A Go framework for building streaming pipelines that produce live semantic knowledge graphs. For environments where connectivity is intermittent, compute is finite, and the environment will not cooperate.
go get github.com/C360Studio/semstreams
Current AI infrastructure assumes always-on connectivity, abundant compute, rich model access, and an enormous token budget. What we call ambient affluence.
Thirty years of experience has taught us that these idealistic conditions rarely hold. Even if you have the budget, operational reality often has other plans. So if the environment will not cooperate, the architecture should embrace that reality from the start.
Read "Comms Suck" →The graph holds locally and syncs when the link comes back. You don't lose state when you lose the network.
Rules and workflows keep running. The system degrades through tiers — not off a cliff.
Structural relationships still function. You bring what you have; the system meets you there.
Start with what works offline. Add intelligence when you can afford it and when the problem demands it. Each tier is genuinely independent — you don't lose everything when you lose something.
Dotted notation internally. Interop at the boundaries. Take or leave what you need — no prescribed ontology required on day one. The system meets you where you are.
Full trajectory capture. An agent that can explain what it did and why isn't just more trustworthy — it's actually useful when auditability isn't optional.
The model registry lets you configure models by capability — right-size inference to the task. Agentic components are built for efficient token use and managed context. Spend where the problem demands it, not everywhere by default.
The documentation reflects where we are, not where we're going. If your requirements are clearer in production than they were on paper — this was built for you.
Breaking changes will happen. That's the deal.