MIT License · 100% local · 100% free

Your AI assistant.
Your machine.
Your rules.

TalhaGPT wraps Qwen3:8B in a full assistant layer: an agent loop with tool calling, persistent memory, ChromaDB-powered RAG, web access, vision and image generation — all running locally through Ollama.

🐍 Python 3.12+🪟 🍎 🐧 Cross-platform🧪 CI tested
talha@local: ~/TalhaGPT

// features

More than a chatbot

Qwen3:8B is the model. TalhaGPT is everything around it that makes it useful every day.

🤖

Local LLM

Runs entirely on your machine via Ollama + Qwen3:8B. No API keys, no subscriptions, no data leaving your computer.

🧠

Persistent Memory

Conversations and notes survive restarts. TalhaGPT remembers what matters across sessions.

🔎

RAG Pipeline

ChromaDB + Sentence Transformers index your documents and retrieve them by semantic similarity.

🛠️

Tool Calling

An agent loop lets the model pick tools, read results and keep reasoning toward a final answer.

🌐

Web Access

Searches the internet and fetches full web pages when local knowledge isn't enough.

📸

Vision

Captures your screen and understands what's on it — ask questions about anything visible.

🖼️

Image Generation

Generate images directly from the chat without leaving your terminal.

🔊

Voice Output

Optional text-to-speech so the assistant can answer out loud.

🧪

Tested & CI

Automated tests and GitHub Actions keep every commit honest.

// architecture

How the agent loop works

Instead of forwarding every prompt to the model, TalhaGPT lets the model decide when a tool is useful, read the result, and keep reasoning until it reaches a final answer.

👤 User
TalhaGPT Agent Loop
Direct Response
Tool Selection
🌐 Web
🔎 RAG
💻 System
📸 Vision
Tool Result
Agent Evaluates → Final Answer

🧠 Persistent memory

Long-term information lives in a local vector store and is retrieved through semantic similarity — not just whatever fits in the current context window.

🔎 RAG over your docs

Index any document with add_document_to_memory and query it later with natural language via search_memory.

// tools

10 built-in tools

Each tool is registered with the agent. The model picks the right one at the right time — you just ask.

toolwhat it does
get_weatherWeather information
get_system_statusCPU, RAM and system resources
save_notePersistent notes
launch_appLaunch allowed applications
add_document_to_memoryIndex documents into RAG
search_memorySemantic memory search
generate_imageImage generation
web_searchInternet search
fetch_web_pageRetrieve web page contents
capture_screenScreen capture

// stack

Python 3.12+OllamaQwen3:8BChromaDBSentence TransformersTransformers / PyTorchRequests / BeautifulSoupPillow / Pygame

// install

Running in under 5 minutes

Windows, macOS and Linux are all supported. Install Python 3.12+ and Ollama, then:

terminal — windows

# 0. Install Python 3.12+ and Ollama first

$ git clone https://github.com/dinguk0624/TalhaGPT.git # clone the repo

$ cd TalhaGPT

$ py -m pip install -r requirements.txt # dependencies

$ ollama pull qwen3:8b # download the model

$ py main.py # run it

Requirements: Python 3.12+, Ollama, ~8 GB free RAM for Qwen3:8B

// faq

Questions, answered

>Is it really free?

Yes. TalhaGPT is MIT-licensed open source. The model (Qwen3:8B) runs locally through Ollama, so there are no API costs at all.

>What hardware do I need?

Qwen3:8B needs roughly 6–8 GB of free RAM (more is better). A GPU helps speed things up, but it also runs on CPU.

>Is TalhaGPT a new model?

No — Qwen3:8B is the model. TalhaGPT is the assistant layer around it: the agent loop, memory, RAG and tools that turn a raw LLM into a useful daily assistant.

>Does my data leave my machine?

Your conversations and memory stay local. The only outbound requests happen when you explicitly use web search or page fetching tools.

// open source

Fork it. Break it. Make it yours.

TalhaGPT is MIT-licensed. Star the repo, open an issue, or send a pull request.

★ Star on GitHub