Open WebUI provides a self hosted platform for connecting AI models and extending the interface with code.
Jan
Jan runs an offline AI chat assistant on a personal computer as an open-source ChatGPT alternative.

About Jan
Jan is an open-source desktop program that downloads and runs large language models on a personal computer for offline chat. It can download models such as Llama, Gemma, Qwen and GPT-oss from HuggingFace and allows creation of custom assistants.
It provides a local OpenAI-compatible server at localhost:1337 and MCP integration for agentic capabilities. It can also optionally connect to external providers such as OpenAI, Anthropic, Mistral, Groq and MiniMax, so local-only operation applies when using local models. Installers are listed for Windows, macOS and Linux, and larger models need more memory, listed as 16GB for 7B models and 32GB for 13B models on macOS.
Key features
- Download and run LLMs from HuggingFace locally
- Connect to external models via OpenAI, Anthropic, Mistral and others
- Create specialized custom assistants for tasks
- Provide local OpenAI-compatible API server at localhost:1337
- Support Model Context Protocol for agentic capabilities
- Offer installers for Windows, macOS and Linux
- Runs models on the user's own computer for local use
- Works with both downloaded HuggingFace models and external provider connections
- Lists installers for Windows, macOS and Linux
- Needs sufficient hardware, listed on macOS as 8GB RAM for 3B models, 16GB for 7B and 32GB for 13B
- Building from source requires Node.js, Yarn, Make and Rust
- Windows source builds need Git Bash plus tools such as Visual Studio Build Tools, LLVM, Ninja and CMake
Jan at a glance
- Website
- github.com/janhq/jan
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Jan alternatives
Tools and sites you could use instead, ranked by how closely they match.
Open WebUI provides an interface for using AI models, including Ollama and the OpenAI API.
Build personal AI agents with nanobot, a self-hosted Python framework that includes web UI, tools, memory, and integrations.
Petals runs large language models across distributed computers and supports fine-tuning and inference.
Enclave explores a virtual world for AI companionship and social interaction.
AnythingLLM is a local-first platform for using AI agents and language models in a self-managed workspace.
Popular in AI Chatbots & Assistants
Well-known listings from the same topic.
Jan FAQ
Where can Jan be downloaded?
Can Jan use models from outside providers?
What system is needed to run models?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












