Two open-source dashboards let you watch AI pipelines in real time
Two open-source tools were released that let developers see exactly what's happening inside AI pipelines as they run. One targets .NET apps, the other macOS, and both help cut costs by spotting unnecessary LLM calls.
When building AI applications, figuring out why something went wrong is notoriously hard. LLMs often run through multiple steps — searching documents, calling other agents, generating text — and the whole process looks like a black box from the outside. The first tool is an observability dashboard for .NET developers working with RAG pipelines and multi-agent systems; it shows each step's inputs, outputs, and timing in a single view. The second is a macOS debugger that visualizes LLM call chains live as they execute, making it easy to spot redundant or slow calls. Together, they address one of the most practical pain points in AI development: reducing wasted API spend and speeding up debugging.
Key points
- See every step of your AI pipeline in real time — no more guessing where it broke
- Spot duplicate or unnecessary LLM calls and cut API costs
- Works for .NET developers (observability dashboard) and macOS users (agent debugger)
- Both tools are open source and free to use
- Supports multi-agent flows where several AI agents hand off tasks to each other
Quick term guide
- open-source
- Software whose code is shared publicly so others can inspect, use, or change it.
- developers
- Developers are people who build software, apps, or websites.
- observability
- The ability to monitor and understand what's happening inside a running system by looking at its outputs and logs.
- RAG pipeline
- The full process of splitting documents into chunks, converting them to embeddings, storing them, and searching them at query time.
- multi-agent system
- A setup where several AI programs each take a specific role and work together to complete one larger task
- multi-agent
- A setup where several AI agents each handle a different subtask and work together to complete a larger goal.
- LLM call chain
- The sequence of requests sent to a language model as it works through multiple steps to produce a final answer.
- open source
- Software whose code is available for people to view and often modify.