in runtime dependencies (OSV)
  • 1 npm install hook, none downloading remote content
  • Skill scripts contact: localhost, my-project.server.staging.mastra.cloud, my-project.server.mastra.cloud, platform.mastra.ai, projects.mastra.ai, gateway-api.staging.mastra.ai, gateway-api.mastra.ai, studio.staging.mastra.ai

Notes:

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

Automated scan of commit e1e64f0 on 2 Nov 2026, not a manual audit. 20,743 files checked. What we check

Repo activity

From the GitHub API, fetched 2 Nov 2026.

  • 10+Releases, 90 daysLatest @mastra/vercel@1.6.3, 30 Oct
  • –Median issue closeFewer than 5 closed issues
  • 29.3kStars+189 since 26 Oct
  • 3.1kForks703 open issues
  • 2024Repo created6 Aug 2024
30 days ago2 Nov
10 releases in the last 30 days, one mark each (GitHub releases feed, last 10 entries).

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

Questions about Mastra

Answers use this week's StackGrade data.

Is Mastra safe to use?

No issues found. StackGrade's weekly scan of mastra-ai/mastra found no issues: no critical-severity dependency advisories, no downloading install hooks, no remote-code patterns and no agent instruction file that changes the label. It does list 6 high-severity advisories in runtime dependencies, which don't change the label. 3 phrases in agent instruction files were flagged for human review (unclear). Automated scan of commit e1e64f0 on 2 Nov 2026, not a manual audit.

How does StackGrade score Mastra?

Mastra scores 44 out of 100 in Week 45: #33 of 52 tracked tools overall and #7 in Automation & agent frameworks. The score combines maintenance (83), adoption (15) and docs (29) 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 Mastra?

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 Mastra use?

The licence listed for mastra-ai/mastra is Apache-2.0 (ee/ excluded). Read the licence text before commercial use.

Compare and use it

All facts and sources
Type
Agent framework
License
Apache-2.0 (ee/ excluded)
Language
TypeScript
Created
6 Aug 2024
Owner
mastra-ai (Organization)
Forks
3,066
Homepage
mastra.ai

GitHub description: “Mastra is the modern TypeScript framework for AI-powered applications and agents.”

Sources: github.com/mastra-ai/mastra, api.github.com/repos/mastra-ai/mastra, raw.githubusercontent.com/mastra-ai/mastra/main/README.md. Fetched 2 Nov 2026.

Know when Mastra 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.