federated-search

AI Search & RAG Without Moving Your Data. Get instant answers from your company's knowledge across 100+ apps while keeping data secure. Deploy in minutes, not months.

Neuronto Agentic Resource Discovery (ARD) Index. Federated search across every public ARD registry, plus a verified tool index read from each MCP server's own tools/list, hybrid lexical and semantic retrieval, and ARD-Bench.

An app that showcases federated search in Typesense (Open source alternative to Algolia)

Log issues, request enhancements or ask questions about Searchcraft.

Emacs Advanced Searching Interface

A decentralized cooperative memory & research layer for AI agents — collectively and cooperatively learning and advancing as a community.

开元族谱 (OpenZupu) 是一个面向宗亲会、档案馆的开源数字化家谱管理与联邦互证系统。支持 Y-DNA/mtDNA、STR 比对、本地 AI/OCR 录入及分布式联邦检索。

The self-hostable open-source company OS. Google Workspace SSO + per-user data connections + privacy-preserving federation across users. Apache 2.0.

Multi-agent AI analytics & polyglot data warehouse platform. Unifies Cloudflare D1 (SQLite), AlloyDB (PostgreSQL), and Aiven MySQL into a governed Google BigQuery Data Lakehouse with 13 quality gates & fanout-safe AI SQL generation.

TypeScript client library for the Searchcraft API

Federated Search Engine built with Spring Boot, Java, HTML, CSS, and JavaScript. Aggregates results from multiple sources with filtering, ranking, and spam detection.

Federated listings marketplace across personal humanMCP servers

Metadata-driven Spring Boot federated search service for querying and aggregating data across MySQL, PostgreSQL, and MongoDB.

Federated plugin registry aggregator for DeepSeek Harness — combine npm, GitHub, and JSON catalogs into one searchable index.

Federated memory search MCP server — one query, all knowledge

Federated knowledge retrieval engine for AI agents. Routes queries across specialized backends (FTS5, ChromaDB, graph) via a registry-first orchestrator with TypeSafe/Jev AI routing and evidence re-ranking. Read-only by default, security-gated by design.

Gives applications one reliable search API across separate Typesense clusters, with durable indexing, safe routing changes and recovery controls.

Private, local-first federated search across SearXNG, Obsidian, local documents, and opt-in browser history—with locally generated answers and full citations.

🎯 Federated recall across an agent's knowledge — cortex, agent-hq, scout and lens — in one token-budgeted query. CLI + web + MCP. Zero deps.