Open-source Microsoft Copilot alternatives

Open WebUI is a self-hosted web interface for working with large language models. It connects to Ollama for local models and to any OpenAI-compatible endpoint, so one deployment can front LM Studio, Groq, Mistral, OpenRouter, vLLM and similar backends side by side. It is designed to keep working fully offline when you rely only on local models.

Administrators get role-based access control with user groups and per-group permissions, which suits shared team or household installs. Beyond chat there is retrieval-augmented generation over your documents, custom models that bundle instructions, tools and knowledge into agents, and an extension system made of filters, actions, pipes, tools and skills. External services attach through MCP, MCPO and OpenAPI tool servers, and an optional Open Terminal feature gives agents a filesystem to work in.

You can install it with pip, uv or Docker, or deploy it to Kubernetes using kubectl, kustomize or Helm, and container images are tagged for bundled Ollama and for CUDA. The project lists an enterprise plan for organizations that want vendor support. Its license is listed as custom rather than a standard one, so review the terms before reselling or rebranding it.

LobeHub describes itself as a Chief Agent Operator that organizes your AI agents into around-the-clock operation. It is designed to take on the hiring, scheduling and reporting for a whole team of agents so that you stay in charge without having to stay online. The project is written in TypeScript, and its GitHub topics point to chat, agent, knowledge base and MCP functionality.

The README groups its features around four ideas: Operator, Create, Collaborate and Evolve, which cover treating agents as the unit of work, scaling new kinds of collaboration networks, and the co-evolution of humans and agents. A plugin ecosystem extends the platform, and the project's topics reference model providers such as OpenAI, Claude, Gemini and DeepSeek.

LobeHub can be self-hosted: the README documents deployment on Vercel, Zeabur, Sealos and Alibaba Cloud, as well as Docker, and describes the environment variables used for configuration. GitHub lists the license as 'Other', so check the repository for the exact terms. It suits individuals and teams who want to run a shared workspace of AI agents on infrastructure they choose.

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.

Cherry Studio is a desktop client for working with multiple large language model providers, available for Windows, Mac and Linux. It is written in TypeScript and licensed under AGPL-3.0, and it is described as an AI productivity studio offering chat, autonomous agents and a large library of ready-made assistants.

It can connect to major cloud LLM services such as OpenAI, Gemini and Anthropic, to AI web services like Claude, Perplexity and Poe, and to local models through Ollama and LM Studio. Conversations can involve several models at once, and users can pick from more than 300 preconfigured assistants or create their own.

Other tools include handling of text, images, Office files and PDFs, WebDAV backup, Mermaid chart rendering, code highlighting, global search, topic management, AI translation, mini programs and an MCP server. Themes and complete Markdown rendering are included, and no environment setup is needed. It suits individuals who want one desktop app for many models.

LibreChat is an open-source chat interface modeled on ChatGPT that you can self-host. It is written in TypeScript and released under the MIT license. Rather than being tied to one vendor, it connects to many providers, including OpenAI, Anthropic, Azure, AWS, Google Vertex AI and Gemini, Mistral, Groq, DeepSeek and OpenRouter, and lets you switch between models within a conversation.

Its feature set includes agents, MCP and skills, artifacts, a code interpreter, image generation, OpenAPI actions and functions, presets, message search and secure multi-user authentication. The recent README highlights an agent management API in beta, optional attached workspaces for code workers that are described as highly experimental, code approval controls, manual context compaction and unified file attachments.

Administrators can set role-based grants and approval modes for sensitive actions such as file writes and command execution. LibreChat suits individuals and organizations that want a private alternative to ChatGPT with a choice of models, and teams that need multi-user access control on infrastructure they manage.

Jan is an open-source desktop application that serves as a ChatGPT alternative you control. It can download and run language models such as Llama, Gemma, Qwen and GPT-oss from Hugging Face entirely on your own computer, so conversations stay private and work without an internet connection.

When you want more capability than local hardware allows, Jan can connect to cloud models from OpenAI, Anthropic, Mistral, Groq, MiniMax and others from the same interface. You can create custom assistants for specific tasks, and Model Context Protocol support adds agentic abilities. A built-in local server on localhost port 1337 exposes an OpenAI-compatible API, so other applications can use your local models as a drop-in backend.

Jan is built with Rust and Tauri and ships installers for Windows, macOS and Linux in deb and AppImage form. Its license is listed as 'Other' on GitHub, so check the repository terms before redistributing it. It is meant for people who want local AI with a polished interface rather than a command line.

Chatbox is a desktop client for talking to ChatGPT, Claude and other large language models, available for Windows, Mac and Linux. This repository holds the Community Edition, which is published as open source under GPLv3, and the maintainers say they regularly sync code between it and their pro repository. It is written in TypeScript.

It works with multiple providers, including OpenAI, Azure OpenAI, Claude, Google Gemini and Ollama, which makes local models such as Llama, Mistral and Mixtral available, plus ChatGLM-6B, and it can generate images through DALL-E 3. Setup is a matter of downloading an installer, launching the app and entering your provider settings.

System requirements listed are Windows 10, macOS 11 on Intel or Apple Silicon, or Ubuntu 20.04 and compatible AppImage-capable distributions. Download links for iOS and Android, including an APK, are mentioned alongside the desktop builds. Chatbox suits people who want a single desktop front end for several AI services, using their own API keys or local models.

NextChat is a lightweight AI chat assistant that works with several model providers, including Claude, GPT, Gemini and DeepSeek, and local runtimes such as Ollama. It is available as a web app and PWA, with desktop apps for Windows, macOS and Linux built using Tauri, and mobile apps. The code is written in TypeScript with Next.js and React, and it is released under the MIT license.

You can deploy your own instance, for example on Vercel, or use the hosted NextChatAI service, which the project describes as pay-as-you-go and not requiring your own API key. The README also notes support for the Model Context Protocol when an environment flag is set before building. An Enterprise Edition targets companies that need private deployment, brand customization, centralized management of AI resources, permission controls and integration of internal knowledge bases.

Khoj is a personal AI app that you can run on your own machine or scale up to an enterprise cloud deployment. You can chat with local or online models, such as Llama, Qwen, Gemma, Mistral, GPT, Claude, Gemini and DeepSeek, and get answers drawn from the internet and from your own documents, including images, PDFs, Markdown, org-mode files, Word documents and Notion pages.

It can be reached from a browser, Obsidian, Emacs, a desktop app, a phone or WhatsApp. Users create agents with their own knowledge, persona, chat model and tools, set up automations that deliver personal newsletters and smart notifications by email, and use advanced semantic search to find relevant documents. It can also generate images and speak responses aloud. The README highlights benchmark results for retrieval and reasoning and introduces Pipali, a separate open-source AI coworker for your own computer.

Khoj is written in Python and licensed under AGPL-3.0. You can self-host it, with offline models via llama.cpp, or use the hosted app. It suits individuals and teams who want an AI assistant grounded in their notes and files while keeping a choice of model.

Big-AGI is a multi-model AI workspace aimed at engineers, founders and researchers who want to use several AI models from one interface. This repository is the open-source foundation of the product, and it can be deployed on your own infrastructure or in the cloud.

Its main feature is Beam, which sends a question to multiple models and merges the answers, with the aim of reducing hallucinations. Further capabilities include AI personas, native search, image generation from text, voice, streamed responses, code highlighting and execution, PDF import and developer presets. Repository topics show connections to APIs from OpenAI, Anthropic, Gemini, DeepSeek, Perplexity and xAI.

Big-AGI is written in TypeScript and licensed under MIT. The project describes itself as independent and not venture-funded, with a Pro subscription at $10.99 per month that pays for development, which also benefits the free and open-source tiers.