🧠 openstackai
Three-Dimensional Intelligence Engine
The Intelligence Engine for Software Factories
Build, Orchestrate, and Scale AI-Native Applications
🚀 Quick Start
pip install openstackai
One-Line AI Operations
from openstackai import ask, summarize, research
# Ask anything
answer = ask("What is machine learning?")
# Summarize documents
summary = summarize("Long document text...")
# Research topics
report = research("Latest AI trends 2026")
Build AI Agents
from openstackai import Agent, Runner
agent = Agent(
name="Assistant",
instructions="You are a helpful AI assistant."
)
result = Runner.run_sync(agent, "Hello!")
print(result.final_output)
Multi-Agent Workflows
from openstackai import Agent, Runner
from openstackai.blueprint import ChainWorkflow
researcher = Agent(name="Researcher", instructions="Research topics")
writer = Agent(name="Writer", instructions="Write articles")
workflow = ChainWorkflow([researcher, writer])
result = Runner.run_sync(workflow, "AI in healthcare")
✨ Key Features
| Feature | Description |
|---|---|
| 🎯 Simple APIs | One-liner functions: ask(), summarize(), research(), extract(), generate() |
| 🤖 Agent Framework | Full agent system with Agent, Runner, memory, and context passing |
| 🔗 Multi-Agent | Orchestration patterns: Chain, Supervisor, Swarm, Tree of Thoughts |
| 🔌 Multi-Provider | OpenAI, Azure OpenAI, Anthropic, Ollama, Gemini, Groq |
| 📊 Vector DBs | ChromaDB, Pinecone, Qdrant, Weaviate integration |
| 🏢 Enterprise | Azure AD auth, sessions, guardrails, evaluation, tracing |
| 🧩 Extensible | Custom skills, OpenAPI tools, A2A protocol, plugins |
| 🎙️ Multimodal | Vision, audio, document understanding |
🔌 Supported Providers
| Provider | Status | Authentication |
|---|---|---|
| OpenAI | ✅ Full Support | API Key |
| Azure OpenAI | ✅ Full Support | API Key / Azure AD |
| Anthropic Claude | ✅ Full Support | API Key |
| Ollama | ✅ Full Support | Local / Remote |
| Google Gemini | ✅ Full Support | API Key |
| Groq | ✅ Full Support | API Key |
📦 Module Overview
| Module | Purpose |
|---|---|
openstackai.easy |
One-liner AI functions |
openstackai.core |
Agent, LLM providers, memory |
openstackai.runner |
Agent execution engine |
openstackai.blueprint |
Workflows & orchestration patterns |
openstackai.skills |
Tools and skills system |
openstackai.sessions |
SQLite/Redis session storage |
openstackai.vectordb |
Vector database connectors |
openstackai.evaluation |
Agent evaluation framework |
openstackai.openapi |
OpenAPI tool generation |
openstackai.multimodal |
Vision, audio support |
openstackai.a2a |
Agent-to-Agent protocol |
🔧 Configuration
Environment Variables
# OpenAI
export OPENAI_API_KEY="sk-..."
# Azure OpenAI
export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/"
export AZURE_OPENAI_DEPLOYMENT="gpt-4o-mini"
export AZURE_OPENAI_API_KEY="..." # Or use Azure AD
# Anthropic
export ANTHROPIC_API_KEY="sk-ant-..."
YAML Agent Configuration
# research_agent.yaml
name: "Research Agent"
instructions: "You are an expert researcher."
provider: "openai"
model: "gpt-4o-mini"
skills:
- web_search
- summarize
from openstackai.config import AgentConfig
agent = AgentConfig.from_yaml("research_agent.yaml").create_agent()
📚 Documentation
- 📖 Full Documentation: gitpavleenbali.github.io/PYAI
- 📘 GitHub Repository: github.com/gitpavleenbali/PYAI
- 📋 Changelog: Changelog
- 🏗️ Architecture: Architecture Guide
🤝 Contributing
Contributions are welcome! See our Contributing Guide.
📄 License
MIT License - see LICENSE for details.
Built with ❤️ for the AI community
openstackai - The Intelligence Engine for Software Factories
Metadata
Release files for openstackai 0.6.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| openstackai-0.6.1.tar.gz | 400.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| openstackai-0.6.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 724.8 kB
Release files / openstackai-0.6.1.tar.gz
| Download URL | openstackai-0.6.1.tar.gz |
|---|---|
| Size | 400.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b94a04f461affef472e55d9bd6842b019dcb37abbb5bf6778be18a1b11dbb803
|
|
BLAKE2b-256 checksum How to use checksums |
dbb06ebf6f540111e04d23a9f7ab92c52551fd68bd675ff4e53069cc55a79682
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 18, 2026.
Transparency logRelease files / openstackai-0.6.1-py3-none-any.whl
| Download URL | openstackai-0.6.1-py3-none-any.whl |
|---|---|
| Size | 324.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
48b0cbd59a0494fd6516a1315a1a09e4e6561b6c12fd9e069b2d17df84fd28ef
|
|
BLAKE2b-256 checksum How to use checksums |
d83c8b4bd7d25d4519639936a8a586e0c6a6b72e0a639b1b0299492a29ac5655
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 18, 2026.
Transparency log