Open Sourcing Fabr and OpenCaddis

Today we're open sourcing two projects: Fabr, our .NET framework for building AI agent systems, and OpenCaddis, the full AI agent workspace built on top of it. Fabr is available under the Apache 2.0 license and OpenCaddis under the MIT license — both free to use, modify, and build upon.

Why We're Doing This

Throughout my career as a software developer, open source has been the foundation of nearly everything I've built professionally. The .NET ecosystem exists because Microsoft made the decision to open source it. The libraries I reach for daily — the ORMs, testing frameworks, logging systems, UI components — they're maintained by people who chose to share their work.

I've been withdrawing from the open source community for my entire career, and it's time to make a deposit. Fabr and OpenCaddis are that deposit.

The AI agent space is also moving fast, and .NET developers are underserved. Most interesting agent frameworks are Python-first. The .NET ecosystem has Microsoft's Semantic Kernel and the emerging Agents SDK, but there's room for more options — especially opinionated, full-stack examples that show how to build a complete agent application, not just call an API.

Fabr: The Framework

Fabr (Fabricate Agent Behavior and Reasoning) started as a question: what would an AI agent framework look like if it were designed as a first-class .NET library? Not a Python project with .NET bindings, but a native .NET framework that uses the patterns .NET developers already know — dependency injection, configuration, async/await, Orleans for distributed state.

Fabr provides the infrastructure that agent applications need:

• Agent lifecycle management — initialization, health reporting, message processing with OpenTelemetry tracing
• Chat history persistence — thread-based message storage with Orleans grain state
• Chat history compaction — automatic LLM-powered summarization to manage context window limits
• Tool resolution — automatic discovery of tools from dependency injection with the IFabrPlugin interface
• Multi-model support — configurable providers (Azure OpenAI, OpenAI, local models) with named configurations
• Structured output — JSON schema extraction for deterministic LLM responses

The key design decision is the FabrAgentProxy base class. Every agent type inherits from it and gets the full infrastructure for free. The concrete agent just implements OnInitialize() and OnMessage().

OpenCaddis: The Application

A framework without an application is just documentation. OpenCaddis is a full AI agent workspace built on Fabr — a Blazor Server application where you create, configure, and interact with multiple AI agents through a chat interface.

It runs entirely on your machine. Conversations, agent configurations, vector memories — all stored locally in SQLite. The only external calls are to your configured LLM provider.

OpenCaddis also includes CaddisFly, a pipeline orchestration engine that lets agents execute multi-step command workflows with approval gates, retries, parallel execution, and timeout controls.

Get Started

# Try OpenCaddis with Docker
docker run -d -p 5000:5000 --name opencaddis vulcan365/opencaddis:latest

# Or clone and build
git clone https://github.com/vulcan365/OpenCaddis.git
cd OpenCaddis/src/OpenCaddis
dotnet run

Both repos have documentation, example configurations, and Docker support. Full documentation is available at opencaddis.ai/docs.

What's Next

Open sourcing is the starting point. Both projects are actively developed, and we're focused on:

• More agent patterns — new agent types and composition patterns
• Plugin development guide — making it easy to build and share plugins
• Additional LLM providers — broadening model support
• Community feedback — listening to what developers need and adjusting accordingly

If you're a .NET developer working with AI, we'd love your feedback. File issues, submit PRs, or just try it out and tell us what works and what doesn't.