# AnythingLLM

> AnythingLLM is a desktop (Mac, Windows, Linux) and Docker app for chatting with your documents: it ingests PDFs, DOCX and more into a built-in LanceDB vector store with a native embedder, then answers with citations using a local llama.cpp model, Ollama, LM Studio or 30+ cloud providers. Agents can browse the web. MIT licensed; ships no chat model weights, so each model's licence matters. Docs recommend 16GB RAM and an 8-core CPU. Anonymous telemetry is on by default and can be disabled.

- Repository: https://github.com/Mintplex-Labs/anything-llm
- Official docs: https://docs.anythingllm.com/
- Checked: 2026-10-15

## What it replaces
- ChatGPT Plus: Chat assistant, Chat with your documents (partial). Replaces the chat interface and file chat; answer quality depends on the model you run. Local models are generally less capable than paid frontier models.
- Perplexity Pro: Chat with your documents (partial). Chat over your own files with citations; web answers only via agent browsing, not a dedicated answer engine.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, desktop app or Docker; local by default | https://github.com/Mintplex-Labs/anything-llm#readme | 2026-10-15 |
| Code licence | Confirmed | MIT | https://github.com/Mintplex-Labs/anything-llm/blob/master/LICENSE | 2026-10-15 |
| Model weights licence | Confirmed | No bundled chat weights; licence depends on the model you pick | https://github.com/Mintplex-Labs/anything-llm#supported-llms-embedder-models-speech-models-and-vector-databases | 2026-10-15 |
| Commercial use | Confirmed | Yes, MIT code; check the licence or terms of the model you use | https://github.com/Mintplex-Labs/anything-llm/blob/master/LICENSE | 2026-10-15 |
| Paid services needed? | Confirmed | None required; local LLM, embedder and vector DB by default; cloud optional | https://github.com/Mintplex-Labs/anything-llm#supported-llms-embedder-models-speech-models-and-vector-databases | 2026-10-15 |
| Hardware | Confirmed | Recommended 16GB RAM, 8-core CPU; GPU recommended on Windows; storage varies by model | https://docs.anythingllm.com/installation-desktop/system-requirements | 2026-10-15 |
| Operating systems | Confirmed | Desktop for Mac, Windows and Linux; Docker for servers | https://github.com/Mintplex-Labs/anything-llm#readme | 2026-10-15 |
| Setup effort | Confirmed | Easy; desktop installer, or Docker for multi-user | https://anythingllm.com/download | 2026-10-15 |

GitHub: 67180 stars, 7507 forks, last push 2026-10-16, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/anything-llm). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.