Archive
Two thirds of AI users reach AI services through personal accounts on corporate devices, and shadow AI now appears in 43% of the AI security incidents IBM studied. The risks, the four detection layers, the acceptable use policy and the controls that turn unsanctioned use into governed use.
In the spring of 2026, engineers at large technology companies competed on leaderboards ranked by how many AI tokens they consumed. By summer the leaderboards were gone and the budgets were blown. The episode is a lesson in what a token is: a unit of cost, not a unit of work.
Claude now runs on Amazon Bedrock, Google Cloud and Microsoft Foundry, and GPT models run on both OpenAI and Azure. That makes cross-cloud failover practical, but each cloud throttles, authenticates and names models differently. Five gateways, measured against seven published criteria.
Claude Code, Codex CLI and Cursor each reach a model provider in a different way. Five gateways that put all three behind one set of developer keys, budgets and logs, compared on how each client connects, what governance applies and where the gateway runs.
A multimodal LLM stack sends images, audio, video and files as well as text. Five gateways, measured endpoint by endpoint against the same published criteria, and which kind of team each one suits.
Most production teams now call at least two of the three big model providers. Five gateways that put OpenAI, Anthropic and Gemini behind one endpoint, measured on native SDK formats, cross-provider failover, spend control and where the proxy runs.
Most teams now run some models on their own GPUs and rent the rest. Five self-hostable gateways that route between vLLM, Ollama and hosted APIs, compared on how they reach local servers, how they decide where a request goes, and what happens when a local box falls over.
An on-premise LLM stack is only as private as the gateway in front of it. Five self-hosted AI gateways, read at the level of what each one fetches from the internet, how it installs without a connection, and how it routes to vLLM, Ollama and private cloud endpoints.
Agent frameworks have converged on the same feature list, but they still differ in how they model control flow, where state lives and how much they assume about your model provider. Ten code-first, open-source frameworks, compared against published criteria with GitHub activity checked on 5 October 2026.
An enterprise AI agent platform is where agents run, get an identity, reach tools and get audited. Ten managed options, from the three hyperscalers to the SaaS suites and an automation tool, compared on published criteria with documented prices.
An AI gateway now sits in front of most production model traffic. Ten options, from open-source binaries to cloud API platforms and managed routers, measured against ten published criteria before any ranking.
Claude Opus 5.5 leads the independent indexes this month, but no single model is best at everything. Ten models, from $50-per-million-token flagships to MIT-licensed open weights, measured against published criteria, with the best pick for reasoning, coding, cost, long context, multimodal and self-hosting.
Most of the MCP servers worth connecting in 2026 are now hosted by the vendors themselves, behind OAuth. The differences that matter are how much a server lets an agent change, how finely access can be narrowed, and how each one has handled its security incidents.
A coding agent is only as useful as the systems it can reach. Ten MCP servers for repositories, browsers, errors, databases, tickets, designs and infrastructure, compared on what they unlock, what they cost in context, and what they can break.
An open-source AI gateway is only as open as its license file and its paid tier allow. Ten self-hosted LLM gateways, read at the level of the LICENSE file, the dependency list and the release history, with criteria published before the ranking.
Xiaomi, Z.ai, Moonshot, Alibaba and DeepSeek now publish weights within a few points of the closed frontier. Ten models, ranked on Artificial Analysis and Arena scores, with the licence clause, parameter count and GPU budget that decide whether a team can actually run each one.
No single product secures the Model Context Protocol. Tool poisoning, rug pulls, shadow servers and token misuse each need a different control. Ten tools, compared against the risks the specification and OWASP name, with the gaps each one leaves.
The Model Context Protocol leaves authorization optional and tool safety to the implementer. An MCP gateway is where most teams end up enforcing both. Ten gateways, compared on the controls the specification asks for.
TypeSafe's Jev returns typed answers with probabilities instead of text. Its documentation, the first developer reports and early independent papers show where it fits in a pipeline, what the published price works out to, and why its probabilities need checking on your own data.
LiteLLM is the default first gateway for many teams. Its production footprint, the March 2026 PyPI compromise and its license split send some of them looking elsewhere. Six alternatives, measured against published criteria, with a migration path.