# RAW Labs

> AI engineering for the enterprise. We engineer the data, integration, governance, and runtime layers behind production-grade AI.

RAW Labs (https://www.raw-labs.com) is a Swiss-headquartered engineering firm specialising in production-grade AI infrastructure for enterprises. Founded in 2015, we spent a decade building enterprise data platforms (data virtualization, data lakes, secure data access) and now build the data, integration, governance, and runtime layers behind AI systems that have to work reliably under real load — typed inputs, traced calls, policy enforcement, observable behaviour. We open-source MXCP, a production-grade Model Context Protocol (MCP) server, and develop Kora, our reliable agentic-workflow product. Customers include Squirro, where RAW Labs technology powers operational data access inside SquirroGPT.

## Products

- [Kora](https://kora.raw-labs.com): Production-grade orchestration for AI agents. Built so they behave the same on the thousandth run as on the first — typed inputs, traced calls, deterministic recovery.
- [MXCP](https://mxcp.dev): Open-source enterprise-grade MCP framework. Audit trails, policy enforcement, observability, and operational guardrails for putting Model Context Protocol servers into production.

## Engineering blog

- [Introducing Kora: A Workflow Operating System for AI-Ready Operations](https://www.raw-labs.com/blog/introducing-kora-workflow-operating-system/): For enterprise AI, capability is no longer the hard part - control is. Kora runs critical business processes as governed workflows, introducing AI one reliable step at a time.
- [Constrained Space, Better Code: MXCP & Claude Skills](https://www.raw-labs.com/blog/constrained-space-better-code/): LLMs can generate code fast but also break systems just as easily. Learn how frameworks with built-in validation transform chaotic AI code generation into reliable, production-ready output.
- [MXCP: Production-Grade MCP Server for Enterprise AI](https://www.raw-labs.com/blog/mxcp-production-mcp-enterprise-ai/): Build secure AI agents with MXCP. Enterprise MCP framework with audit trails, policy enforcement, and governance for connecting AI to databases, APIs, and enterprise systems.
- [RAW Labs Partners with Squirro for Real-Time Enterprise AI Data Access](https://www.raw-labs.com/blog/raw-labs-squirro-partnership-announcement/): RAW Labs and Squirro partner to bring real-time operational data to SquirroGPT. Enable AI-driven queries and actions across databases, SaaS, and enterprise systems.
- [The End of Websites: Moving to a Conversational Web](https://www.raw-labs.com/blog/end-of-websites-conversational-web/): AI agents are bypassing websites for APIs. Learn why MCP, function calling, and structured data are replacing traditional web interfaces for AI-first interactions.

## Site

- [Home](https://www.raw-labs.com/): Introducing Kora — RAW Labs' workflow operating system that runs critical business processes as governed agentic workflows
- [Company](https://www.raw-labs.com/company): Brand overview, products, industries, and mission
- [About](https://www.raw-labs.com/about): Who we are — Swiss engineering firm since 2015
- [Careers](https://www.raw-labs.com/careers): Engineering, research, and builder roles
- [Contact](https://www.raw-labs.com/contact): Reach the team

## Optional

- [RSS feed](https://www.raw-labs.com/rss.xml): Engineering blog feed
- [Sitemap](https://www.raw-labs.com/sitemap-index.xml): Full site map
- [Full content](https://www.raw-labs.com/llms-full.txt): Concatenated full text of blog posts for LLM ingestion
- [Privacy policy](https://www.raw-labs.com/privacy)