Week 45, updated 2 Nov 2026

Automation & agent frameworks OpenBot

Is OpenBot safe?

Short answer: Caution. StackGrade's weekly scan of CopilotKit/OpenBot gives it a Caution label for 5 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 65 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 OpenBot is exploitable in your setup. Automated scan of commit c396a5f on 2 Nov 2026, not a manual audit.

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

Open-source AI coworkers that each get their own browser, files and tools, with actions logged.

  • 9,675 stars
  • pushed 1 Nov
  • MIT
  • TypeScript

github.com/CopilotKit/OpenBot · www.copilotkit.ai/openbot

41score out of 100

#39of 52 overall#10in Automation & agent frameworks▼ 2 vs Week 44

  • Maintenance 30%60
  • Adoption 30%4
  • Docs 20%69
  • Community 20%–
W42W43W44W45

Score over the last 4 weeks: 42, 42, 43, 41.

Caution

5 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 Nov 2026. Last 10 GitHub releases within 28 days (about 9.6 per 30 days), latest release 12 Oct 2026. Issue close time: fewer than 5 closed issues, so not used.
  • Adoption: 9,675 stars (70%), 1,195 forks (30%).
  • Docs: README 33,762 characters, 25 headings, 10 code blocks, install section: yes.

Methodology

#10 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
Show the other 4
  1. 11AutoGen#41 overall40Caution
  2. 12OpenAI Agents SDK (Python)#42 overall39Caution
  3. 13smolagents#47 overall30No dependencies scanned
  4. 14artemis#50 overall25Caution

Safety scan, 2 Nov 2026

Automated scan of commit c396a5f, 2,368 files. Not a manual audit.

Caution

  • 5Critical dependency advisories65 high, 71 medium, 22 low. OSV, runtime dependencies only.
  • 0Install hooksNo npm install scripts found.
  • 0Remote-code patternsFor example eval(fetch(…)).
  • 65Agent files checked0 phrases flagged for review.
  • 0curl | sh installersIn docs or program code. Information only.
Why this label?

Why this label:

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

Known vulnerabilities in runtime dependencies (OSV): 5 critical, 65 high, 71 medium, 22 low, 16 unrated

  • better-auth@1.7.1 (GHSA-965c-763c-88jm) in bun.lock
  • dompurify@3.4.14 (GHSA-cg2g-xh64-v4q7) in bun.lock
  • proxy-addr@2.0.7 (GHSA-jqcg-44mw-7w3h) in bun.lock
  • zip@2.4.2 (RUSTSEC-2026-0369) in desktop/src-tauri/Cargo.lock
  • zip@2.4.2 (GHSA-m665-v7pm-7grj) in desktop/src-tauri/Cargo.lock

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

  • 65 high-severity known vulnerabilities in runtime dependencies (OSV)
  • Critical advisories counted once per package: 6 matches across 3 lockfiles

Notes:

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

Automated scan of commit c396a5f on 2 Nov 2026, not a manual audit. 2,368 files checked. What we check

Repo activity

From the GitHub API, fetched 2 Nov 2026.

  • 10+Releases, 90 daysLatest v0.2.0, 12 Oct
  • –Median issue closeFewer than 5 closed issues
  • 9.7kStars+2,540 since 26 Oct
  • 1.2kForks90 open issues
  • 2026Repo created17 Aug 2026
30 days ago2 Nov
3 releases in the last 30 days, one mark each (GitHub releases feed, last 10 entries).

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

Questions about OpenBot

Answers use this week's StackGrade data.

Is OpenBot safe to use?

Caution. StackGrade's weekly scan of CopilotKit/OpenBot gives it a Caution label for 5 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 65 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 OpenBot is exploitable in your setup. Automated scan of commit c396a5f on 2 Nov 2026, not a manual audit.

How does StackGrade score OpenBot?

OpenBot scores 41 out of 100 in Week 45: #39 of 52 tracked tools overall and #10 in Automation & agent frameworks. The score combines maintenance (60), adoption (4) 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 OpenBot?

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 OpenBot use?

The licence listed for CopilotKit/OpenBot is MIT. Read the licence text before commercial use.

Compare and use it

All facts and sources
Type
AI tool
License
MIT
Language
TypeScript
Created
17 Aug 2026
Owner
CopilotKit (Organization)
Forks
1,195

GitHub description: “Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.”

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

Know when OpenBot 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.