Open Agent Spec (OAS) CLI
A command-line tool for generating agent projects based on Open Agent Spec YAML files.
Installation
pip install open-agent-spec
Usage
Basic Usage
# Show help
oas --help
# Initialize a new agent project
oas init --spec path/to/spec.yaml --output path/to/output
# Preview what would be created without writing files
oas init --spec path/to/spec.yaml --output path/to/output --dry-run
# Create a base working agent with minimal spec
oas init --template minimal --output path/to/output
Enable verbose logging
oas init --spec path/to/spec.yaml --output path/to/output --verbose
### Spec File Format
The spec file should be in YAML format with the following structure:
```yaml
open_agent_spec: 1.0.4
agent:
name: hello-world-agent
role: Responds with a greeting
intelligence:
type: llm
engine: openai
model: gpt-4
tasks:
greet:
description: Say hello
input:
properties:
name:
type: string
output:
properties:
response:
type: string
prompts:
system: >
You are a friendly agent that greets people by name.
Respond with: "Hello <name>!"
user: "{{name}}"
behavioural_contract:
version: "0.1.2"
description: "Simple contract requiring a greeting response"
role: "Friendly agent"
behavioural_flags:
conservatism: "moderate"
verbosity: "compact"
response_contract:
output_format:
required_fields: [response]
interface:
cli:
enabled: true
arguments:
- name: name
type: string
required: true
Generated Project Structure
output/
├── agent.py # Main agent implementation
├── prompts/ # Prompt templates
│ └── analyst_prompt.jinja2
├── requirements.txt # Project dependencies
└── .env.example # Environment variables template
Development
Setup
# Clone the repository
git clone https://github.com/aswhitehouse/open-agent-spec.git
cd oas-cli
# Install development dependencies
pip install -e ".[dev]"
Running Tests
pytest
Building
python -m build
Pacakge Installation
License
This project is licensed under the GNU Affero General Public License v3.0 (AGPLv3), which ensures that improvements and deployments of this codebase stay open and benefit the wider community.
If you're a business or enterprise and would like to:
Use this tool in a proprietary or internal-only setting
Avoid open-sourcing your modifications or integrations
Receive custom implementation support or consulting
Discuss a commercial license or enterprise partnership
➡️ Please feel free to reach out: 📧 andrewswhitehouse@gmail.com
Myself and my collaborators would be happy to support your journey with AI agents and ensure responsible, scalable use of this tooling in your stack.
Overview
Metadata
Release files for open-agent-spec 1.0.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| open_agent_spec-1.0.4.tar.gz | 33.3 kB | Without provenance | Details for open_agent_spec-1.0.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| open_agent_spec-1.0.4-py3-none-any.whl | Python 3 | none | any | Details for open_agent_spec-1.0.4-py3-none-any.whl |
Total release size: 62.2 kB
Release files / open_agent_spec-1.0.4.tar.gz
| Download URL | open_agent_spec-1.0.4.tar.gz |
|---|---|
| Size | 33.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2f19fdbd8e7c1703f0030513eed96bf6a5691d6930165339602e17853dd39d35
|
|
BLAKE2b-256 checksum How to use checksums |
682b5e6868770783555ad1e9583ff1e16a40bce7d539fd0ce3e48b3cf8a95989
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.0.1 CPython/3.12.5
|
Release files / open_agent_spec-1.0.4-py3-none-any.whl
| Download URL | open_agent_spec-1.0.4-py3-none-any.whl |
|---|---|
| Size | 28.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
9de7166ad18d5f3d570991c53faee54f1f86e7c8280ed987ee492fb15bb6667c
|
|
BLAKE2b-256 checksum How to use checksums |
1934671465f85f38bc7b8a3b7e382cbd31f9e77c659bfc6ec1b32e6b76e3c269
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.0.1 CPython/3.12.5
|
Security for open-agent-spec 1.0.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.