Sabr Research
  • Agentic Market SimulatorLarge-scale agentic market simulationDocument IntelligenceFacts extracted from messy documents · Private beta
  • Custom AI
  • BlogCookbooksEnterprise AI GuidesWhite paper
Contact us
  1. Home
  2. Cookbooks
  3. Deployment & Infrastructure

Deployment & Infrastructure Cookbooks

Getting a model, or an agent built on one, running somewhere real. Self-hosting on your own infrastructure, building tools it can call through MCP, and the practical tradeoffs of doing it yourself versus a hosted API.

AllDeployment & InfrastructureData & EvaluationPost-Training TechniquesModel Architecture & InternalsReinforcement LearningAgentic Systems
Deployment & Infrastructure·Setup Guide

Self-Hosting an Open-Weight Coding Agent on AWS

Run a private coding agent on your own AWS account: instance choice, setup, costs and security. No per-token API bills, and your code stays in your VPC.

AWSEC2vLLMQwenVS CodeDevOps
→
Deployment & Infrastructure·Setup Guide

Building Local MCP Servers for VS Code & Cursor with FastMCP

A step-by-step technical guide to building Python MCP servers with FastMCP, configuring VS Code and Cursor mcp.json, and debugging stdio JSON-RPC streams.

FastMCPMCPVS CodeCursorPythonAI Agents
→
Deployment & Infrastructure·Deep Dive

What is the Model Context Protocol (MCP)?

A technical architecture guide to the Model Context Protocol (MCP). Learn how it solves the M x N integration problem for AI agents and tool calling.

AgentsAnthropicMCP
→
← All cookbooks
Sabr Research

Specialized AI for the enterprise.

NVIDIA Inception Program

Products

Market SimulatorDocument Intelligence

Custom AI

Custom AI systems

Resources

BlogCookbooksEnterprise AI GuidesWhite paper

Company

ContactTerms of Use

© 2026 Sabr Research Inc.

This is the only official website of Sabr Research Inc. We are an independent corporation with no subsidiaries, affiliates, or representatives outside of this platform.