A plug-and-play collection of quickstart tutorials for popular LLM tools and agent frameworks.
No fluff. Just code. Get in, get it running, and start building cool stuff.
A quick overview of all available modules — click the folder to explore examples, or visit the upstream repo to learn more about the original project.
| Module | Quickstart Folder | Upstream Repo |
|---|---|---|
| OpenAI Agents SDK Spin up and wire agents using OpenAI's new experimental framework |
llm-quickstart-tutorial/openai_agents_sdk/ |
OpenAI SDK |
| Mem0 Memory-powered agents that learn over time |
llm-quickstart-tutorial/mem0/ |
Mem0 |
| Fast MCP Minimal controller for managing multi-agent workflows |
llm-quickstart-tutorial/fast_mcp/ |
Fast MCP |
| Neo4j Integrate agents with graph databases using Neo4j |
llm-quickstart-tutorial/neo4j/ |
Neo4j |
Uses
uv— blazing-fast Python package manager
(Don’t worry — one-liner install below)
# 1. Install uv (if needed)
curl -Ls https://astral.sh/uv/install.sh | sh
# 2. Clone the repo
git clone https://github.com/Vu0401/llm-quickstart-tutorial.git
cd llm-quickstart-tutorial
# 3. Create virtual environment, activate it, and install dependencies
uv venv
source .venv/bin/activate # or .venv\Scripts\activate on Windows
uv pip install -r pyproject.toml
# 4. Setup your environment variables
cp .env.example .env
# Then open `.env` and fill in the required values🧪 All dependencies are in pyproject.toml — no requirements.txt, no clutter.
# Example: Run a basic OpenAI agent
uv run python src/openai_agents_sdkl/1_basic_agent.pyEach folder has a few ready-to-run scripts. Check README.md inside the folder or just open the .py files — they come with inline guides.
Found this useful? Give it a ⭐ Have a cool integration or demo? PRs are very welcome.