# obto.co > AI-optimized mirror of obto.co containing 25 pages totalling 21,776 words of clean markdown content, structured data, and semantic HTML. Original source: https://obto.co/. Last updated: 2026-06-16T02:03:13.640Z. Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG). ## Homepage - [Open Source Democracy](/content/site-root.html): OBTO is a self-hostable, MCP-native platform to build, observe, and deploy autonomous AI agents and full-stack apps — model-agnostic, transparent, no vendor lock-in. (1,277 words) ## Articles & Blog Posts - [01 Acceptance of Terms & Eligibility](/content/site/ob/terms/index.html): OBTO Terms of Service. Read the legal agreement governing use of the OBTO Glass Box AI platform, agentic deployment engine, and related services. (1,714 words) - [01 About OBTO's Agentic Platform](/content/site/ob/responsible-use/index.html): OBTO Responsible Use Policy. Guidelines and limitations for using the OBTO Glass Box AI platform's agentic deployment and orchestration features responsibly. (1,216 words) - [Getting Started](/content/site/ob/getting-started/index.html): Dream, build, and ship. Sign up, connect your AI client to OBTO, and deploy your first app through conversation. (1,051 words) - [Introducing OBTO Functions: The Serverless Powerhouse.](/content/site/ob/functions/index.html) (795 words) - [Get in touch with OBTO](/content/site/ob/contact/index.html): Contact the OBTO team for sales inquiries, technical support, or partnership opportunities. We're based in Albany, NY. (95 words) - [How to Build an MCP Tool: A Practical Guide](/content/site/ob/build-an-mcp-tool/index.html): A practical guide to building a Model Context Protocol (MCP) tool: the three primitives, stdio vs. Streamable HTTP transport, a worked example, and production tips. (1,364 words) - [site/ob/privacy/index.html](/content/site/ob/privacy/index.html) (1 words) - [Multi-Model Orchestration: Routing LLMs by Cost and Task](/content/site/ob/multi-model-orchestration/index.html): Stop paying frontier prices for every token. See how multi-model orchestration routes each LLM request by cost, latency, and task—without lock-in. (1,189 words) - [How to Host a Remote MCP Server in 2026: A Practical Guide](/content/site/ob/host-remote-mcp-server/index.html): Learn how to host a remote MCP server in 2026: transport choices, OAuth, scaling, and observability — and why most hosted MCP endpoints fail. (1,106 words) - [Radical Transparency](/content/site/ob/pricing/index.html): Two dimensions, zero surprises. Pay a base fee for the platform, then only for what your agents consume. Bring your own AI client and pay per application. (1,107 words) - [AI Agent Cost Tracking: Know What Every Run Costs](/content/site/ob/ai-agent-cost-tracking/index.html): A practical guide to AI agent cost tracking: token attribution, per-task unit economics, hidden cost drivers, and how to build a real cost dashboard. (1,121 words) - [AI Agent Observability: What It Takes to Debug Agents in Production](/content/site/ob/ai-agent-observability/index.html): Learn what AI agent observability actually requires—traces, tool calls, token cost, and replay—and how to instrument agents you can debug in production. (1,053 words) - [Insights from the Glass Box](/content/site/ob/blog/index.html): The OBTO blog: articles on agentic AI, the Model Context Protocol, observability, fast inference, and building transparent AI workflows. (463 words) - [The Manifesto](/content/site/ob/about-us/index.html): We got tired of renting black boxes. So we built a glass one. Read the OBTO manifesto and our mission for an Open Source Democracy in AI. (554 words) - [How OBTO is Defining the AI Workforce of the Future](/content/site/ob/ai-workforce/index.html): How OBTO builds an AI workforce: fine-tuning on the OBTO dataset, extensive prompt engineering, and Retrieval-Augmented Generation (RAG) with memory systems. (762 words) - [Services one](/content/site/ob/monitors/index.html): Build And Run Applications Of The Connected World (250 words) - [Support for Groq, Fast Inferencing: Improving AI Workflow Response Times](/content/site/ob/fast-ai-inference/index.html): How Groq's fast inference improves AI workflow response times — low latency, high throughput, and how OBTO uses it for real-time agentic applications. (528 words) - [Serverless Microservices](/content/site/ob/microservices/index.html): Build And Run Applications Of The Connected World (345 words) - [Comprehensive API Development](/content/site/ob/api-engine/index.html): Build And Run Applications Of The Connected World (346 words) - [The infrastructure of intelligence.](/content/site/ob/the-platform/index.html): OBTO is the MCP-native platform for building and deploying agentic AI applications — full-stack backend, observable workflows, and self-hostable on Kubernetes. (410 words) - [Security at OBTO](/content/site/ob/security/index.html): How OBTO secures your data — end-to-end encryption, role-based access, tenant isolation, Glass Box audit trails, and enterprise compliance. (294 words) - [Task Workers](/content/site/ob/schedule-workers/index.html): Build And Run Applications Of The Connected World (211 words) - [Sign up for OBTO](/content/site/ob/signup/index.html): Create your free OBTO account. Get your personal MCP endpoint, connect your AI client, and deploy your first application in under 5 minutes. (48 words) - [Developer Docs](/content/site/ob/documentation/index.html): OBTO developer documentation. Learn how to build routes, server scripts, and MCP-native applications on the OBTO platform. (4,476 words) ## Resources - [Full Page Index](/index.html): Browse all cached pages with rich metadata - [About This Cache](/content/about.html): Methodology, technical details, and usage guidelines - [XML Sitemap](/sitemap.xml): Machine-readable sitemap for crawler discovery - [Robots.txt](/robots.txt): Crawler directives