whereismyai
AnythingLLM
AnythingLLM is an open-source AI assistant application that runs entirely on local devices for private productivity tasks.
AnythingLLM is a private, on-device AI assistant application designed for productivity, document chat, and meeting transcription. It runs entirely on your computer or mobile device without requiring accounts, cloud API keys, or internet connectivity. The software features a built-in meeting assistant that transcribes and summarizes calls locally, real-time voice refinement, web search integrations via You.com, and support for hardware-accelerated models including Microsoft Foundry Local. Users can chat with documents, build custom workflows, and scale capabilities using the developer API and custom tool builder. It is available as a free, MIT-licensed open-source desktop app for macOS, Windows, and Linux, as well as an Android mobile application.
AnythingLLM at a glance
- Best for: Software engineer, Founder, Researcher
- Runs on: macOS, Windows, Linux, Android, API, self-hosted, open source
- Pricing: Free
- Released: June 2023
- Category: AI chat assistant
- Website: anythingllm.com
Key features
- Local meeting transcription and summary generation
- Document chat and knowledge base creation
- Real-time voice refinement and speech processing
- Web search integration without API keys
- Custom tool builder and developer API
- Multi-model selection and auto-recommendation
- Mobile synchronization with desktop workspaces
Use it for
- Transcribing and summarizing meetings locally
- Chatting with local documents and files
- Conducting AI research without cloud dependencies
- Building custom workflows and developer tools
Companions
Tools that articles about AnythingLLM recommend using with it, each with its job.
- Cline — Open source, any model, with approval on every step
- CrewAI — Point CrewAI's agents at the local endpoint.
- LangChain — Framework for custom agents with memory and tools on local models.
- Chroma — Local vector database for embeddings and semantic search.
- OpenHands — Runs autonomous agents locally, in the cloud, or inside your VPC with complete control.
Companion to
Tools whose articles name AnythingLLM as a companion, each with its job for them.
- LM Studio — AnythingLLM: Document chat
- Ollama — AnythingLLM: Chat with documents
Alternatives to AnythingLLM
- GPT4All — Runs open-source language models locally on your device for complete data privacy.
- LM Studio — Runs open source language models locally with real-time voice transcription.
- Ollama — Run open models locally or in the cloud with private prompts
- Open WebUI — Run AI on your own terms with complete data privacy and self-hosting control.
- llmspy.org — Self-host access to 530+ AI models across 24 providers with built-in tools.
- LLMStack — Builds AI applications and agents with custom data without writing code.
- Everywhere — Extracts on-screen context via a shortcut to deliver tailored AI strategies.
- LibreChat — Unifies multiple AI models and tools in one customizable, open-source platform.
- RikkaHub — Integrates a Linux workspace for AI agents on Android devices.
- Chat UI — It runs instantly anywhere with a web browser and weighs under 100 KB.
- KernelAI — Runs 53 open-weight models offline with no account or subscription required.
- OpenLess — Keeps data local and allows the use of your own preferred ASR and LLM providers.
All AnythingLLM alternatives