Skip to main content

Agent Studio


## Installation

1. Install the package from PyPI:
```bash
pip install agent-studio

CLI Usage

The package provides two main CLI commands:

  1. Start the AgentStudio application:
agentstudio start

This command starts both the Streamlit interface and FastAPI backend servers.

  1. Check the version:
agentstudio version

Important Note: If you're a first-time user, we strongly recommend checking the tutorial webpage in the application after installation. The tutorial will guide you through building agents and workflows effectively.

API Endpoints

Process Workflow

  • URL: /api/process
  • Method: POST
  • Body:
{
    "content": "Your input data here"
}

Health Check

  • URL: /health
  • Method: GET

Example Usage

# Check health
curl http://localhost:8000/health

# Process workflow
curl -X POST http://localhost:8000/api/process \
     -H "Content-Type: application/json" \
     -d '{"content": "Example input data"}'

Extending the Workflow

To add new workflow steps, create a new WorkflowStep instance:

new_step = WorkflowStep(
    name="step_name",
    description="Step description",
    requires=["dependent_step_name"]
)
workflow_manager.add_step(new_step)

Error Handling

The API includes comprehensive error handling and logging:

  • All errors are logged with timestamps and context
  • HTTP exceptions include detailed error messages
  • Step execution failures are properly propagated

License

MIT License

Author

Made with love by Harish Sanathanalakshmi Ganesan

Metadata

Release files for agent-studio 0.1.7

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for agent-studio 0.1.7
File Interpreter ABI Platform Actions
agent_studio-0.1.7-py3-none-any.whl Python 3 none any Details for agent_studio-0.1.7-py3-none-any.whl

Release files / agent_studio-0.1.7-py3-none-any.whl

Download URL agent_studio-0.1.7-py3-none-any.whl
Size 74.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
fef9a0a2b33389ec8a06e34ef8c65695c3a08ee3e85bb93d34315a3b40526237
BLAKE2b-256 checksum
How to use checksums
fca7e7ec8e86f7410232fbe54ecff8d749ffd08b3701c5d192128346451b1e78
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.10

Security for agent-studio 0.1.7

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page