AnythingLLM
AnythingLLM is an all-in-one AI application: turn documents, websites and other content into a chat-ready knowledge base with RAG, agents and multi-user workspaces. It connects to local model runners such as Ollama and LM Studio as well as OpenAI, Anthropic and other hosted providers.
AnythingLLM
In Development
This script is currently in active development and may be unstable or incomplete. Use in production environments is not recommended.
This script is currently in active development and may be unstable or incomplete. Use in production environments is not recommended.
Installation
Default install:
1
bash -c "$(curl -fsSL https://raw.githubusercontent.com/community-scripts/ProxmoxVED/main/ct/anythingllm.sh)"
Configuration
Config file:
1
/opt/anythingllm/server/.env
Notes
Open http://[IP]:3001 and complete the onboarding: pick an LLM provider (for example an existing Ollama container) and an embedding model. Nothing works until a provider is configured.
Upstream does not support bare-metal deployments - BARE_METAL.md is explicitly a reference only and issues from non-Docker installs are not answered. This script follows that documented procedure.
Documents, the LanceDB vector store and the SQLite database live in /opt/anythingllm_data/storage, outside the app directory, so they survive updates. Back up that directory.
Two services run here: anythingllm (server and web UI on 3001) and anythingllm-collector (document processing). No models run in this container - point it at a separate Ollama or a hosted API.