# szczyglis-dev/py-gpt

Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, speech synthesis and recognition, web search, memory, presets, assistants,and more. Linux, Windows, Mac

Repository: https://github.com/szczyglis-dev/py-gpt
Canonical: https://ross.abutalabs.com/products/py-gpt
Homepage: https://pygpt.net
Language: Python
License: NOASSERTION
License Family: other
Topics: artificial-intelligence, chatbot, desktop-app, openai, ai, ai-assistant, llm, autonomous-agent, llama-index, gpt-4, claude, gemini, o1, ollama, deepseek, perplexity, grok, gpt-5, mcp, sora2
Last push: 2026-08-19T18:15:55+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 98, release rhythm 86, longevity 88
- inputs: {"age_days": 1242, "days_push": 14, "days_rel": 14, "gap_med": 0, "n_releases_24m": 246}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1892, forks 335 (observed 2026-08-28T04:05:49.640250+00:00)

## What it is
PyGPT is an open-source, all-in-one desktop AI assistant for Linux, Windows, and Mac, written in Python. It supports chat, agents, vision, voice, RAG-based chat with files, image/video generation, and multiple LLM providers including OpenAI, Gemini, Claude, Ollama, and DeepSeek.

## Use cases
- chat with gpt-4 and claude locally on my desktop
- talk to my pdf files with an ai assistant
- run a local ai assistant with ollama models
- generate images and videos with ai from a desktop app
- voice-controlled ai assistant with speech recognition and synthesis
- build autonomous ai agents that run system commands
- connect mcp tools to a desktop chat assistant
- ai assistant with web search and plugins

## When to choose
- you want a ChatGPT-like assistant running locally on your desktop
- you need multi-provider LLM support (OpenAI, Gemini, Claude, Ollama) in one app
- you want chat with your own files via RAG, voice, vision, and agents in a single tool
- you need a plugin/MCP-extensible assistant with presets and conversation memory

## When to avoid
- you need a headless API or server-side integration rather than a GUI app
- you only want a lightweight CLI or library for LLM calls
- you require a fully offline assistant without any API keys (local Ollama works, but many features need cloud providers)
- you need a mobile or web-based assistant

## Facets
- artifact type: application
- maturity: active
- function: chatbot, agent-framework, rag, speech-recognition, tts, llm-inference, image-processing, video-processing, mcp, plugin-system, chat-interface
- domain: artificial-intelligence, large-language-models, chatbots, desktop-applications, cross-platform
- platform: windows, python, cross-platform
- tags: desktop-ai-assistant, openai, gpt-4, gpt-5, gemini, claude, ollama, llama-index, voice-assistant, image-generation, video-generation, autonomous-agents, chat-with-files, ai-agents, retrieval-augmented-generation, linux, macos, desktop

## Member repositories
- szczyglis-dev/py-gpt (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:49.640250+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:12:58.543693+00:00, confidence not recorded.
  - readme: https://github.com/szczyglis-dev/py-gpt (fetched 2026-08-28T04:05:49.640250+00:00, sha 100e9d7bdd92)
  - homepage: https://pygpt.net (fetched 2026-08-29T10:52:08.291699+00:00, sha e37794effad8)
- Data as of 2026-08-30T08:39:29.467469+00:00.