4 posts tagged with "open-source"

The first decision in any agentic project isn't which model to use. It's which framework will orchestrate it. Get that wrong and you inherit a stack you can't run locally, can't afford to scale, and can't escape when the vendor changes the API.

This is a JigsawFlux project. JigsawFlux builds open-source tools for health tech, humanitarian response, and crisis management — in places where "cloud-native" is not an option and IT budgets are measured in grants, not headcount. That context imposes hard constraints on every architecture decision: portability, cost, and freedom from vendor lock-in.

The frameworks here — LangGraph, CrewAI, and AutoGen — were chosen because they meet those constraints. They are open source, actively maintained, and run entirely on hardware you own. Alternatives like Microsoft Semantic Kernel or Amazon Bedrock Agents are capable, but they introduce hard dependencies on specific cloud ecosystems. That trade-off doesn't fit the JigsawFlux model.

In Part 1 I ran Ollama directly on a Linux machine and wired it up through an MCP layer to a small web app. It worked. But bare-metal has friction — if the process crashes, it stays down. Adding Open-WebUI means managing another process. Resource limits are manual. There's no clean internal networking between services.

This post moves the whole thing into Kubernetes. The goal isn't enterprise-grade infrastructure — it's a home lab setup that's reliable, easy to extend, and honest about its limitations.

Manifests are in the ollama-mcp-starter repo under backend/k8s-deployment/.

Welcome to the JigsawFlux Blog — a space for updates, ideas, and stories from the JigsawFlux open-source community.

AI inference doesn't have to mean a cloud API call. This post walks through a spike I built to run a locally hosted language model through a clean, layered architecture using Ollama and the Model Context Protocol (MCP).

The full source is on GitHub. Contributions and feedback welcome.