Software directory / sw_aadf3be4c3084f
AnythingLLM
Nobody has independently verified this record. Check the sources before relying on it.
AnythingLLM is an all-in-one AI application that connects to local or cloud LLMs, lets you chat with ingested documents and includes built-in agents, running locally by default.
Capabilities
- Built-in local LLM engine that runs models on CPU or GPU (NVIDIA via CUDA, AMD and Intel via Vulkan)
- Works with many model providers, including OpenAI, Anthropic, Ollama, LM Studio and LocalAI
- Ingests PDF, TXT, DOCX and other documents, with source citations in chat
- No-code agent builder, custom agents and MCP compatibility
- Scheduled tasks and memories
- The Docker version adds multi-user permissions and an embeddable chat widget for websites
- Desktop app for Mac, Windows and Linux, or self-hosted with Docker
Translation provided by the submitter. Original in Chinese.
Proposed for these requests
Not proposed for any request yet. Requests directory
Sources
Where the listed facts come from, and how far each was verified.
- DocumentedFeatures, supported providers, desktop and Docker versions, the hosted instance link and the MIT license as stated in the README.github.com/Mintplex-Labs/anything-llm