OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Agentic Desktop Pet

Agentic Desktop Pet is an open-source desktop companion with a Godot 4.x interface and Python FastAPI backend. It connects to LLM APIs and uses Cognee for knowledge-graph memory, persistent conversational history and semantic retrieval. Its assistant includes tools for local files, code and scripts, and to-do management, while companion features add configurable themes, emotional behavior and RPG-style progression.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agentic Desktop Pet — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a desktop pet interface for an LLM assistant whose documented tasks include memory-backed conversation, local-file operations, code or script execution, and to-do management.

Who it is for

  • People who want a desktop companion that can retain conversational context across sessions.
  • Users seeking a conversational helper for local file changes, code or script execution, and to-do management.
  • Developers interested in a Python and Godot project they can customize with different pet themes.

Documented uses

  • Recall relevant conversational context using persistent memory and semantic search.
  • Ask an assistant to read, create or edit local files.
  • Run code or scripts and manage to-do items through conversation.
  • Customize a desktop companion with themes and interactive emotional or RPG-state features.
Before you choose

Requirements & limits

The README's setup requires Python 3.13 or later, Godot 4.3 or later, and an LLM API key. The repository is public and identifies the project as open source; its README cautions that the complete project cannot be packaged for commercial use and that asset copyrights should be considered.

  • The stack separates a Python FastAPI backend from a Godot 4.x desktop front end.
  • Cognee is used for graph-based memory, cross-session persistence and semantic retrieval.
  • The documented assistant tools extend beyond chat to local files, code or scripts, and task management.
  • The project explicitly describes itself as still in development and warns that bugs remain.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the backend and Godot desktop pet

Prepare the documented backend and frontend components for local use.

Before you start

  • Python 3.13 or later
  • Godot 4.3 or later
  • An LLM API, such as OpenAI, DeepSeek or Claude
  • The project repository and uv

Steps

  1. From the repository, enter the backend directory and run the command below.

    Documented command
    uv sync

  2. Copy .env.example to .env and edit the file to add an API key.

  3. Start the backend with the command below.

    Documented command
    uv run main.py

  4. Open Godot 4.3 or later, import the godot/ folder and run the project.

Expected outcome

The README's setup sequence starts the FastAPI backend and runs the Godot front end.

Guide limitations

  • The project warns that development is ongoing and that bugs remain.
  • For packaged builds, the README says theme .pck files belong in themes/*.pck beside the executable.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
jihe520/Agentic-Desktop-Pet · Official homepage title · retained in its source language
How we review sourcesSuggest a correction