OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Demogpt

Demogpt is an open-source Python framework for generating and configuring LLM-agent applications. It brings together tools, prompts, frameworks, models, RAG, knowledge graphs and vector databases.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Demogpt — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Demogpt when a code-based, self-hosted framework is more relevant than a single-purpose AI application and your project needs configurable agents, tools or retrieval components.

Who it is for

  • Python developers building LLM-agent prototypes
  • Developers creating tool-using agent applications
  • Teams exploring RAG, knowledge-graph or vector-database workflows

Documented uses

  • Generate agentic application prototypes from prompts
  • Create and customize agents with tools and language models
  • Build retrieval-oriented applications with RAG, knowledge graphs or vector databases
  • Use a reusable Python interface for agent development
Before you choose

Requirements & limits

The repository is public, open source and licensed under MIT. Installation documentation uses pip for the main package.

  • Python is the primary language.
  • LangChain is listed as an ecosystem.
  • The project documents Linux, Windows, macOS, CLI and self-hosted contexts.
  • AgentHub includes documented tool-calling, RAG and combined RAG-with-agents paths.
  • The repository is not marked as archived.

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

Install DemoGPT AgentHub and define a custom tool

Set up the AgentHub package and create the documented skeleton of a custom tool.

Before you start

  • Python package installation with pip
  • A Python development environment

Steps

  1. Install the main package with the command below.

    Documented command
    pip install demogpt

  2. Import BaseTool from demogpt_agenthub.tools.

  3. Create a class that sets a tool name and description and implements run(query).

  4. Instantiate the custom tool for use with an agent.

Expected outcome

A custom tool object is prepared for inclusion in a DemoGPT AgentHub agent.

Guide limitations

  • The documented example leaves the tool's functionality to be implemented.
  • This recipe covers tool setup, not a complete production workflow.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
melih-unsal/DemoGPT · Official homepage title · retained in its source language
How we review sourcesSuggest a correction