Is Mem0 safe?
Short answer: Caution. StackGrade's weekly scan of mem0ai/mem0 gives it a Caution label for 18 critical-severity known vulnerabilities in runtime dependencies (OSV) and a skill or agent instruction file (skills/mem0-oss-to-platform/references/gotchas.md) that tells the agent to pipe a remote script into a shell. It does list 151 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 Mem0 is exploitable in your setup. Automated scan of commit 753496c on 2 Nov 2026, not a manual audit.
Updated : the last week its score, rank or safety result changed.
Memory layer that gives AI agents and apps long-term, persistent context.
- 68,260 stars
- pushed 30 Oct
- Apache-2.0
- Python
#21of 52 overall#2in RAG, knowledge & memory▼ 2 vs Week 44
- Maintenance 30%52
- Adoption 30%48
- Docs 20%69
- Community 20%–
Score over the last 4 weeks: 62, 56, 57, 55.
18 critical-severity known vulnerabilities in runtime dependencies (OSV) (+1 more).
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 30 Oct 2026. Last 10 GitHub releases within 7 days (about 37 per 30 days), latest release 25 Sept 2026. Issue close time: fewer than 5 closed issues, so not used.
- Adoption: 68,260 stars (70%), 8,099 forks (30%).
- Docs: README 12,266 characters, 22 headings, 10 code blocks, install section: yes.
#2 of 3 in RAG, knowledge & memory
Ranked by score. The yellow row is this tool.
- 1RAGFlow#6 overall69Caution
- 2Mem0#21 overall55Caution
- 3LlamaIndex#35 overall43Caution
Safety scan, 2 Nov 2026
Automated scan of commit 753496c, 1,333 files. Not a manual audit.
Caution
- 18Critical dependency advisories151 high, 126 medium, 13 low. OSV, runtime dependencies only.
- 0Install hooksNo npm install scripts found.
- 0Remote-code patternsFor example eval(fetch(…)).
- 131Agent files checked1 file tells the agent to pipe a script into a shell.
- 2curl | sh installersIn docs or program code. Information only.
Why this label?
Why this label:
- 18 critical-severity known vulnerabilities in runtime dependencies (OSV)
- Skill/agent file instructs piping a remote script into a shell: skills/mem0-oss-to-platform/references/gotchas.md — curl -fsSL https://raw.githubusercontent.com/mem0ai/mem0/main/scripts/oss-to-platform-migrate.sh | bash
Known vulnerabilities in runtime dependencies (OSV): 18 critical, 151 high, 126 medium, 13 low
handlebars@4.7.9 (GHSA-8r5x-fm3f-whwj) in integrations/n8n-nodes-mem0/pnpm-lock.yamlhandlebars@4.7.9 (GHSA-p8wg-vrv2-v86f) in integrations/n8n-nodes-mem0/pnpm-lock.yamlanyio@4.9.0 (PYSEC-2026-4025) in poetry.lockauthlib@1.6.10 (PYSEC-2026-4355) in poetry.lockauthlib@1.6.10 (PYSEC-2026-4356) in poetry.lock
Also found (informational, does not change the label):
- 151 high-severity known vulnerabilities in runtime dependencies (OSV)
- Program code runs a curl|sh style installer (1 occurrence, e.g. integrations/hermes-plugin-mem0/_setup.py)
- Documents curl|sh style installer (1 occurrence, e.g. examples/nemoclaw/setup-mem0-nemoclaw.sh)
- Critical advisories counted once per package: 25 matches across 7 lockfiles
- Skill scripts contact: api.mem0.ai, app.mem0.ai
Notes:
- 2 affected packages only in dev/test/docs manifests, not counted
- Telemetry/analytics references in code: telemetry, posthog
Automated scan of commit 753496c on 2 Nov 2026, not a manual audit. 1,333 files checked. What we check
Repo activity
From the GitHub API, fetched 2 Nov 2026.
- 10+Releases, 90 daysLatest ts-v3.3.1, 25 Sept
- –Median issue closeFewer than 5 closed issues
- 68.3kStars+443 since 26 Oct
- 8.1kForks898 open issues
- 2023Repo created20 Jun 2023
0 releases in the last 30 days (GitHub releases feed, last 10 entries).
Questions about Mem0
Answers use this week's StackGrade data.
Is Mem0 safe to use?
Caution. StackGrade's weekly scan of mem0ai/mem0 gives it a Caution label for 18 critical-severity known vulnerabilities in runtime dependencies (OSV) and a skill or agent instruction file (skills/mem0-oss-to-platform/references/gotchas.md) that tells the agent to pipe a remote script into a shell. It does list 151 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 Mem0 is exploitable in your setup. Automated scan of commit 753496c on 2 Nov 2026, not a manual audit.
How does StackGrade score Mem0?
Mem0 scores 55 out of 100 in Week 45: #21 of 52 tracked tools overall and #2 in RAG, knowledge & memory. The score combines maintenance (52), adoption (48) 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 Mem0?
The highest-scored other tools in RAG, knowledge & memory this week: RAGFlow (69, Caution), LlamaIndex (43, Caution). StackGrade has not tested them hands-on.
What licence does Mem0 use?
The licence listed for mem0ai/mem0 is Apache-2.0. Read the licence text before commercial use.
Compare and use it
Used in 1 AI use case
All facts and sources
- Type
- AI tool
- License
- Apache-2.0
- Language
- Python
- Created
- 20 Jun 2023
- Owner
- mem0ai (Organization)
- Forks
- 8,099
- Homepage
- mem0.ai
GitHub description: “The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.”
Sources: github.com/mem0ai/mem0, api.github.com/repos/mem0ai/mem0, raw.githubusercontent.com/mem0ai/mem0/main/README.md. Fetched 2 Nov 2026.
Know when Mem0 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.