Local AI LobeHub
Is LobeHub safe?
Short answer: Caution. StackGrade's weekly scan of lobehub/lobehub gives it a Caution label for 3 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 24 high-severity advisories in runtime dependencies, which don't change the label. 1 phrase in agent instruction files was flagged for human review (unclear). Critical advisories are counted once per package; a known issue in a locked package version does not prove LobeHub is exploitable in your setup. Automated scan of commit 73f7f1b on 2 Nov 2026, not a manual audit.
Updated : the last week its score, rank or safety result changed.
Open-source AI chat and agent workspace for organising and running your AI agents.
- 83,689 stars
- pushed 2 Nov
- LobeHub Community License
- TypeScript
#7of 52 overall#2in Local AI▲ 1 vs Week 44
- Maintenance 30%78
- Adoption 30%60
- Docs 20%69
- Community 20%–
Score over the last 4 weeks: 76, 68, 68, 69.
3 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 3 days (about 87 per 30 days), latest release 1 Nov 2026. Issue close time: fewer than 5 closed issues, so not used.
- Adoption: 83,689 stars (70%), 16,028 forks (30%).
- Docs: README 43,642 characters, 18 headings, 4 code blocks, install section: yes.
#2 of 5 in Local AI
Ranked by score. The yellow row is this tool.
- 1Ollama#2 overall73Caution
- 2LobeHub#7 overall69Caution
- 3Open WebUI#8 overall68Caution
- 4llama.cpp#9 overall68Caution
- 5vLLM#24 overall54Caution
Safety scan, 2 Nov 2026
Automated scan of commit 73f7f1b, 21,870 files. Not a manual audit.
Caution
- 3Critical dependency advisories24 high, 17 medium, 9 low. OSV, runtime dependencies only.
- 4Install hooksnpm scripts that run on install; none downloads remote content.
- 0Remote-code patternsFor example eval(fetch(…)).
- 793Agent files checked1 phrase flagged for review.
- 2curl | sh installersIn docs or program code. Information only.
Why this label?
Why this label:
- 3 critical-severity known vulnerabilities in runtime dependencies (OSV)
Known vulnerabilities in runtime dependencies (OSV): 3 critical, 24 high, 17 medium, 9 low, 1 unrated
dompurify@3.4.16 (GHSA-cg2g-xh64-v4q7) in apps/desktop/pnpm-lock.yamltar@6.2.1 (GHSA-23hp-3jrh-7fpw) in apps/desktop/pnpm-lock.yamlfast-xml-parser@5.2.5 (GHSA-m7jm-9gc2-mpf2) in apps/desktop/scripts/security-policy-runtime/package-lock.json
Also found (informational, does not change the label):
- 1 injection-related phrase in instruction files, flagged for human review (often defensive guidance), e.g. .agents/skills/ux/references/act.md
- 24 high-severity known vulnerabilities in runtime dependencies (OSV)
- 4 npm install hooks, none downloading remote content
- Program code runs a curl|sh style installer (2 occurrences, e.g. packages/types/src/agent/heterogeneousAgent.ts)
- Skill scripts contact: 127.0.0.1, localhost, unpkg.com, app.lobehub.com, device-gateway.lobehub.com, agent-gateway.lobehub.com, host.docker.internal, registry.npmjs.org
Notes:
- 9 affected packages only in dev/test/docs manifests, not counted
- Telemetry/analytics references in code: telemetry, posthog
Automated scan of commit 73f7f1b on 2 Nov 2026, not a manual audit. 21,870 files checked. What we check
Repo activity
From the GitHub API, fetched 2 Nov 2026.
- 10+Releases, 90 daysLatest v0.0.0-nightly.pr22067.…, 1 Nov
- –Median issue closeFewer than 5 closed issues
- 83.7kStars+195 since 26 Oct
- 16kForks1,193 open issues
- 2023Repo created21 May 2023
10 releases in the last 30 days (GitHub releases feed, last 10 entries):
Questions about LobeHub
Answers use this week's StackGrade data.
Is LobeHub safe to use?
Caution. StackGrade's weekly scan of lobehub/lobehub gives it a Caution label for 3 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 24 high-severity advisories in runtime dependencies, which don't change the label. 1 phrase in agent instruction files was flagged for human review (unclear). Critical advisories are counted once per package; a known issue in a locked package version does not prove LobeHub is exploitable in your setup. Automated scan of commit 73f7f1b on 2 Nov 2026, not a manual audit.
How does StackGrade score LobeHub?
LobeHub scores 69 out of 100 in Week 45: #7 of 52 tracked tools overall and #2 in Local AI. The score combines maintenance (78), adoption (60) 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 LobeHub?
The highest-scored other tools in Local AI this week: Ollama (73, Caution), Open WebUI (68, Caution), llama.cpp (68, Caution), vLLM (54, Caution). StackGrade has not tested them hands-on.
What licence does LobeHub use?
The licence listed for lobehub/lobehub is LobeHub Community License. Read the licence text before commercial use.
Compare and use it
Side by side
Used in 2 AI use cases
All facts and sources
- Type
- AI tool
- License
- LobeHub Community License
- Language
- TypeScript
- Created
- 21 May 2023
- Owner
- lobehub (Organization)
- Forks
- 16,028
- Homepage
- lobehub.com
GitHub description: “🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.”
Sources: github.com/lobehub/lobehub, api.github.com/repos/lobehub/lobehub, raw.githubusercontent.com/lobehub/lobehub/canary/README.md. Fetched 2 Nov 2026.
Know when LobeHub 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.