Y1y14·Oct 6, 2025Submission
Show HN: I built an open-source AI data layer that connects any LLM to any data
Excited to share a project I’ve been building for months! Would love to receive honest feedback :)
My motivation: AI is clearly going to be the interface for data. But earlier attempts (text-to-SQL, etc.) fell short — they treated it like magic. The space has matured: teams now realize that AI + data needs structure, context, and rules. So I built a product to help teams deliver “chat with data” solutions fast with full control and observability (agent tracing, quality scores, etc) — am I wrong?
The product allows you to connect any LLM to any data source with centralized context (instructions, dbt, code, AGENTS.md, Tableau) and governance. Users can chat with their data to build charts, dashboards, and scheduled reports — all via an agentic, observable loop. With slack integration as well!
* Centralize context management: instructions +
Read the rest
external sources (dbt, Tableau, code, AGENTS.md), and self-learning
* Agentic workflows (ReAct loops): reasoning, tool use, reflection
* Generate visuals, dashboards, scheduled reports via chat/commands
* Quality, accuracy, and performance scoring (llm judges) to ensure reliability
* Advanced access & governance: RBAC, SSO/OIDC, audit logs, rule enforcement
* Deploy in your environment (Docker, Kubernetes, VPC) — full control over infrastructure
GitHub: github.com/bagofwords1/bagofwords
Docs / architecture / quickstart: docs.bagofwords.com