# SWIRL AI Connect > SWIRL is the private knowledge layer for enterprise AI: a federated AI search and Retrieval-Augmented Generation (RAG) platform that connects to 150+ enterprise sources (Microsoft 365, SharePoint, Google Workspace, Salesforce, ServiceNow, Confluence, Jira, Snowflake, GitHub, iManage, Box, web search engines, AI models, and more) without copying, ingesting, or indexing data. Every result is traceable to its source, and teams can pin the canonical, organization-approved answer for any query. SWIRL is offered as open-source Community Edition (Apache 2.0), SWIRL Enterprise (SaaS or self-hosted), and OEM / source-code licensing for product builders. SWIRL was created and open-sourced by Sid Probstein in 2023 and is developed by SWIRL AI. SWIRL queries each source in parallel using the user's existing permissions, normalizes and re-ranks results with a local three-pass relevancy pipeline (keyword/BM25, then E5 embeddings with hybrid RRF fusion, then an MS-MARCO cross-encoder), and optionally generates an answer with traceable citations using the LLM of the customer's choice. No vector database is required and no data leaves the source systems unless the operator explicitly enables it. The core message: SWIRL makes your chosen LLM and agents better, without moving your data. As of SWIRL 5, the standalone AI Search Assistant is deprecated in favor of headless, agentic retrieval. SWIRL 5 is API-first with a first-class MCP server, so any agent (Claude, Copilot, ChatGPT, or a custom agent) calls SWIRL as its governed knowledge layer. The Galaxy UI remains as a demo and admin surface. This site (swirlaiconnect.com) is the SWIRL marketing site. Product documentation lives at https://docs.swirlaiconnect.com (llms.txt: https://docs.swirlaiconnect.com/llms.txt). The legal-AI vertical site is https://swirllegal.com (llms.txt: https://swirllegal.com/llms.txt). ## New in SWIRL 5 - Home dashboard with workspaces and recent files from every connected source (config-driven; adding a source is configuration, not code). - Canonical answers (Pinned Results): teams pin the organization-approved answer for a query; every later search, by a person or an agent over MCP, returns the endorsed result. - Three-pass relevancy pipeline that runs locally (no data sent over the wire); no vector database required. - First-class MCP server and REST API for headless, agentic retrieval. - Hallucination warning: each generated answer is checked against its cited sources and unsupported claims are flagged. - Business console with AI-Yield analytics, semantic caching, and deduplication. ## Product - [Home - The private knowledge layer for enterprise AI](https://swirlaiconnect.com/): Federated AI search and RAG across 150+ systems. No copying, no index, no vector database. Ranked, permissioned, organization-approved answers for people and agents. - [Connectors](https://swirlaiconnect.com/connectors): 150+ out-of-the-box connectors - enterprise platforms (M365, SharePoint, Google Workspace, Salesforce, ServiceNow, Confluence, Jira, Box, Dropbox, iManage, NetDocuments, Slack, Teams), search engines, databases (Snowflake, Postgres, Elastic, Solr), AI models, and research sources. - [Pricing](https://swirlaiconnect.com/pricing): An annual platform license in three editions (Departmental, Business, Enterprise), a paid Founding-Customer program, a creditable paid pilot, and OEM / embed licensing. Priced by scope, not per-seat. - [Releases](https://swirlaiconnect.com/releases): Product release notes for SWIRL Community and SWIRL Enterprise. - [FAQ](https://swirlaiconnect.com/faq): SWIRL 5 features, editions, deployment, connectors, RAG, MCP, security and compliance, OEM embedding, and support. ## Use cases and proof - [Case Studies](https://swirlaiconnect.com/case-studies): Real enterprise deployments - an AmLaw firm replacing aging federated search, a business school unifying faculty and staff search, an anonymized drone manufacturer federating 10+ silos (M-Files, SpiraPlan, Redmine, SVN, file shares, internal sites), and COMPLiQ embedding SWIRL in its GRC platform for private, on-prem-LLM insight. - [Consulting & Build Services](https://swirlaiconnect.com/consulting): Agentic connector factory, custom integrations, Docker and Kubernetes deployment, and OEM-embedding services for SaaS platforms and enterprise builders. ## Company - [History](https://swirlaiconnect.com/history): The story of SWIRL - from the 2023 open-source release to today's private knowledge layer for enterprise AI. - [Team](https://swirlaiconnect.com/team): The SWIRL team - experts in AI, search, data, and human behavior. - [News & Announcements](https://swirlaiconnect.com/news): Company news, awards (e.g., KMWorld 100 Companies That Matter), and partnership announcements (e.g., iManage Technology Partner Program). - [Contact](https://swirlaiconnect.com/contact-us/): Contact SWIRL AI. ## Content - [Blog](https://swirlaiconnect.com/blog): ~200 posts on federated AI search, the private knowledge layer, agentic systems and MCP, RAG without a vector database, canonical answers, knowledge management, and SWIRL product updates. - [Resources](https://swirlaiconnect.com/resources): Documentation, blog, connector library, GitHub, white paper, and data sheet. ## Documentation - [SWIRL Docs](https://docs.swirlaiconnect.com/): Full product documentation - Quick Start, User Guide, Admin Guide, Developer Guide and Reference, Installation, Kubernetes, Security, RAG, MCP, and Microsoft 365 / Google Workspace / SharePoint guides for both Community and Enterprise. - [Docs llms.txt](https://docs.swirlaiconnect.com/llms.txt): Machine-readable index of the documentation site. ## Localization - [日本語 (Japanese)](https://swirlaiconnect.com/jp): Japanese-language overview of SWIRL, the private knowledge layer for enterprise AI. ## Optional - [Sitemap (XML)](https://swirlaiconnect.com/sitemap.xml): Full URL list for swirlaiconnect.com. - [robots.txt](https://swirlaiconnect.com/robots.txt): Crawl policy. - [Privacy Policy](https://swirlaiconnect.com/privacy-policy/) - [Terms of Service](https://swirlaiconnect.com/terms-of-service/) - [SWIRL on GitHub](https://github.com/swirlai/swirl-search): Apache 2.0 source for SWIRL Community Edition. - [SWIRL Legal](https://swirllegal.com/): Vertical site for legal AI - knowledge authority, traceable citations, and Claude-for-Legal integration.