Jan vs PyGPT

Jan

• Running open models offline on your own computer
• People who want one desktop app for local and cloud models
• Developers who want a local OpenAI-compatible endpoint

PyGPT

• Technical users who want one desktop app for many model providers
• Running agents that can execute Python and work with local files
• Pairing a chat interface with local Ollama models at no cost

Jan

• Desktop only, on macOS, Windows and Linux. Intel-based Macs are not supported.
• Local models need memory: Jan's Mac guide suggests 8GB of RAM for 3B models, 16GB for 7B models and 32GB for 13B models.
• Cloud models need your own API key from each provider, and those providers see the messages you send them.
• Cowork and the standalone Jan Agent are previews on nightly builds, and the memory feature is marked as coming soon.

PyGPT

• Cloud models need your own API keys, and each provider charges for usage separately.
• macOS has no prebuilt app: it is installed from PyPI with Python 3.10 to 3.13, or run from source.
• Local models are not built in; they run through a separate Ollama installation and need compatible hardware.
• It is a desktop application only, for Windows 10 and 11, 64-bit Linux and macOS.

Jan

Local models

Downloads and runs open models such as Llama, Gemma and Qwen from Hugging Face using llama.cpp or MLX. The Hub shows whether each model fits your hardware.

Cloud providers with your own key

Connects to OpenAI, Anthropic, Gemini, Mistral AI, Groq, OpenRouter and Azure OpenAI, or to any OpenAI- or Anthropic-compatible endpoint, using an API key you supply.

Built-in web search

Web search and page fetch tools are on by default for models that support tool use. They run through a keyless Exa endpoint, so no API key or MCP server is needed.

Projects and assistants

Projects group conversations under shared instructions and files, and custom assistants keep their own instructions for recurring kinds of work.

Local API server

A built-in OpenAI-compatible server at localhost:1337 lets other applications use the models running in Jan, and Claude Code can be set to use them as its backend.

MCP connectors and Cowork preview

MCP servers add tools such as code execution and databases. Cowork, which works through multi-step tasks on files and commands, ships only in nightly builds as a preview.

PyGPT

Cloud and local models

Works with OpenAI, Claude, Gemini, Grok, DeepSeek, Perplexity Sonar and Hugging Face models through your own API keys, and with local models such as Llama, Qwen or Mistral served by Ollama.

Multi-agent workflows

Agents run as a primary agent, an orchestrator or a swarm of workers. Portable SKILL.md skills can be imported from GitHub or disk, and AGENTS.md files add project-specific instructions.

RAG and conversation memory

LlamaIndex indexes files, web pages, images, audio, video and past conversations into built-in vector stores, with a separate index per project and short- and long-term memory.

Python, system tools and MCP

Models can run Python, IPython and system commands in a built-in sandbox or Docker, call MCP servers through a Connectors manager, search the web and run scheduled tasks.

Voice, vision and generation

Realtime voice, speech recognition and speech synthesis through several providers, analysis of images and camera input, and image and video generation with models such as Imagen, Veo and Sora.

Profiles and built-in tools

Profiles keep separate settings, history and files. The workspace includes a notepad, a painter, a calendar with day notes, a web browser, presets, plugins and themes.

Jan

• Free$0

  The full desktop app for macOS, Windows and Linux, with local models, cloud provider connections and the local API server.

PyGPT

• Free$0

  The full desktop app for Windows, Linux and macOS, including agents, RAG, plugins, MCP connectors and every work mode.