# higress-group/higress

🤖 AI Gateway | AI Native API Gateway

Repository: https://github.com/higress-group/higress
Canonical: https://ross.abutalabs.com/products/higress
Homepage: https://higress.ai
Language: Go
License: Apache-2.0
License Family: permissive
Topics: api-gateway, ai-gateway, envoy, ai-native, cloud-native
Last push: 2026-08-25T16:35:28+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 100
- inputs: {"age_days": 1406, "days_push": 8, "days_rel": 20, "gap_med": 14, "n_releases_24m": 36}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9196, forks 1252 (observed 2026-08-28T04:10:28.819420+00:00)

## What it is
Higress is a CNCF Sandbox, cloud-native AI-native API gateway built on Istio and Envoy, extensible with Wasm plugins written in Go, Rust, or JS. It unifies management of LLM API traffic, MCP Server hosting, and Kubernetes inference workloads with features like multi-model proxy, token rate limiting, semantic caching, and content safety.

## Use cases
- proxy requests to multiple LLM providers behind one unified API
- host and expose MCP servers for AI agents
- rate-limit and track token usage per consumer
- cache LLM responses semantically to save tokens
- filter sensitive data and unsafe content in AI traffic
- serve as a Kubernetes ingress / API gateway
- fallback between model providers on failure

## When to choose
- you need a production-grade gateway for LLM, agent, and MCP traffic
- you want protocol conversion across 100+ model providers with fallback
- you need token quotas, observability, and content safety at the gateway layer
- you want Envoy/Istio-based ingress with Wasm plugin extensibility

## When to avoid
- you only need a simple reverse proxy without AI-specific features
- you cannot run Docker or Kubernetes infrastructure
- you need a lightweight client-side SDK rather than a gateway service

## Facets
- artifact type: service
- maturity: active
- function: api-gateway, proxy, rate-limiting, caching, middleware, mcp, llm-inference, monitoring, auth, plugin-system
- domain: large-language-models, apis, microservices, cloud-computing, self-hosted, security
- platform: cloud, self-hosted, go, rust
- tags: ai-gateway, envoy, istio, wasm-plugins, mcp-server-hosting, token-management, semantic-cache, cncf-sandbox, model-fallback, ingress, ai-agents, devops, docker, kubernetes, linux

## Member repositories
- higress-group/higress (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:28.819420+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:23:19.127969+00:00, confidence not recorded.
  - readme: https://github.com/higress-group/higress (fetched 2026-08-28T04:10:28.819420+00:00, sha b33f585b1942)
  - homepage: https://higress.ai (fetched 2026-08-29T08:23:23.981252+00:00, sha 8a5a72dea6fc)
  - site_page: https://higress.ai/docs/latest/overview/what-is-higress (fetched 2026-08-29T08:23:23.990698+00:00, sha 843701bdca48)
  - site_page: https://higress.ai/docs/developers/developers_dev (fetched 2026-08-29T08:23:23.992946+00:00, sha d194fe855fa0)
  - site_page: https://higress.ai/docs/ai/quick-start (fetched 2026-08-29T08:23:23.994858+00:00, sha 99a94401b65d)
  - site_page: https://higress.ai/docs/ai/scene-guide/multi-proxy (fetched 2026-08-29T08:23:23.996678+00:00, sha 37b7937acb4f)
  - site_page: https://higress.ai/docs/ai/scene-guide/application-safety (fetched 2026-08-29T08:23:23.998685+00:00, sha eee5600ad943)
  - site_page: https://higress.ai/docs/ai/scene-guide/semantic-cache (fetched 2026-08-29T08:23:24.000849+00:00, sha e5fca7cd0683)
  - site_page: https://higress.ai/docs/ai/scene-guide/token-management (fetched 2026-08-29T08:23:24.002894+00:00, sha bfa5e6cffc54)
- Data as of 2026-08-30T08:39:29.467469+00:00.