Latest

Sovereign AI Infrastructure: A Guide for Enterprises

Sovereign AI infrastructure is the set of models, data stores, network paths, and controls an enterprise runs inside its own jurisdiction and infrastructure. This guide covers the layers it must include, in-VPC, on-prem, and air-gapped options, and why a self-hosted AI gateway is its control point.

API Key Management for LLM Apps: How to Manage Client Access

API key management for LLM applications means issuing every app, service, and environment its own revocable credential instead of sharing raw provider keys. This guide shows how to do it with Bifrost virtual keys, covering scoping, rate limits, rotation, revocation, and log attribution.

OpenAI Agents SDK Through a Gateway: Models, Budgets, MCP

The OpenAI Agents SDK sends every model call through an OpenAI client, so one base URL change routes an agent workflow through an AI gateway. This guide shows the working code for Bifrost, then adds non-OpenAI models, failover, per-agent budgets, MCP tools, and tracing.

Agentic AI Security: Risks and Runtime Controls

Agentic AI security is the discipline of controlling what autonomous agents can call, which credentials they hold, and how their actions are recorded. This guide maps six agent-specific risks to OWASP guidance and to the runtime controls an AI gateway enforces.

Agent Gateway vs LLM Gateway vs MCP Gateway: Key Differences

An agent gateway governs agent-to-agent calls, while an LLM gateway governs model calls and an MCP gateway governs tool calls. This comparison explains what each layer controls, where they overlap, and how Bifrost brings models, tools and agents into one gateway.

A2A Protocol: How to Run Agent Traffic Through a Gateway

The A2A protocol is an open standard that lets AI agents discover each other, exchange messages, and hand off tasks. This guide covers its core objects and transports, then shows how to route, govern, and trace A2A traffic through Bifrost Agent Gateway.

Claude Agent SDK Through a Gateway: Routing, Budgets, MCP

The Claude Agent SDK packages Claude Code's agent loop, tools, and context management as a Python and TypeScript library. This guide shows how to route Claude Agent SDK traffic through Bifrost for provider routing and failover, per-tenant budgets, and governed MCP tool access.

How to Enforce AI Budgets Per Team, Project and Key

An AI budget is a hard spending ceiling enforced in the LLM request path, not a monthly report. This guide covers budget hierarchies, project mapping, reset windows, rate limits, exhausted-budget behavior, and a worked $10,000 example in Bifrost.

Non-Human Identity for AI Agents at the Gateway

A non-human identity is a credential and policy that belongs to software rather than a person. This guide explains why every AI agent needs its own, how virtual keys scope and budget it, and how Bifrost Agent Gateway handles credentials when one agent calls another.

MCP Connectors Explained: How They Work and How to Govern Them

An MCP connector is the configured link between an AI application and an external system, made of an MCP client, a transport, credentials, and an MCP server. This guide explains how connectors work, where they break down at scale, and how an MCP gateway governs them centrally.

MCP Authorization: OAuth Scopes and Per-Tool Permissions

MCP authorization controls which clients may call a protected MCP server and what their tokens allow. This guide walks through the OAuth 2.1 flow in the current MCP spec, scopes and step-up, token audience rules, the gaps teams hit in production, and per-tool enforcement at a gateway.

EU AI Act Compliance for LLM Applications and Agents

EU AI Act compliance for LLM applications means mapping each feature to a risk category and producing evidence for logging, oversight, and transparency duties. This guide covers the post-Omnibus timeline, the engineering obligations, and where an AI gateway helps and where it stops.

ABAC vs RBAC for AI Agents and LLM Access

ABAC vs RBAC is the choice between granting access by job role or by evaluating attributes of the caller, resource, and context. This guide compares both models and shows how to apply them to LLM, MCP tool, and AI agent access at the gateway.

OpenAI Responses API vs Chat Completions vs Anthropic Messages

The OpenAI Responses API is OpenAI's stateful, item-based interface for agentic apps, while Chat Completions and Anthropic Messages remain stateless message APIs. This guide compares the three on state, tools, reasoning, and retention, and shows how Bifrost serves all three formats.