Automation & agent frameworks Pydantic AI
Is Pydantic AI safe?
Short answer: Caution. StackGrade's weekly scan of pydantic/pydantic-ai gives it a Caution label for 1 critical-severity known vulnerability in runtime dependencies (OSV). It does list 5 high-severity advisories in runtime dependencies, which don't change the label. 3 phrases in agent instruction files were flagged for human review (unclear). Critical advisories are counted once per package; a known issue in a locked package version does not prove Pydantic AI is exploitable in your setup. Automated scan of commit 129c94e on 2 Nov 2026, not a manual audit.
Updated : the last week its score, rank or safety result changed.
Type-safe Python agent framework from the Pydantic team, works with many models.
- 20,992 stars
- pushed 2 Nov
- MIT
- Python
#31of 52 overall#6in Automation & agent frameworkssame score as Week 44
- Maintenance 30%66
- Adoption 30%10
- Docs 20%69
- Community 20%–
Score over the last 4 weeks: 45, 46, 46, 46.
1 critical-severity known vulnerability 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 2 Nov 2026. Last 10 GitHub releases within 12 days (about 22 per 30 days), latest release 1 Nov 2026. Issue close time: fewer than 5 closed issues, so not used.
- Adoption: 20,992 stars (70%), 3,079 forks (30%).
- Docs: README 25,964 characters, 11 headings, 14 code blocks, install section: yes.
#6 of 14 in Automation & agent frameworks
Ranked by score. The yellow row is this tool.
Show the other 8
- 7Mastra#33 overall44No issues found
- 8LangGraph#34 overall44No issues found
- 9Agent Development Kit (ADK, Python)#36 overall43Caution
- 10OpenBot#39 overall41Caution
- 11AutoGen#41 overall40Caution
- 12OpenAI Agents SDK (Python)#42 overall39Caution
- 13smolagents#47 overall30No dependencies scanned
- 14artemis#50 overall25Caution
Safety scan, 2 Nov 2026
Automated scan of commit 129c94e, 5,268 files. Not a manual audit.
Caution
- 1Critical dependency advisories5 high, 3 medium, 1 low. OSV, runtime dependencies only.
- 0Install hooksNo npm install scripts found.
- 0Remote-code patternsFor example eval(fetch(…)).
- 147Agent files checked3 phrases flagged for review.
- 5curl | sh installersIn docs or program code. Information only.
Why this label?
Why this label:
- 1 critical-severity known vulnerability in runtime dependencies (OSV)
Known vulnerabilities in runtime dependencies (OSV): 1 critical, 5 high, 3 medium, 1 low
brotlicffi@1.2.0.0 (PYSEC-2026-4323) in uv.lock
Also found (informational, does not change the label):
- 3 injection-related phrases in instruction files, flagged for human review (often defensive guidance), e.g. src/pydantic_ai_harness/pydantic_ai_harness/.agents/skills/pydantic-ai-harness/references/CONTROL-AND-SAFETY.md
- 5 high-severity known vulnerabilities in runtime dependencies (OSV)
- Program code runs a curl|sh style installer (1 occurrence, e.g. src/pydantic_ai_harness/pydantic_ai_harness/macroscope/_toolset.py)
- Documents curl|sh style installer (4 occurrences, e.g. docs/harness/approval-reviewer.md)
Notes:
- 1 affected package only in dev/test/docs manifests, not counted
- Telemetry/analytics references in code: telemetry, posthog, amplitude
Automated scan of commit 129c94e on 2 Nov 2026, not a manual audit. 5,268 files checked. What we check
Repo activity
From the GitHub API, fetched 2 Nov 2026.
- 10+Releases, 90 daysLatest clai2-bleeding, 1 Nov
- –Median issue closeFewer than 5 closed issues
- 21kStars+118 since 26 Oct
- 3.1kForks1,731 open issues
- 2024Repo created21 Jun 2024
10 releases in the last 30 days (GitHub releases feed, last 10 entries):
Questions about Pydantic AI
Answers use this week's StackGrade data.
Is Pydantic AI safe to use?
Caution. StackGrade's weekly scan of pydantic/pydantic-ai gives it a Caution label for 1 critical-severity known vulnerability in runtime dependencies (OSV). It does list 5 high-severity advisories in runtime dependencies, which don't change the label. 3 phrases in agent instruction files were flagged for human review (unclear). Critical advisories are counted once per package; a known issue in a locked package version does not prove Pydantic AI is exploitable in your setup. Automated scan of commit 129c94e on 2 Nov 2026, not a manual audit.
How does StackGrade score Pydantic AI?
Pydantic AI scores 46 out of 100 in Week 45: #31 of 52 tracked tools overall and #6 in Automation & agent frameworks. The score combines maintenance (66), adoption (10) 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 Pydantic AI?
What licence does Pydantic AI use?
The licence listed for pydantic/pydantic-ai is MIT. Read the licence text before commercial use.
Compare and use it
Side by side
Used in 1 AI use case
All facts and sources
- Type
- Agent framework
- License
- MIT
- Language
- Python
- Created
- 21 Jun 2024
- Owner
- pydantic (Organization)
- Forks
- 3,079
- Homepage
- pydantic.dev/pydantic-ai
GitHub description: “How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.”
Sources: github.com/pydantic/pydantic-ai, api.github.com/repos/pydantic/pydantic-ai, raw.githubusercontent.com/pydantic/pydantic-ai/main/README.m. Fetched 2 Nov 2026.
Know when Pydantic AI 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.