#
ENJA

py-gpt

MCP Server

szczyglis-dev/py-gpt

PyGPT is a comprehensive desktop AI assistant that provides multi-model LLM support, filesystem access, code interpretation, and advanced multimodal features.

1.9k 334No licenseUpdated 2026-08-12

Overview

PyGPT is a full-featured, open-source desktop AI application designed for Windows, Linux, and macOS. It functions as an all-in-one command center supporting OpenAI models, local Ollama models, LlamaIndex data connectors, and various alternative cloud providers. The platform includes capabilities like text generation, vision analysis, speech-to-text, text-to-speech, web searches, file management, and an integrated Python code interpreter, making it adaptable for both everyday tasks and advanced agentic workflows.

Capabilities

  • Multi-model LLM chat interface
  • Local file and directory I/O
  • Real-time Python code execution
  • Web search integration
  • Voice recognition and text-to-speech synthesis
  • Vision analysis using camera or uploaded images
  • LlamaIndex document embedding and RAG
  • Plugin and MCP extension support

Best for

Chatting with local and cloud-based large language models from a unified desktop interface., Analyzing local documents, PDFs, and codebases via integrated LlamaIndex vector search., Executing local Python code and system commands through built-in interpreters and plugins., Automating tasks with multi-modal agent workflows, web searches, and scheduled cron jobs.

Works with

CursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
66
Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 AIによるcapabilities/use-cases解析

Code quality15%85 → +12.8

実装・指示の品質。 AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 GitHub 最終push日時の新しさ

Documentation12%55 → +6.6

ドキュメントの充実度・分かりやすさ。 README/独自要約の情報量

Security15%50 → +7.5

危険・不審な挙動が無いか。 AIによるセキュリティレビュー

Originality10%70 → +7.0

ありふれたラッパーではない独自性。 AIによる独自性判定

Popularity8%85 → +6.8

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%50 → +2.5

対応AIエージェントの広さ。 AIによる対応エージェント判定

Weighted total78.1 / 100

ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

The assistant features capabilities to execute local system commands and run Python code, which presents inherent risks if untrusted prompts or malicious models trigger unintended operations.

Categories

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.