Back to directory

LLM Tornado

LLM Tornado is a .NET SDK for building AI agents and workflows against more than 30 model providers and vector databases through one provider-agnostic interface.

LLM Tornado

LLM Tornado is a .NET library for building, orchestrating and deploying AI agents and workflows. It ships built-in connectors to over 30 providers, including Anthropic, OpenAI, Google, Cohere, Mistral, DeepSeek and OpenRouter, as well as local runtimes such as vLLM, Ollama and LocalAI, and exposes each provider's distinct features through strongly typed code rather than a lowest-common-denominator API.

Its agent orchestration model separates an Orchestrator (the graph), a Runner (a node) and an Advancer (an edge), and supports handoffs between agents, parallel execution and export to Mermaid diagrams. It supports the Model Context Protocol and an Agent2Agent protocol for cross-platform agent collaboration, text, image, video, document, URL and audio input and output, and integrates with Microsoft.Extensions.AI for use inside Semantic Kernel applications.

A pipeline is written once and can run against any supported provider by changing only the model's name.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.