higress

In this catalog it is the LLM Gateway option when you need to route and govern calls across model providers. Keep higress on the observe/propose side of the loop: useful signals and drafts, with human or policy authority still required before anything irreversible runs.

Applications send chat/completions to the gateway; it routes to providers, applies keys/limits, and returns responses (often with logging/fallbacks).

1. Configure upstream model providers and API credentials.
2. Set routing, budgets, and any default guard policies.
3. Send a canary completion through the gateway and inspect logs.
4. Point agent frameworks at the gateway base URL instead of raw providers.

Related: envoy · kong · litellm · topics/01-architecture · topics/12-central-nervous-system

• Use when: Higress (Alibaba) is an AI-native API gateway on Envoy/Istio patterns with WASM extensibility and AI route features matches the bottleneck and you specifically need to route and govern calls across model providers.
• Skip when: another pack already covers the need with less ops surface, or higress would become a second place people retype truth.
• Prefer instead: compare Envoy, Kong, LiteLLM before locking the cell.

• Ops: confirm license, hosting, and release cadence for higress (higress-group/higress) before relying on it in a live corridor.
• Integration: bad credentials, scopes, or schema drift produce empty retrievals or runaway tool/model spend without an obvious UI alarm.
• Scope: LLM Gateway components support agents; they are not the company ledger or the approval authority.