semantic-kernel  by microsoft

SDK for building intelligent AI agents and multi-agent systems

created 2 years ago
25,597 stars

Top 1.6% on sourcepulse

GitHubView on GitHub
Project Summary

Semantic Kernel is an enterprise-ready, model-agnostic SDK for integrating AI capabilities into applications. It empowers developers to build, orchestrate, and deploy AI agents and multi-agent systems, supporting complex workflows and offering flexibility with various LLM connectors and plugin ecosystems.

How It Works

Semantic Kernel provides a framework for creating modular AI agents that can access tools (plugins), memory, and planning capabilities. It supports multi-agent systems, allowing specialized agents to collaborate on complex tasks. The SDK offers seamless integration with vector databases and supports multimodal inputs, enabling sophisticated AI applications with enterprise-grade reliability.

Quick Start & Requirements

  • Installation: pip install semantic-kernel (Python), dotnet add package Microsoft.SemanticKernel ( .NET).
  • Prerequisites: Python 3.10+, .NET 8.0+, or JDK 17+. Environment variables for AI service API keys (e.g., OPENAI_API_KEY, AZURE_OPENAI_API_KEY) are required.
  • Resources: Official documentation and detailed samples are available.

Highlighted Details

  • Model flexibility with connectors for OpenAI, Azure OpenAI, Hugging Face, NVIDIA, and more.
  • Extensible plugin ecosystem supporting native code, prompt templates, and OpenAPI specs.
  • Vector database integration with Azure AI Search, Elasticsearch, Chroma, and others.
  • Local deployment options via Ollama, LMStudio, or ONNX.

Maintenance & Community

Microsoft maintains the project. Community engagement is encouraged through GitHub discussions and a Discord server. Contributions are welcomed, with a process for feature proposals to ensure alignment with the project's direction.

Licensing & Compatibility

Licensed under the MIT license. This permissive license allows for commercial use and integration into closed-source applications.

Limitations & Caveats

The framework is actively developed, and while enterprise-ready, specific features or connectors might be in preview or subject to change. Users should consult the latest documentation for the most up-to-date compatibility and feature status.

Health Check
Last commit

1 day ago

Responsiveness

1 week

Pull Requests (30d)
68
Issues (30d)
104
Star History
1,468 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.