AnythingLLM Mintplex-Labs/anything-llm

All-in-one desktop or Docker app to chat with your documents using local or cloud LLMs, with agents and a built-in vector database.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

AnythingLLM at a glance

Checked 15 Oct 2026

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.

Cite this pageRepoQuarry. “AnythingLLM.” Checked 15 Oct 2026. https://repoquarry.dev/projects/anything-llm

How much of ChatGPT Plus does it replace?

2 of 3 jobs. 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.

Chat assistant Partial replacement

Chat with your documents Partial replacement

Web search answers Not covered

For web search answers, see other ChatGPT Plus alternatives. You may also need to build an interface, an API server and hosting yourself.

How much of Perplexity Pro does it replace?

1 of 3 jobs. Chat over your own files with citations; web answers only via agent browsing, not a dedicated answer engine.

Web search answers Not covered

Chat assistant Not covered

Chat with your documents Partial replacement

For web search answers, see other Perplexity Pro alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Yes, desktop app or Docker; local by default runs locally by default with zero setup friction. github.com · anything-llm#readme ↗ 1d ago

Code licence MIT github.com · LICENSE ↗ 1d ago

Model weights licence No bundled chat weights; licence depends on the model you pick Any open-source llama.cpp compatible model github.com · anything-llm#supported-llms-embedder-models-speech-models-and-vector-databases ↗ 1d ago

Commercial use Yes, MIT code; check the licence or terms of the model you use github.com · LICENSE ↗ 1d ago

Paid services needed? None required; local LLM, embedder and vector DB by default; cloud optional AnythingLLM Native Embedder (default) ... LanceDB (default) github.com · anything-llm#supported-llms-embedder-models-speech-models-and-vector-databases ↗ 1d ago

Hardware Recommended 16GB RAM, 8-core CPU; GPU recommended on Windows; storage varies by model The storage requirements are based on the size of the local LLM model you want to use. docs.anythingllm.com · system-requirements ↗ 1d ago

Operating systems Desktop for Mac, Windows and Linux; Docker for servers AnythingLLM for desktop (Mac, Windows, & Linux)! github.com · anything-llm#readme ↗ 1d ago

Setup effort Easy; desktop installer, or Docker for multi-user AnythingLLM for desktop (Mac, Windows, & Linux)! Download Now anythingllm.com · download ↗ 1d ago