Open-source Claude alternatives

Ollama makes it straightforward to run open large language models on your own machine. You install it on macOS, Windows or Linux, or use the official Docker image, then pull a model and chat with it from the command line. It is written in Go and released under the MIT license, and it builds on the llama.cpp project for inference.

Besides the CLI, Ollama provides a REST API for managing and running models, with official Python and JavaScript client libraries. Models can be imported and customized through a Modelfile, and an online library lists what is available. It can be connected to coding agents and assistants such as Claude Code, OpenCode, Codex and OpenClaw, and many community chat interfaces, including Open WebUI and LibreChat, work with it.

Because models run on your own hardware, Ollama can serve as a self-hosted alternative to cloud assistants such as ChatGPT and Perplexity when privacy, offline use or cost control matter. It is aimed at developers and hobbyists experimenting with open models, and at teams that want to wire local models into their own applications.

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.

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.

Oh My Claudecode, often shortened to OMC, is an open-source add-on for Claude Code, Anthropic's command line coding assistant. It is not a standalone application: it layers multi-agent orchestration on top of an existing Claude Code setup so that a team of AI agents can share and run work together.

The project advertises a zero learning curve, meaning developers can use its prepared workflows instead of learning every Claude Code feature themselves. Topics highlight agentic coding, multi-agent systems and parallel execution. The repository points to documentation, a CLI reference, workflows and a migration guide, and it has sibling projects for other tools, including oh-my-codex for the OpenAI Codex CLI and a lighter alternative called gajae-code.

It is MIT licensed and written in TypeScript, with translated READMEs in several languages. Because it runs locally alongside the Claude Code CLI, there is nothing to host. It is intended for developers who already use AI coding agents and want a structured way to coordinate several of them.

OpenWork is a free, open-source desktop application, available on macOS, Windows and Linux, in which AI agents work on your own files. It is presented as an alternative to Claude Cowork and Codex and is built on OpenCode. It is model-agnostic: connect more than fifty providers with your own API keys, or run local models through Ollama, and no OpenWork account is needed to use it locally.

A key idea is sharing: teams can distribute skills and MCP servers, and attaching one OpenWork MCP server to Codex, Claude Code, Cursor or a similar agent lets you carry the same skills, MCPs and connected services across tools, teammates and machines. The desktop app gives you a dedicated workspace but is optional, because the capabilities work from whichever agent you already use. For bigger organizations an admin interface lets administrators release capabilities, control who can use them and set up either shared or per-user connections.

The desktop app is MIT licensed according to the README, while the repository license is listed as 'Other' on GitHub, so confirm what applies to each component. It suits individuals and teams who want agentic automation of file-based work with control over models and data.

Suna is the repository of Kortix, which describes itself as an open-source AI Management System. Instead of a single chatbot, it organizes AI agents that carry out tasks and deliver finished work such as reports, code and replies. Agents, the skills they share, company memory and connectors to other services are all kept as files in a git repository, so configuration is versioned and can be reviewed like code.

Each agent session runs in an isolated cloud sandbox on its own branch, and the result lands as a change request that a human approves before it is merged. The platform works with any model provider using your own API keys, rather than being tied to a single model vendor.

The project positions itself as an open alternative to closed, hosted agent products such as ChatGPT, offering source access and the option to run on your own cloud or on-premise network. The repository lists its license as 'Other', so check the license file before commercial use. A managed cloud edition is also available.

Chat UI is a chat interface for LLMs built as a SvelteKit application. It is the open source codebase behind HuggingChat on Hugging Face and lets you run a similar conversational front end against models you choose, whether hosted or running locally.

The current version speaks only to OpenAI-compatible APIs, configured through a base URL and a models endpoint. The README lists the Hugging Face Inference Providers router, a llama.cpp server, Ollama through its OpenAI-compatible bridge, OpenRouter and Poe as example backends. Older provider-specific integrations were removed from the main branch but remain available on a legacy branch.

Setup involves creating an .env.local file with the endpoint and key, choosing a database option, and launching the app, with an optional Docker image. The project is written in TypeScript with Tailwind CSS and is licensed under Apache-2.0, making it a base for self-hosted assistants.

Enchanted is an open-source app for macOS, iOS and visionOS that provides a chat interface for privately hosted language models. It works with Ollama, so models such as Llama 2, Mistral and Vicuna run on a server you control while the app supplies the polished front end. The README describes it as essentially a ChatGPT-style interface that connects to your own models.

The feature list includes conversation history stored on the device, markdown rendering for tables, lists and code blocks, voice prompts, read-aloud text to speech, image attachments, a configurable system prompt, editing messages or resubmitting them with a different model, deleting conversations, light and dark modes and a Spotlight-style panel on macOS. The project notes that all features work offline against your own server.

You need to run your own Ollama server, version 0.1.14 or later, and point the app at it, either publicly or through your own network setup. The app is distributed through the App Store and licensed under Apache-2.0. The README mentions that a successor project called Jaz is the new iteration of this one.

ChatMCP is an AI chat client that implements the Model Context Protocol, the standard used to connect language models to external tools and data. It is built with Flutter and Dart, so the same app runs on macOS, Windows, Linux, iOS, Android, and the web. It is released under the Apache-2.0 license.

Installers are provided through GitHub releases for desktop and Android, an iOS build through TestFlight, and a web version hosted on GitHub Pages. The README notes Linux runtime requirements for AppImage and DEB packages on Ubuntu 22.04 and 24.04, and mentions improvements such as better dark theme support and unified data storage in recent versions. Documentation is available in English, Chinese, and Turkish.

ChatMCP suits developers and enthusiasts who want a single graphical client for trying MCP servers with the language model of their choice, rather than using a command-line host. It is a client application, so there is no server component to host.

slides-grab is a harness, editor and linter for creating presentations with AI coding agents. Slides are generated as plain HTML and CSS, which agents handle well, and you can select an area on a slide and ask the agent to change it, while simple tweaks such as text, size or bold can still be done by hand.

The project supports Claude Code and Codex and describes itself as an open-source alternative to Claude Design. Decks can be converted to PDF or to an experimental PPTX format. There is also a build for a ChatGPT plugin ZIP containing the published skills, though export, visual validation, the local editor and image generation need the local Node.js and Playwright runtime. A gallery of example presentations is available online.

The editor is a single JavaScript file, so adding new coding agents or changing designs is straightforward. The project requires Node.js 20 or newer, uses main as its only integration branch, and is licensed under MIT. It runs locally on your own machine with your own agent subscription. It suits developers and technical presenters who want AI-assisted decks they can version and edit as code.