PyGPT
Overview
PyGPT is an open source desktop AI Assistant powered by multiple versions of GPT, including GPT-4, GPT-4 Vision, GPT-3.5, and DALL-E 3. Compatible with Linux, Windows, and Mac, it offers features such as speech synthesis and recognition aided by Microsoft Azure and OpenAI TTS, and voice recognition through OpenAI Whisper.
It supports carrying out internet searches via Google and executing Python code. The tool can also follow customized user commands and offers plugin extensions.
PyGPT is designed to provide a user-friendly and fully configurable setting, thus requiring no previous knowledge of AI models from its users. It operates efficiently on a desktop and necessitates an OpenAI API key for operation.
Functions of PyGPT include real-time internet access, speech synthesis and recognition, image analysis, short and long-term memory, command execution, file upload and download, and more.
It also supports multiple modes such as chat, completion, real-time vision analysis, image generation, and integration with LLMs provided by Langchain.
Releases
Top alternatives
-
243,8571,0275 released 2mo ago#7 in Trending
Dmitry G.🙏 134 karmaAug 29, 2023State of the Art -
Open174,293189v1.1.7 released 25d agoFree + from $5.99/moAthena has been a useful product for travel and product recommendations. Additionally, it has helped me with my daily tasks. -
74,06973v5.1.1 released 1d agoFrom $89## Image generation Nodes Introduces Image generation nodes. You can now generate images with nodes. You can also connect other images to an image generation node to provide references to the image generation model. Supports Nano banana, Gpt Image 1, and Ideogram, etc ## RAG (Retrieval Augmented Generation) Introduced RAG mode which let’s you deal with large files, and cases when there’s a lot of nodes connected to a chat node reaching the context limits of the selected model ## Search for Nodes on Canvas with AI + Keywords As canvases got bigger with many nodes, it was difficult to find your place or look up a node. Search modal can now help you search for nodes using a local keyword search, or also using Intelligent AI search ## Token summary You can now view the token count estimation of each node, the tokens incoming into a given node as context, and also the token estimation that you’d send to the AI ## Voice Input Use voice transcription to talk to the Nodes, and get your prompts transcribed ## Persona Prompts Library Save and reuse persona prompts (system prompts or like custom GPT) and assign them to your chat nodes so that the models can follow the instructions of the prompt ## Refactored Context Engine A completely refactored context engine. This is a step forward in making the app ready for upcoming updates, like MCP clients and tool use.
-
46,960622Released 2y ago100% FreeHeya, the app seems to be up and running. Give it another shot. Have fun!
-
33,061110Released 2y agoFree + from $9/mo
-
31,946119Released 2y agoFree + from $8.25/moit’s a cool tool if you wanna chat with made up characters or build your own. works fine and feels fun. the ui could def be better organized. alsooo letting people upload any pic for their characters makes things kinda messy, some look 🔥, some are like 144p pics. would be sick if they added a 'generate image' button that uses your character's description or lets you write one for it.
