AI & Agents
AnythingLLM
Source: Mintplex-Labs/anything-llm · ★ 61428 · JavaScript
Last updated 2026-06-11 · benchmark measured 2026-10-13 — deterministic & reproducible
Desktop app for chatting with documents and AI agents using any LLM, fully offline.
AnythingLLM at a glance
AnythingLLM is a free, open-source desktop application that lets individuals, developers, and teams chat with documents and run AI agents using any local or cloud LLM, with data processed locally on the user's device.
Good for
- Privacy-conscious users or teams who want to keep documents and AI processing entirely on their own device
- Non-technical users who want to chat with PDFs, Word files, CSVs, or codebases without writing code
- Developers who want to extend the app with a built-in API, custom agents, and data connectors
Pricing
Desktop app: free (MIT license). Cloud: Basic $50/mo, Pro $99/mo, Enterprise - contact for quote.
Questions people ask
Is AnythingLLM free to use?
The desktop app is free and open source under the MIT license. A paid cloud version is also available, with Basic at $50/month and Pro at $99/month, plus a custom-quote Enterprise plan.
Does AnythingLLM work without an internet connection?
Yes, it is designed to run fully offline, storing and processing data locally on your device by default.
What kinds of files can I chat with?
It supports PDFs, Word files, CSVs, and codebases, among other document types.
Can I use my own choice of AI model?
Yes, AnythingLLM works with any LLM, whether it's run locally on your machine or accessed in the cloud.
Is there a mobile app?
Yes, AnythingLLM Mobile runs small models on-device on Android, with features like web search, document chat, and scheduled jobs, and can pair with the desktop app for access to larger models.
Written by Legit.Show from anythingllm.com on 2026-10-08. It does not change the score.
Are you the maker of AnythingLLM? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/gh-mintplex-labs-anything-llm/2026-10-13. That address never changes; this page moves with every re-measure.
Legit.Show scored AnythingLLM 70/100 on 2026-10-13, measured across all 7 frames from its public surface. legit.show/s/gh-mintplex-labs-anything-llm/2026-10-13
Is AnythingLLM production-ready?
Legit.Show scores AnythingLLM 70 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on AnythingLLM (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Accessibility; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 70/100
- Accessibility — 100/100
- Security — 45/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 0/100How this compares across the catalogue: The Privacy Gap
- Reliability — 100/100
- Standards — 89/100
- Discoverability — 85/100
What we measured
- Security headers present: X-Content-Type-Options, Referrer-Policy.
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 140 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who built it
product account @AnythingLLM
Who it's for
Individual users · Non-technical users · Developers · Enterprises · Privacy-conscious teams
Pricing
Free and open source (MIT licensed)
Sources and updates
- Description
- Taken from anythingllm.com's own website on 2026-06-11.
- Operator
- AnythingLLM, as named in anythingllm.com's terms, privacy page or footer.
- Code
- github.com/Mintplex-Labs/anything-llm.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-10-13.
Put together from public information, without AnythingLLM's involvement. If anything here is wrong, tell us and a person will check it.
Visit AnythingLLM → · Alternatives to AnythingLLM → · How this was measured →