#1
An all-in-one AI application for chatting with your documents and running AI agents locally, with multi-user support and desktop and Docker versions.
- GitHub stars
- 68k
- Last commit
- yesterday
- Latest release
- v1.19.0
- Licence
- MIT
- Self-hosted
- Yes
- Hosted version
- Available
anythingllm.com
AnythingLLM is an all-in-one AI application for chatting with your own documents and automating work with AI agents. It runs locally by default, lets you connect local or cloud language models, and is written in JavaScript under the MIT license. The README describes it as a way to build a private, fully featured assistant in the style of ChatGPT.
Vector databases, document processing pipelines, multi-user support and agents all come included. Newer features listed include dynamic model routing based on rules you define, automatic and user-managed memories, scheduled tasks with agent capabilities, skill selection, a no-code agent builder, MCP compatibility and multi-modal support for both closed and open-source models.
It is available as a desktop app for Mac, Windows and Linux, as a Docker version that adds multi-user access control, and as a hosted instance, and there is an open-source Android app. Administrators can control access and experience per user. It suits individuals and teams who want a private document-chat and agent workspace without much setup.
Key features
- Chat with your documents using RAG
- Built-in AI agents and no-code agent builder
- Multi-user access control in Docker version
- Connects to local or cloud LLMs
- Vector database and document pipeline support
- MCP compatibility and scheduled tasks
- Desktop apps for Mac, Windows and Linux
Pricing: Self-hosting with Docker is free. Hosted Cloud costs $50 per month (Basic) or $99 per month (Pro); Enterprise with on-premise deployment is quoted on request.
An open-source browser extension that adds a sidebar and web UI for chatting with locally running AI models such as Ollama while you browse.
- GitHub stars
- 8.3k
- Last commit
- 5 days ago
- Latest release
- v1.5.91
- Licence
- MIT
chromewebstore.google.com
Page Assist is a Chrome extension that lets you use AI models running on your own machine while you browse the web. It offers a sidebar for various tasks and a minimal web UI for a local AI model provider such as Ollama or Chrome AI.
Beyond plain chat it supports vision models, internet search, and chatting with PDFs in the sidebar or with documents in pdf, csv, txt, md and docx formats. Tab mention, MCP client support and memory are marked as beta. Besides Ollama it connects to Chrome AI (Gemini Nano, beta) and to OpenAI-compatible APIs such as LLaMA.cpp, LM Studio, Llamafile and vLLM. The Chrome Web Store lists 14 interface languages.
Key features
- Use local models while browsing or as a web UI
- Vision model support and a minimal web UI
- Chat with PDFs and documents
- Tab mention, MCP client and memory support
- Works with OpenAI-compatible providers
TextCortex alternatives: questions
- What is the best open-source alternative to TextCortex?
- AnythingLLM is the top-ranked open-source alternative to TextCortex on Enlisted: An all-in-one AI application for chatting with your documents and running AI agents locally, with multi-user support and desktop and Docker versions. Another strong option is Page Assist.
- What are the best commercial alternatives to TextCortex?
- Rytr, Writesonic, ContentMaschine.ai, CopyPilot AI and Frase are among the hosted, closed-source alternatives to TextCortex listed on Enlisted, which lists 25 in total. Compare their pricing and features on each tool page.
- Are these TextCortex alternatives free?
- Both are open source, so the code is free to use under its licence, and both can be self-hosted on your own server or computer. 1 also offers a paid or managed cloud version if you'd rather not host it yourself.
- How is this list of TextCortex alternatives ranked?
- By a score built from GitHub stars, star growth over the last 30 days and how recently the code changed. 2 of these projects shipped code in the last 30 days. Data is refreshed daily, and nobody can pay to move up.