create-agent 🤖
One-command bootstrap for OpenAI Agents SDK projects.
Usage
# npx (no install needed)
npx create-agent my-project
# With agent type
npx create-agent my-project --type single # default — single agent + tools
npx create-agent my-project --type multi # multi-agent with handoffs
npx create-agent my-project --type voice # voice pipeline (STT → agent → TTS)
# uvx (if you prefer Python toolchain)
uvx create-agent my-project
What you get
my-project/
├── main.py # Entry point — just run this
├── agents/ # Agent definitions
├── tools/ # @function_tool functions
├── tests/ # Pytest tests (ready to run)
├── pyproject.toml # uv-managed deps
├── Makefile # make run / make test / make lint
├── .env.example # Copy → .env, add OPENAI_API_KEY
├── .gitignore
└── .github/copilot-instructions.md # Copilot context — team onboarding
After bootstrap
cd my-project
cp .env.example .env # add your OPENAI_API_KEY
uv sync # install deps
uv run main.py # run your agent
Agent types
| Type | Description |
|---|---|
single |
Single agent with function tools. Best starting point. |
multi |
Orchestrator + specialist agents connected via handoffs. |
voice |
Voice pipeline skeleton (STT → agent → TTS). |
Copilot integration
Every project includes .github/copilot-instructions.md. When your teammate opens the project in VS Code with GitHub Copilot, it automatically loads the agent context — they can ask Copilot things like:
- "Add a tool that fetches weather data"
- "Add a guardrail that blocks off-topic questions"
- "Write a test for the orchestrator"
- "Add memory to persist conversation history"
Stack
- openai-agents — OpenAI Agents SDK
- uv — Python package manager
- pytest — testing
- ruff — linting + formatting
Author
Eddie Chan — github.com/unrealandychan
Metadata
Release files for create-openai-agent 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| create_openai_agent-1.0.0.tar.gz | 14.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| create_openai_agent-1.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 47.0 kB
Release files / create_openai_agent-1.0.0.tar.gz
| Download URL | create_openai_agent-1.0.0.tar.gz |
|---|---|
| Size | 14.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4afd907f1b73c9d216022b61215f7c75a694d309f4b25ddc9e1a050885f6d5e2
|
|
BLAKE2b-256 checksum How to use checksums |
9573818210aeb86a571584eb231e1d12ebd0eca104704afc775994e9c93d6a7f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / create_openai_agent-1.0.0-py3-none-any.whl
| Download URL | create_openai_agent-1.0.0-py3-none-any.whl |
|---|---|
| Size | 32.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a6fecd547d47c94b650a3f7736a2ec1bd85db3b3c78199a9319024da51229acc
|
|
BLAKE2b-256 checksum How to use checksums |
f10b165a227bbb77ef2c3568c5b551352cc297542e4f3d422da2a27334f04162
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|