AnythingLLM
by AnythingLLM · On-device AI assistant with local document knowledge
BenchRank score
Screenshots of AnythingLLM
Homepage
Overview
AnythingLLM is a desktop AI assistant that runs locally, turning documents into an agent's knowledge base without data leaving the device. It also transcribes and summarises meetings on-device, and adds web scraping and search, dynamic model selection, background jobs and custom agent skills. It is MIT licensed and can be self-hosted with Docker or run as a hosted multi-user instance.
- Best for
- Individuals and small teams wanting a private AI assistant that runs on their own machine
- Pricing
- The desktop app and Docker self-hosting are free; hosted instances are $50/month (Basic) or $99/month (Pro), with Enterprise priced on request.
- Runs on
- WebAndroidmacOSLinuxSelf-hosted
Strengths and trade-offs
Strengths
- Runs on device; no account, API key or token limits
- MIT licensed and free to self-host with Docker
- One-file install for macOS, Windows and Linux
- Meeting transcription without a bot joining the call
Trade-offs
- Cloud Basic still needs you to supply your own LLM API key
- SSO and RBAC are only on the contact-sales Enterprise plan
- A support SLA (72 hours) is stated only on the $99/mo Pro plan
- No annual billing rate is published for the cloud plans
How AnythingLLM markets itself
A structured read of the promise, proof and page design on AnythingLLM’s captured homepage.
Homepage capture
“Own your intelligence.”
- Angle: Open source / ownership
- Hero: Product screenshot
Pricing
Published plans and prices from AnythingLLM’s own pricing page.
How this score is made up
Each dimension is scored out of 100 and combined into the headline score using fixed weights.
MCP support
Whether an agent can drive the product through the Model Context Protocol, and how much setup that takes.
API quality
Public API surface: machine-readable spec, official SDKs, documented auth, errors, rate limits and versioning.
Documentation
Publicly reachable docs — coverage, freshness, code samples and machine readability.
Agent friendliness
How readable the site is to an automated client: llms.txt, structured data, server-rendered content, crawler access.
Pricing transparency
Whether real prices are published, self-serve signup exists, and usage costs are knowable without a sales call.
Changelog
A public, dated record of what shipped and when — the clearest signal that a product is still alive.
Marketing site structure
Whether the site answers a buyer's questions: clear positioning, the pages that matter, and accessibility.
Page speed
How fast the site loads for real visitors: Chrome UX Report 75th-percentile LCP, INP and CLS, with a Lighthouse mobile run standing in where a site has too little traffic for field data.
Operational trust
Status page and incident history, security disclosure, compliance and data-processing documentation.
Measured, but not part of the score
Useful to know, but not a mark for or against the product — so these do not affect the ranking.
Openness
Source availability, self-hosting, data export and open standards. Scored and shown, but not part of the composite — paid SaaS is not worse for being paid SaaS.
Maintenance
Release cadence and repository activity. Scored and shown, but not part of the composite — it is only measurable for open repositories.
This doesn’t look right — report a problem with AnythingLLM’s score
Where this comes from
The AnythingLLM pages BenchRank reads when it scores the product — its documentation, release notes, status and security pages, and its repository where there is one.
Alternatives in Chat Assistants
Ranked 1
77.8 — BenchRank score out of 100LobeHub
LobeHub · Hosted multi-agent platform with a skills and MCP marketplace
Best for: Individuals and small teams wanting to run several AI agents on a hosted, credit-metered platform
Ranked 2
77.3 — BenchRank score out of 100Browser Use
Browser Use · Open-source browser automation with hosted stealth browsers and agents
Best for: Teams building web automation that need hosted stealth browsers and agent APIs, plus an open-source library
Ranked 3
71.3 — BenchRank score out of 100OpenClaw
OpenClaw · Open-source AI assistant that runs on your own machine
Best for: People who want an AI assistant they run themselves and drive from WhatsApp, Telegram or Discord.
Is this your product?
Claim AnythingLLM to manage its profile. Claiming lets you suggest edits to the descriptive fields — it never changes scores or rankings.