One private chat window for ChatGPT, Claude, Gemini and models on your own computer.
AnythingLLM
Ask questions about your own documents with an AI that can run entirely on your computer.
AI helpers
MIT
What it does
AnythingLLM lets you drop in PDFs, Word files, web pages and notes, then chat with them and get answers that point back to the source. Each topic gets its own "workspace", so household paperwork, a hobby and a course stay separate. It comes with a built-in local AI and document search, so it can work without any cloud account, or you can plug in ChatGPT, Claude, Gemini or Ollama.
- Chat with PDFs, Word files, web pages and more, with sources shown
- Built-in local AI, so it works with no cloud account at all
- Separate workspaces per topic, and separate logins per person
- Agents that can search the web, summarise and run on a schedule
Great for: People who want to chat with their own documents privately, from household paperwork to study notes, without sending them to a big tech company.
- LicenceMIT
- Where it runsOnline (from $16/month) · Your computer (free)
- Built withjavascript
- Your dataStays in your own copy
- SourceMintplex-Labs/anything-llm
Ways to use it
Choose one when you tell your AI. It sets everything up with you, in plain words.
- Online with Elestio from $16/monthFully managed hosting on your own private server, with automatic backups, updates and monitoring. Third-party host.
- On my own computerFreeAnythingLLM has a desktop app. Your AI can install it with you.
AnythingLLM has no login by default: keep it private, or ask your AI to add a password before putting it online.
Hosts are independent companies, not BespokeAI. You sign up and pay them directly. We may earn a referral fee, which never changes your price.
How people are using this project
Examples of what people ask their AI to do with AnythingLLM. Start from one, or just tell your AI and it will ask what you'd like.
-
“I have a folder of PDFs: insurance, mortgage, boiler manual, council tax. Set up a 'House' workspace so I can ask things like 'when does my car insurance renew?' and see which document it came from.”
Start with this idea -
“I don't want anything to leave my laptop. Set up AnythingLLM with the built-in local model and embedder, and turn off telemetry.”
Start with this idea -
“Turn on multi-user mode so my partner and I each have our own login, with a shared 'Family' workspace and private ones for each of us.”
Start with this idea -
“My son is revising GCSE biology. Make a workspace from his class notes that only answers from those notes and quizzes him at the end.”
Start with this idea -
“Every Monday morning, summarise any new documents I added to my 'Letters' workspace last week and list anything I need to act on.”
Start with this idea -
“My mum finds the chat screen fiddly. Make the text bigger, hide the sidebar for her account and keep just one big 'Ask a question' box.”
Start with this idea
Can I trust it?
- MIT. Very permissive. You can use, change and share it, even commercially, as long as you keep the copyright notice. No obligation to publish your changes.
- Your data: stores personal data, on your own device or server. Everything lives in the storage folder you mount (STORAGE_LOCATION): the SQLite database (anythingllm.db), uploaded and processed documents, the LanceDB vector index, downloaded models, and the .env file with settings and keys.
- Other services: Built-in local LLM engine and embedder (optional, free (uses your own computer)); Cloud AI providers (OpenAI, Anthropic, Gemini, Mistral, OpenRouter, Groq and many more) (optional, pay-per-use with your own API key); Ollama, LM Studio or LocalAI (optional, free (uses your own computer)); Web search for agents (e.g. SearXNG, Serper, Bing, Tavily) (optional, free (SearXNG) or free tiers / pay-per-use); PostHog telemetry (optional, free)
- Pinned version
0acf0e8. Every handover uses exactly this code, which we've reviewed. - Out of the box the Docker version has no password. Set one (or turn on multi-user mode) in Settings → Security before anyone else can reach it, and use HTTPS before putting it on the internet.
- When you use a cloud model, the parts of your documents that match your question are sent to that provider with each message. Use the built-in model or Ollama to keep everything local.
- Anonymous telemetry is on by default. Turn it off with DISABLE_TELEMETRY=true or in Settings → Privacy.
- API keys are stored in the .env inside your storage folder. Never share that folder or paste it into an AI chat.
- The Docker command needs --cap-add SYS_ADMIN for the built-in web scraper; agents with web browsing or SQL access can reach other systems, so only enable the skills you need.
Did it work for people?
No reports yet
Be the first to tell others how it went.
More for ai helpers
A personal AI that knows your notes and documents and can research the web for you.
Ask a question, get a written answer with sources, from a search engine you run yourself.