# AnythingLLM AnythingLLM is a local, all-in-one AI app for self-hosters that works with any large language model, providing document chat, retrieval-augmented generation, and configurable AI agents. It is open source and self-hosted, installable on Kubernetes (Helm), TrueNAS, Docker Hub, Umbrel, ZimaOS and Unraid. Canonical page: https://ourlocalhost.com/app/666/anythingllm ## Description AnythingLLM is a local, all-in-one AI app for self-hosters that works with any large language model, providing document chat, retrieval-augmented generation, and configurable AI agents. ## Platform availability Available on 8 of 9 platforms: Unraid, TrueNAS, Umbrel, ZimaOS, Proxmox, Helm, Mac, Linux. ## Desktop and other devices Mac, Linux. ## Health score 81/100 (Excellent), based on 5 of 5 factors. - Maintained: 100 (last commit 16 days ago) - Popular: 96 (66,829 GitHub stars) - Easy to install: 100 (8 install platforms, install notes, setup guide, Docker image) - Light to run: 60 (2 GB minimum RAM, runs on ARM) - Security check: 20 (1 serious finding, 5 minor, CI, tests) ## Security check 1 serious finding: Uses proxy-addr 2.0.7, which has a known critical vulnerability. Automated checks on commit 2a10d05, 11 Oct 2026. Not an audit. ## Links - Documentation: https://docs.anythingllm.com/ - GitHub: https://github.com/Mintplex-Labs/anything-llm - Kubernetes (Helm): https://artifacthub.io/packages/helm/anything-llm-helm-chart/anything-llm - TrueNAS: https://apps.truenas.com/catalog/anything-llm/ - Docker Hub: https://hub.docker.com/r/mintplexlabs/anythingllm - desktop: https://github.com/Mintplex-Labs/anything-llm/releases/latest - Umbrel: https://apps.umbrel.com/app/anything-llm - ZimaOS: https://github.com/IceWhaleTech/CasaOS-AppStore/tree/main/Apps/AnythingLLM - Unraid: https://ca.unraid.net/apps/anythingllm-0zoufm008uc3x0?q=AnythingLLM - Official website: https://useanything.com ## Common questions ### What host files and port do I need before starting AnythingLLM with Docker? Create the storage folder and an empty .env file on the host before running the Docker command. Port 3001 must be free, and the storage folder is what keeps your settings and files after restarts. ### Does the self-hosted AnythingLLM server support multiple users? Yes, multi-user instance support and permissioning are available. The README marks this as a Docker version-only feature. ### Can I embed an AnythingLLM chat widget on my website? Yes, AnythingLLM includes a custom embeddable chat widget. The README lists this as available for the Docker version only. ## Alternatives - Alpaca - Ollama Client: Alpaca is an Ollama client where you can manage and chat with multiple models, Alpaca provides an easy and begginer friendly way of interac… - ChatGPT: ChatGPT is a generative artificial intelligence chatbot developed by OpenAI and launched in 2022. - Claude: AI assistant for chat and API, performing summarization, search, writing, Q&A, and coding with high reliability, customizability, priva… - DeepSeek: DeepSeek is a state-of-the-art AI assistant designed to provide intelligent, conversational support across diverse tasks. - Ensu: Private offline on-device local LLM app by Ente, open source code, no accounts or tracking, and works cross-platform on mobile and desktop… - GPT4ALL: GPT4All runs open-source large language models (LLMs) privately on your own hardware, providing a local chat interface and server that need… - Jan.ai: Open-source offline AI chat software supporting local LLMs, cloud model connections, custom assistant creation, OpenAI-compatible API, and… - LM Studio: LM Studio is an application for running and experimenting with local large language models (LLMs) such as gpt-oss, Llama, Gemma, Qwen, and… - LibreChat: LibreChat is an open-source, self-hosted, multi-provider AI chat interface that provides a ChatGPT-style experience for teams or individual… - LocalAI: LocalAI is a free, open-source, self-hosted AI engine that provides a drop-in, OpenAI-compatible API for running local models. - Lumo by Proton: Privacy-first AI assistant with zero-access encryption, no logging or profiling, open-source code, and user-controlled conversations, subje… - Ollama: Ollama is a local runtime for large language models (LLMs) that provides an application programming interface (API) and command-line interf… --- Source: Our Local Host (https://ourlocalhost.com/app/666/anythingllm), the self-hosted and open-source app directory.