LanceDB, Chroma, and storage choices
How the assistant framework thinks about vector stores and local metadata.
Why this mattered
Different vector stores make different tradeoffs for local workflows.
This belongs in the development timeline because Agentic Assistants is not a single feature. It is a local-first assistant framework with a CLI, FastAPI and WebSocket server, MCP bridge, Next.js control panel, indexing, scoped retrieval, knowledge bases, pipelines, discovery, and training workflows. The project only became useful once its infrastructure decisions were written down well enough to be repeated.
Design decision
The framework keeps adapters and scoped retrieval patterns so storage can evolve without rewriting assistant behavior.
The practical stack around this decision includes Python, Poetry, Click, FastAPI, WebSockets, MCP, LanceDB, Chroma, DuckDB, Polars, PyArrow, CrewAI, LangChain, LangGraph, Ollama, MLflow, OpenTelemetry, Next.js, Docusaurus. I try to keep the interfaces small: configuration describes intent, runtime code owns behavior, and operational notes explain what a future maintainer should check first.
What I would repeat
The storage decision should serve retrieval quality, observability, and maintenance.
The repeatable pattern is to make the boring path explicit. For this project that means clear repository boundaries, documented setup, predictable deployment commands, and enough observability to know whether the system is healthy or merely quiet.
Reader takeaway
If you are building something similar, start with the workflow you need to repeat every week. Then add only the platform pieces that make that workflow easier to recover, explain, and extend.