LLMTornado
View on GitHubThe .NET library to build AI agents with 30+ built-in connectors.
.NET SDK for building AI agents and workflows with 30+ provider connectors, MCP and A2A support, vector DB integrations, multimodal IO, and a graph-based agent orchestration API. Works with local runtimes like vLLM, Ollama and LocalAI.
Use Cases
Build provider-agnostic chat apps across 30+ LLM APIsOrchestrate multi-agent graphs with handoffs and parallel executionRAG pipelines with built-in vector DB connectorsConnect agents to tools/data via MCPCross-platform agent collaboration via A2ARun local models with vLLM/Ollama/LocalAIImage, video and audio generation workflowsReal-time audio transcription and voice callsMultimodal document/URL/video summarizationEmbeddings for text and imagesSemantic Kernel interoperability in .NET appsGuardrails and request/response transformationMermaid export of agent workflowsAnthropic-style Skills loading for specialized tasks
Built With
- Language
- C#
- Frameworks
- .NET · Semantic Kernel · Microsoft.Extensions.AI · MCP · A2A · OpenTelemetry · vLLM · Ollama · LocalAI · Chroma · PgVector · Pinecone · Faiss · Qdrant
Tags
dotnet · csharp · llm · ai-agents · multi-agent · orchestration · mcp · a2a · rag · vector-database · sdk · multimodal · embeddings · provider-agnostic · local-inference · workflow