# Praxis

A local-first knowledge layer that turns an organization's scattered documents, operational data and decision history into searchable, source-linked context an AI agent can inspect and reuse.

Praxis is built for organizations whose important knowledge is spread across CRMs, documents, spreadsheets, analytics tools, support systems, meeting notes and past decisions, where an AI agent can be capable and still blind if it only sees one stale export or narrow database. It turns that scattered knowledge into source-linked context that an agent can inspect, explain and reuse, rather than acting as a hosted service, CRM, data warehouse, business-intelligence tool or autonomous runtime itself.

It targets teams whose work depends on context spread across disconnected systems, such as legal firms, managed service providers, healthcare organizations, security teams, agencies and internal operations teams, and is meant to answer questions such as which campaigns produced paying customers, what prior matters relate to a current case, or what changed recently for a client. Its core component runs locally today, with hosted extensions aimed at connecting to live operational systems and multi-client workflows.

Website: https://github.com/sparkplug604/praxis