Tag archive
LiteLLM's Rust gateway reduces forwarding latency and memory use in controlled benchmarks, but feature gaps and routing-quality risks limit the case for migration.
How CVE-2026-42271 turned LiteLLM's MCP connection test endpoints into a command execution primitive, and what defenders should change.
How a fail-open authentication fallback in LiteLLM's MCP endpoint exposes self-hosted AI gateways and the credentials they hold.
Most AI apps let you pick one model, and then every query goes to it. "What's the capital of...
This guide connects Cursor to a LiteLLM proxy, one you run yourself or one your team already hosts....
How to combine local inference with governed cloud fallback by orchestrating Ollama, OpenCode, and...
LiteLLM has been the default OSS LLM gateway since 2024, but CVE-2026-35029 and the working-month ops overhead of self-hosting are pushing teams to reevaluate. Here is an honest look at the alternatives — Leanroute, Portkey, Kong AI Gateway, Helicone, and OpenRouter — and when each is the right pick.
CVE-2026-59822 let an unauthenticated attacker open an authenticated MCP session on LiteLLM. AI gateways hold credentials and deserve to be treated as such.
LLM middleware holds every provider key in your stack, sees every prompt, and often has admin access to spend caps. Self-hosting it means owning the full operational surface. A recent LiteLLM CVE is a reminder to make that choice deliberately, not by default.
This guide connects OpenAI Codex to a LiteLLM proxy, one you run yourself or one your team already...
ZoomEye measurement of AI gateway and orchestration platform exposure, with credential-risk interpretation.
I've been building LLM applications for a while, and I kept hitting the same problem: every gateway...