FollowAgents AI AGENTS DIRECTORY
Home / All Agents / DemoGPT AgentHub
Dev & Engineering streamlit-app-generationlangchainragvector-databasespython-sdktool-callingcomputer-vision

DemoGPT AgentHub

Generate Streamlit apps from prompts and compose Python agents with tools and RAG.

View on GitHub ↗ Quick start ↓
Source repo
melih-unsal/DemoGPT
Stars
★ 1.9k
Last updated
7mo ago
License
MIT
Primary language
Python
FA score
40/100 · Major gaps

At a glance

How it runs
CLILibrary / SDKWeb app
Works with
Portable with changesOpenAI API
Cost
Free software; you pay for model usage
Setup effort
Low · running in minutes
You'll need
PythonpipStreamlitShell / CLINetwork accessLocal filesystem
Typical use
A Python developer prototyping an interactive product idea can submit an instruction and title to DemoGPT and receive staged output culminating in Streamlit code.
Not a fit if
  • Teams avoiding OpenAI APIs; only OpenAIChatModel configuration is documented
  • Users needing production-stable RAG; examples reset and write a local vectorstore path
Source review
40/100 · Major gaps 2 safety controls not found

What does this agent do, and when should you use it?

DemoGPT is a Python project with a DemoGPT pipeline for generating LangChain and Streamlit applications from natural-language instructions, plus DemoGPT AgentHub for tool-using agents. Its generation pipeline plans work, creates tasks, produces code snippets, and assembles final code, returning stage JSON and final Streamlit code. AgentHub exposes ToolCallingAgent, ReactAgent, BaseRAG, OpenAIChatModel, BaseTool, and a set of built-in tools. It can be installed with pip and launched with demogpt, imported as a Python library, or run from source with Streamlit. BaseRAG can add PDF, TXT, CSV, and JSON files to Chroma, Pinecone, or FAISS vector stores.

The Python interface creates DemoGPT(model_name="gpt-3.5-turbo"), accepts an instruction and title, and yields JSON for each generation stage; the completed stage includes final code. The documented pipeline generates a plan, derives tasks from the plan and instruction, turns tasks into code snippets, and assembles a Streamlit application. In AgentHub, developers subclass BaseTool and implement run, then provide those tools and an OpenAIChatModel to ToolCallingAgent or ReactAgent; documented built-ins include TavilySearchTool, WeatherTool, PythonTool, BashTool, WikipediaTool, ArxivTool, and YoloTool. BaseRAG reads PDF, TXT, CSV, and JSON through add_files, stores and retrieves content with chroma, pinecone, or faiss, and can itself be supplied as a ReactAgent tool.

  1. A Python developer prototyping an interactive product idea can submit an instruction and title to DemoGPT and receive staged output culminating in Streamlit code.
  2. A developer building question answering over internal documents can index PDF, TXT, CSV, or JSON files with BaseRAG and query the resulting store.
  3. A developer combining web search, weather lookup, and calculation in one workflow can pass TavilySearchTool, WeatherTool, and PythonTool to ToolCallingAgent or ReactAgent.
  4. A Python team with a domain-specific function can subclass BaseTool, implement name, description, and run, then register the tool with an agent.
  5. A developer who needs object detection for an image URL can use YoloTool with ReactAgent to obtain detected objects and coordinates.

How do you install or deploy this agent?

Install the package:

pip install demogpt

Install from source:

git clone https://github.com/melih-unsal/DemoGPT.git
cd DemoGPT

pip install .

The documented Python examples use OpenAIChatModel. If OPENAI_API_KEY is not set in the environment, provide the key through the DemoGPT openai_api_key argument.

How do you use this agent?

After package installation, run:

demogpt

Use the library:

from demogpt import DemoGPT
agent = DemoGPT(model_name="gpt-3.5-turbo")

for phase in agent(instruction="Your instruction here", title="Your title here"):

print(phase)

Run the source UI:

streamlit run demogpt/app.py

For a tool-calling agent, construct ToolCallingAgent or ReactAgent with tool instances and OpenAIChatModel(model_name="gpt-4o-mini"), then call agent.run(query).

What are this agent's strengths and limitations?

Pros
  • It combines a prompt-to-Streamlit code-generation pipeline with a programmable AgentHub instead of offering only a chat interface.
  • BaseRAG explicitly supports PDF, TXT, CSV, and JSON inputs plus Chroma, Pinecone, and FAISS vector-store choices.
  • The BaseTool inheritance point lets developers add custom tools directly to ToolCallingAgent and ReactAgent.
  • The documented tool set spans search, weather, Python, Bash, academic search, URL requests, and YOLO image detection.
Limitations
  • The documented model interface centers on OpenAIChatModel and examples use gpt-3.5-turbo or gpt-4o-mini; no configuration path for another provider is shown.
  • The OpenAI examples require OPENAI_API_KEY or openai_api_key, while external search, weather, and URL tools also depend on network access.
  • The RAG example writes a vector store at persistent_path, and reset_vectorstore=True removes an existing store, so storage paths need review before use.
  • The to-do list still includes remaining LangChain tasks, self-refinement, Gorilla, Rapid API, Llama2, and a public retrieval database.

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
DemoGPT AgentHub This agent 40 · Major gaps CLIFree + model costs ★ 1.9k 7mo ago Python OpenAI API
LangChain & LangGraph Agent Course 43 · Major gaps CLIFree + model costs ★ 1.8k 8d ago — —
ai4j — Java AI Agentic SDK 60 · Some gaps Library / SDKFree + model costs ★ 439 26d ago Java OpenAI API · Claude API
Agent Craft 52 · Major gaps CLIFree + model costs ★ 536 12d ago Python OpenAI API

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
40/ 100 5-point scale 2.0 / 5
Trust 7/29
Reliability 5/14
Adaptability 8/18
Convention 10/18
Effectiveness 7/13
Verifiability 3/8
Why each dimension lost points
Trust7 / 29 · 1.2/5

The app asks users for an OpenAI API key and uses it for model calls; the input is masked, but the supplied material does not explain key storage, transmission, or protection. The README lists Bash, Python, URL-request, search, and RAG tools, without showing permission limits, per-action confirmation, data-flow details, or rollback safeguards, so credit is limited. The license and pyproject.toml provide authorship clues, but publisher identity is unverified and attribution and maintenance paths remain incomplete. Several dependencies use wildcard versions, and the material gives no security policy or mitigation.

Reliability5 / 14 · 1.8/5

The material includes model and RAG test examples and dependency declarations, but the tests depend on external models/APIs and static evidence cannot establish that they run or are reproducible. README examples, product descriptions, and code interfaces show signs of version or behavior inconsistency. The app displays initialization errors as warnings, but documents little about other errors or failure handling.

Adaptability8 / 18 · 2.2/5

The README targets developers building LLM applications and covers custom tools, models, agents, RAG, and vision tasks, giving useful audience and scenario coverage. The material does not clearly define autonomy permissions or usage boundaries. Model selection and an API-base input show some adaptability, while environment and deployment requirements and trigger conditions are only lightly described.

Convention10 / 18 · 2.8/5

The README has a table of contents, installation steps, and many examples; pyproject.toml specifies package name, version, and MIT license, and the license text is complete. The supplied material lacks a clear change history, limitations, and a definite maintenance owner or update path, so those areas receive partial credit.

Effectiveness7 / 13 · 2.7/5

Examples show tool use, RAG, code generation, and structured output, supporting the product's value for quickly building agent applications. The README gives concrete sample outputs, but provides little evidence about costs, resource use, or review needed before running generated code, limiting the cost-benefit score.

Verifiability3 / 8 · 1.9/5

Some claims are supported by README examples, package metadata, application code, and test files, but sample outputs and promotional claims are not sufficiently corroborated across those sources. Test files are static evidence and do not establish runtime results; factual descriptions, examples, and forward-looking claims are not consistently distinguished.

Risks and how to mitigate them
  • Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
  • Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
  • Review permissions and side effects before running generated apps or enabling Bash, Python, and network-request tools; the material does not describe per-action confirmation or rollback.
  • The app collects keys in a password field, but the material does not explain storage or transmission. Several dependencies use wildcard versions; assess and pin dependencies before adoption.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision aca748b71345
Review evidence README.mddemogpt/app.pyLICENSEpyproject.tomltests/test_llms.pytests/test_rag.py
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/demogpt.svg)](https://followagents.com/en/agents/demogpt)
<a href="https://followagents.com/en/agents/demogpt"><img src="https://followagents.com/badge/demogpt.svg" alt="FARS review"></a>

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

  1. v1.2.6
    Release notes excerpt
    DemoGPT v1.2.6 🚀 Release Notes --- Overview We're back with DemoGPT version 1.2.6, further enhancing our module capabilities and providing significant bug fixes. This release brings a Python module to spawn more generic app ideas, addresses issues in the Document loader and Finalizer modules, and paves the way for Azure-based URLs with OpenAI. Plus, there's an exciting addition for chat model feedback! Python Module for Generic Apps …
    View on GitHub ↗
  2. v1.2.5
    Release notes excerpt
    DemoGPT v1.2.5 🚀 Release Notes Overview Exciting times ahead! We're delighted to roll out DemoGPT version 1.2.5. This release introduces the ability to generate chat-based applications, streamlines OpenAI API Key integration, and includes several document-related bug fixes. Generate Chat-Based Applications With DemoGPT v1.2.5, you can now generate chat-based applications right from your prompts! Your generated chat applications will include a rich set of features that allow for dynamic, real-time conversations. OpenAI API Key Integration …
    View on GitHub ↗
  3. v1.2.4
    Release notes excerpt
    DemoGPT v1.2.4 🚨 Release Notes Overview We're thrilled to announce the release of DemoGPT v1.2.4! This new version brings a customization property. Editing The Generated Code Now, after you generate the code from your prompt, there is an Edit button under the code. Once you press it, you will be able to change the code and play however you like. Once you are done, press Save & Rerun button, it will rerender the code and open up the new app. Bug Fixes & Improvements …
    View on GitHub ↗

FAQ

Does it require OpenAI credentials?
The documented DemoGPT and AgentHub examples use OpenAI models. If OPENAI_API_KEY is not set, the README says to supply a key through openai_api_key.
Which files and vector stores does RAG support?
The BaseRAG example supports PDF, TXT, CSV, and JSON files, with chroma, pinecone, or faiss as the vectorstore.
Does RAG modify local storage?
Yes. The example writes the vector store to persistent_path; with reset_vectorstore=True, its shown output removes the existing rag_chroma vector store.
Can I add a custom business tool?
Yes. Subclass BaseTool, set name and description, implement run, and pass the resulting instance to ToolCallingAgent or ReactAgent.
Was this page helpful?
View on GitHub ↗ Install ↓

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Open Source Coding Agents, Compared

Open source coding agents ranked by FARS review — score, trust, license, language and maintenance side by side, with what each one is and isn't good at.