Best Free & Open Source Alternatives to Claude

Lobe Chat is an AI chat and agent platform that provides a unified interface for interacting with multiple large language models and building personalised AI workflows. It supports connections to local models via Ollama, as well as major cloud providers, and allows users to switch between models within the same workspace. The platform extends beyond simple chat with plugin integrations, voice conversation (TTS/STT), image generation, and internet search capabilities.

Key features include an agent marketplace with thousands of community-contributed agents, branching conversations that support multiple discussion threads, real-time content generation for SVG, HTML, and documents, and a personal memory system that adapts to user context over time. Desktop and mobile applications are available alongside the web interface.

Lobe Chat is designed for developers, researchers, and knowledge workers who want a powerful, customisable AI assistant that can run locally for privacy, integrate with a wide range of models and tools, and support complex multi-step workflows beyond single-turn interactions.

Open WebUI is a self-hosted platform for running AI models on your own infrastructure. It provides a polished chat interface that connects to local models through Ollama, as well as cloud providers such as OpenAI and Anthropic, enabling teams to use different models from a single unified interface. All conversations, files, and model configurations are kept in one place under your control.

The platform supports voice interactions, vision-capable models, retrieval-augmented generation, and code execution. Python-based functions and tools allow developers to extend its capabilities and build custom workflows. For organisations, Open WebUI offers SSO, role-based access control, audit logging, and a community model and prompt marketplace with hundreds of thousands of shared resources.

Open WebUI is designed for individuals who want private AI access, development teams building AI-powered applications, and enterprises that need compliant, data-sovereign AI deployments without sending sensitive information to third-party cloud services.

Ollama is a tool for running large language models locally on your own hardware. It provides a simple command-line interface and a REST API compatible with the OpenAI API format, making it straightforward to pull, run, and switch between models from a growing library. Models run entirely on your machine, with no data sent to external services.

The platform integrates with thousands of applications and developer tools — including coding assistants, RAG pipelines, document processing workflows, and AI chat interfaces — through its API layer. Custom models can be created and shared using a Modelfile format similar to a Dockerfile, and multi-modal models that handle text and images are supported.

Ollama is aimed at developers, researchers, and organisations who want to run AI inference locally for privacy, cost control, or offline use, and who need a straightforward way to manage and serve multiple models without complex infrastructure setup.

Pi is an open-source AI agent toolkit built by Earendil Works. It includes an interactive coding agent CLI that helps you write, refactor, and debug code in real time—similar to Claude Code and OpenAI Codex. The project also provides a unified multi-provider LLM API supporting OpenAI, Anthropic, Google, and others, plus a terminal UI library with differential rendering for building rich CLI experiences.

The monorepo is organized into focused packages: the coding agent CLI, an agent runtime with tool calling and state management, the unified LLM API layer, and a TUI library. Pi is designed to be self-extensible and treats security seriously, with supply-chain hardening measures like pinned dependencies, shrinkwrap generation, and npm audit integration.

Onyx (formerly Danswer) is an open-source GenAI platform that brings AI-powered chat and enterprise search to your organization. It connects to your existing tools and documents to provide accurate, source-backed answers using Retrieval-Augmented Generation (RAG).

With support for every major LLM and 40+ app connectors, Onyx lets teams self-host a private alternative to proprietary AI assistants. It includes features like custom AI agents, deep research, code interpreter, image generation, and role-based access control.