Week 45, updated 2 Nov 2026

Automation & agent frameworks LangChain

Is LangChain safe?

Short answer: Caution. StackGrade's weekly scan of langchain-ai/langchain gives it a Caution label for 7 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 32 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 LangChain is exploitable in your setup. Automated scan of commit aa13e9c on 2 Nov 2026, not a manual audit.

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

Widely used framework and platform for building LLM apps and agents.

  • 148,854 stars
  • pushed 2 Nov
  • MIT
  • Python

github.com/langchain-ai/langchain · docs.langchain.com/langchain

54score out of 100

#23of 52 overall#5in Automation & agent frameworks▼ 2 vs Week 44

  • Maintenance 30%65
  • Adoption 30%78
  • Docs 20%2
  • Community 20%–
W42W43W44W45

Score over the last 4 weeks: 58, 57, 56, 54.

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 2 Nov 2026. Last 10 GitHub releases within 13 days (about 21 per 30 days), latest release 29 Oct 2026. Issue close time: fewer than 5 closed issues, so not used.
  • Adoption: 148,854 stars (70%), 25,017 forks (30%).
  • Docs: README 5,891 characters, 4 headings, 2 code blocks, install section: no.

Methodology

#5 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
Show the other 8
  1. 7Mastra#33 overall44No issues found
  2. 8LangGraph#34 overall44No issues found
  3. 9Agent Development Kit (ADK, Python)#36 overall43Caution
  4. 10OpenBot#39 overall41Caution
  5. 11AutoGen#41 overall40Caution
  6. 12OpenAI Agents SDK (Python)#42 overall39Caution
  7. 13smolagents#47 overall30No dependencies scanned
  8. 14artemis#50 overall25Caution

Safety scan, 2 Nov 2026

Automated scan of commit aa13e9c, 2,953 files. Not a manual audit.

Caution

  • 7Critical dependency advisories32 high, 14 medium, 1 low. OSV, runtime dependencies only.
  • 0Install hooksNo npm install scripts found.
  • 0Remote-code patternsFor example eval(fetch(…)).
  • 283Agent files checked0 phrases flagged for review.
  • 1curl | 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, 32 high, 14 medium, 1 low

  • chromadb@1.5.9 (PYSEC-2026-311) in libs/partners/chroma/uv.lock
  • chromadb@1.5.9 (PYSEC-2026-3814) in libs/partners/chroma/uv.lock
  • pillow@12.3.0 (PYSEC-2026-4330) in libs/partners/nomic/uv.lock
  • pillow@12.3.0 (PYSEC-2026-4332) in libs/partners/nomic/uv.lock
  • pillow@12.3.0 (PYSEC-2026-4339) in libs/partners/nomic/uv.lock

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

  • 32 high-severity known vulnerabilities in runtime dependencies (OSV)
  • Documents curl|sh style installer (1 occurrence, e.g. openwiki/quickstart.md)
  • Critical advisories counted once per package: 12 matches across 3 lockfiles

Notes:

  • Telemetry/analytics references in code: telemetry

Automated scan of commit aa13e9c on 2 Nov 2026, not a manual audit. 2,953 files checked. What we check

Repo activity

From the GitHub API, fetched 2 Nov 2026.

  • 10+Releases, 90 daysLatest langchain-core==1.7.3, 29 Oct
  • –Median issue closeFewer than 5 closed issues
  • 149kStars+384 since 26 Oct
  • 25kForks705 open issues
  • 2022Repo created17 Oct 2022
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 LangChain

Answers use this week's StackGrade data.

Is LangChain safe to use?

Caution. StackGrade's weekly scan of langchain-ai/langchain gives it a Caution label for 7 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 32 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 LangChain is exploitable in your setup. Automated scan of commit aa13e9c on 2 Nov 2026, not a manual audit.

How does StackGrade score LangChain?

LangChain scores 54 out of 100 in Week 45: #23 of 52 tracked tools overall and #5 in Automation & agent frameworks. The score combines maintenance (65), adoption (78) and docs (2) 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 LangChain?

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 LangChain use?

The licence listed for langchain-ai/langchain is MIT. Read the licence text before commercial use.

Compare and use it

All facts and sources
Type
Agent framework
License
MIT
Language
Python
Created
17 Oct 2022
Owner
langchain-ai (Organization)
Forks
25,017

GitHub description: “The agent engineering platform.”

Sources: github.com/langchain-ai/langchain, api.github.com/repos/langchain-ai/langchain, raw.githubusercontent.com/langchain-ai/langchain/master/READ. Fetched 2 Nov 2026.

Know when LangChain 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.