A gateway filters requests. A policy engine proves what happened.
LiteLLM routes requests to your model providers, tracks spend and adds simple guardrails. Swiftward works at a different layer, and the two run side by side.
What LiteLLM is
An open-source proxy in front of many model providers, with one-click integrations and a large community. It routes each request and filters it.
What Swiftward does differently
Swiftward remembers across events: counters, windowed counters, labels, reputation, per account or per agent. A gateway judges each request on its own.
A gateway's filters are settings you edit in place. A Swiftward policy is a versioned artifact that you roll back by naming the previous version. You backtest a change against your own recorded traffic and read every decision that flips before it takes effect, then run it in shadow or A/B on live traffic.
When something goes wrong, Swiftward names the rule that decided and the frozen version it ran on, in a tamper-evident record. A gateway gives you a log. And a flagged call can wait for a person instead of failing.
Running both
Swiftward goes in front of, or alongside, a proxy you already run, and it governs more than model calls: MCP tool calls, network, FIX and blockchain come through the same policy and land in the same records.