Bruriah is an open-source MCP (Model Context Protocol) server designed as a work-intelligence tool. It delivers evidence-backed answers drawn directly from a user's personal history and documents, emphasizing retrieval, provenance tracking, and protection against prompt injection. It is intended for developers building agents that require trustworthy context from personal data.
Bruriah sits in PulseGate's AI & ML category. It focuses on retrieving trustworthy, provenance-linked answers from personal work history and documents without hallucinations or prompt injection risks. Bruriah is an open-source project aimed at developers and AI agent builders. Bruriah is open source under the Apache-2.0 license. It runs on the command line and API, and it can be self-hosted.
Behind Bruriah is Leonardo Primero, and it first shipped in 2026. Development happens publicly on GitHub with 86 commits in the last 90 days. Among its 5 catalogued features are MCP Server, Evidence Provenance, and Personal Retrieval. It exposes integrations via an MCP server and a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match