Skip to main content

Contract-first Agentic AI framework

Project description

OrchestraPy

OrchestraPy is an enterprise-grade framework for building type-safe, contract-first Agentic AI microservices.

The Problem

Most agent frameworks treat LLM output as a "suggestion." In mission-critical enterprise environments—like supply chain demand forecasting or automated complaint analysis—this unpredictability is a liability. Existing frameworks often sacrifice structural integrity for conversational flexibility.

The Solution: OrchestraPy

OrchestraPy acts as a strict Data-Contract Firewall between your business logic and the LLM.

  • Contract-First: Every agent interaction is governed by strict Pydantic schemas.
  • Stateless Microservices: Optimized for scalable, audit-ready, stateless API deployments.
  • Deterministic Tool-Calling: Forces agents to use deterministic Python tools rather than hallucinating mathematical outputs.

Quick Start

  1. Install: pip install orchestrapy
  2. Define: Create your input/output schemas using Pydantic.
  3. Orchestrate:
from orchestrapy.base import BaseAgentService

class MyAgent(BaseAgentService[InputSchema, OutputSchema]):
    # Your agent logic here

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

orchestrapy-0.1.0.tar.gz (3.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

orchestrapy-0.1.0-py3-none-any.whl (3.9 kB view details)

Uploaded Python 3

File details

Details for the file orchestrapy-0.1.0.tar.gz.

File metadata

  • Download URL: orchestrapy-0.1.0.tar.gz
  • Upload date:
  • Size: 3.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for orchestrapy-0.1.0.tar.gz
Algorithm Hash digest
SHA256 f23af1bd5d34c9d7c7ea0ec941b023e8cacfa186755df8a14b6cb8c9355cf044
MD5 27394d1968fea784dd6c3d801db0eb15
BLAKE2b-256 4cb868a291abba23379a6067c4270cb71bb1f569d213a59f554a8ca54952b28c

See more details on using hashes here.

File details

Details for the file orchestrapy-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: orchestrapy-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 3.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for orchestrapy-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0f4300939474621e13230b04f5d0d35678a61a6c749524972c39fc010da11310
MD5 8ca4daa6f046a8defe9f2e74e231164e
BLAKE2b-256 ad0bdb231eace83d76a734dc6db742bf2e13f9bcb718a78485a42b67a50ba6b8

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page