Independent reporting on artificial intelligence.


The Frontier Wire

Comparisons

Top 10 open-source AI gateways for self-hosting in 2026

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.

TL;DR

  • The ten open-source AI gateways ranked here are Bifrost, LiteLLM, Kuadrant, Agent Router (formerly Envoy AI Gateway), Apache APISIX, Higress, Kong Gateway, Plano, New API and vLLM Semantic Router.
  • Eight are Apache 2.0 at the repository level. LiteLLM is MIT with a commercially licensed enterprise directory, and New API is AGPLv3 with extra attribution terms.
  • “Open source” rarely means “everything is free”. SSO, audit logs, guardrails, clustering and advanced load balancing sit in a paid tier for Bifrost, LiteLLM and Kong.
  • The footprint ranges from one process with embedded SQLite (Bifrost, New API) to a Kubernetes cluster running Envoy Gateway (Agent Router).
  • Project health varies sharply: Kong’s open-source repository last shipped a release in June 2026, while TensorZero’s repository is now archived and is not ranked.

A self-hosted LLM gateway is a proxy that runs inside your own network, takes requests from applications in one format, and forwards them to model providers or to your own inference servers. It holds the provider keys, applies rate limits and budgets, retries failed calls, and logs what went where. Plenty of products now call themselves an open source AI gateway. This comparison is narrower than a general gateway list: it reads each project’s LICENSE file, marks where the free edition stops and the paid one starts, lists what each gateway needs to run, and records project health from GitHub as fetched on 5 October 2026. The criteria come first, so a reader who weights them differently can re-rank the list.

What “open source” means in this list

Three licenses appear in the ten repositories, and they impose different obligations.

  • Apache 2.0 is a permissive license. You may use, modify and redistribute the code, including in commercial products, provided you keep the copyright and license notices and state significant changes. It also includes an explicit patent grant from contributors.
  • MIT is shorter and also permissive. It asks only that the copyright notice and license text travel with the code.
  • AGPLv3 (the GNU Affero General Public License) is a copyleft license. If you modify the software and let users interact with it over a network, you must offer them the modified source. That clause is what separates it from the ordinary GPL.

A license at the top of the repository does not settle the question. Many AI gateways are open core: the core is under an open license, and a set of features is sold separately, either as a commercial directory in the same repository or as a separate enterprise build. The practical question for a buyer is where that boundary falls relative to the controls they need. The same reading habit applies to model weights, as the Frontier Wire map of open-weight licensing shows: the headline label and the clauses often differ.

This list only includes projects whose gateway code is published and can be self-hosted. Managed services are excluded. For a broader list that includes hosted gateways, see the sibling piece on the best AI gateways in 2026.

Evaluation criteria

The criteria below are weighted toward teams that will operate the gateway themselves. License and the open-core boundary come first because they decide what you can legally and practically run without a contract.

CriterionWhat was checkedWhy it matters for self-hosting
LicenseThe LICENSE file and any NOTICE or directory carve-outsDecides commercial use, redistribution and copyleft duties
Open-core boundaryFeatures the vendor documents as enterprise or paidGovernance controls are often the paid part
Language and runtimePrimary language, proxy engine (Envoy, OpenResty, native)Shapes performance, extension model and who can debug it
Deployment footprintRequired databases, caches, control planes, KubernetesEvery dependency is another system to patch and back up
LLM gateway features in the free editionUnified API, fallbacks, rate limits, budgets, caching, MCPThe reason to deploy a gateway at all
Project healthLatest release, releases since 5 April 2026, stewardIndicates whether fixes and provider updates will keep coming
Operational effortConfig model, upgrade path, components to runThe cost after the first install

GitHub figures were read through the GitHub API on 5 October 2026. Contributor counts are the API’s count, which includes commit authors without GitHub accounts. Release counts include every published GitHub release, which inflates the figure for repositories that tag each sub-module separately.

The ten gateways at a glance

RankGatewayLicenseLanguage and engineMinimum footprintPaid tier
1BifrostApache 2.0Go, native binaryOne process, embedded SQLiteBifrost Enterprise
2LiteLLMMIT, enterprise directory commercialPython SDK and proxy, “Rust core”Proxy plus PostgreSQL; Redis when scaled outLiteLLM Enterprise
3KuadrantApache 2.0Go operator on Istio or Envoy GatewayKubernetes with a Gateway API providerRed Hat Connectivity Link (separate product)
4Agent RouterApache 2.0Go control plane on EnvoyKubernetes 1.32+ and Envoy Gateway 1.8.1+None documented
5Apache APISIXApache 2.0Lua on OpenResty (NGINX)APISIX plus etcd, or standalone file modeNone on the AI gateway page
6HigressApache 2.0Go control plane, Envoy, Wasm pluginsOne all-in-one container for developmentNot covered
7Kong GatewayApache 2.0Lua on OpenResty (NGINX)DB-less or PostgreSQLKong AI Gateway Enterprise
8PlanoApache 2.0Rust and Envoy, plus routing modelsNative binary or one containerHosted routing models
9New APIAGPLv3 plus Section 7 termsGo backend, React consoleOne container with SQLiteCommercial license on request
10vLLM Semantic RouterApache 2.0Go, sits beside EnvoyDocker stack with dashboardNone documented

The ranking rewards a clean license, governance features in the free edition, a small footprint and steady releases. A team that already runs Envoy, NGINX-based gateways or Istio would reasonably move Agent Router, APISIX, Kong or Higress up, because consolidating on an existing proxy saves more operational effort than any single feature.

Project health in October 2026

GatewayRepositoryLatest releaseReleases since 5 Apr 2026Steward
Bifrostmaximhq/bifrosttransports v2.2.5, 2 Oct 2026100+ (per-module tags)Maxim AI
LiteLLMBerriAI/litellmv1.104.0, 3 Oct 2026100+BerriAI
KuadrantKuadrant/kuadrant-operatorv1.5.3, 3 Sep 202621 (8 stable)CNCF sandbox
Agent Routertheagentrouter/agent-routerv1.1.0, 21 Aug 20266Agentic AI Foundation
Apache APISIXapache/apisix3.19.0, 28 Sep 20264Apache Software Foundation
Higresshigress-group/higressv2.2.5, 4 Oct 20265CNCF sandbox
Kong GatewayKong/kong3.9.3, 17 Jun 20262Kong Inc.
Planokatanemo/plano0.4.37, 28 Sep 202619Katanemo
New APIQuantumNous/new-apiv1.0.0-rc.41, 30 Sep 202661QuantumNous
vLLM Semantic Routervllm-project/semantic-routerv0.4.0, 27 Sep 20262vLLM project

The most useful signals are the date of the last release and who controls the project. Four of the ten sit in a foundation (ASF, CNCF, Agentic AI Foundation), which makes a sudden license change harder. Five are run by a single company, which can move faster but can also change course, and Semantic Router sits under the vLLM project.

General-purpose LLM gateways

These two are built as standalone LLM gateways first, with a unified API, provider keys, budgets and fallbacks as the core product rather than plugins on a general proxy.

1. Bifrost

Bifrost is an AI gateway written in Go by Maxim AI, published on GitHub under Apache 2.0 with no directory carve-outs in the license file. It exposes one OpenAI-compatible API across more than 20 providers and runs as a single binary.

License and paid tier. The repository is Apache 2.0 throughout. The Bifrost LLM gateway page states that the open-source version is free and that adaptive load balancing, clustering, guardrails, RBAC, SSO, audit logs and in-VPC deployment need an enterprise license. The enterprise overview adds log exports to object storage and data warehouses, directory sync through OIDC providers, and custom Go plugins to that list.

Footprint. The setup guide starts the gateway with npx -y @maximhq/bifrost or docker run -p 8080:8080 maximhq/bifrost. Configuration and logs live in SQLite by default; PostgreSQL 16 or later is the option for production, and a file-only mode turns the config store off entirely. The Helm guide recommends PostgreSQL with three or more replicas and autoscaling for high availability.

Free-edition features. Virtual keys carry their own budgets (resetting from one minute to one year), token and request rate limits, and model allow and deny lists, and roll up into teams and customers. The README lists provider fallbacks, key-level load balancing, semantic caching, an MCP gateway, Prometheus metrics and tracing in the open-source build. Budgets and virtual keys are covered in more depth on the Bifrost AI governance page.

Performance. Bifrost’s benchmark documentation reports 11 µs of added overhead per request at 5,000 requests per second on an AWS t3.xlarge.

Enterprise tier: SSO, RBAC, audit logs, guardrails and clustering are part of Bifrost Enterprise, which uses the same configuration schema as the open-source build.

Best for: teams that want a standalone, self-hosted LLM gateway with budgets and fallbacks in the free edition and no mandatory database.

2. LiteLLM

LiteLLM is one of the most widely adopted projects in this list. It ships a Python SDK that runs inside an application and a proxy server that adds virtual keys, spend tracking, load balancing and an admin dashboard. The README now describes it as having a “Rust core with Python SDK”.

License and paid tier. The license file places everything under MIT except the enterprise/ directory, which has its own license. The enterprise page lists SSO for the admin UI beyond five users, JWT authentication, audit logs, RBAC with organizations, IP allowlists, key rotation, secret-manager integrations and per-team logging, with pricing that “depends on your deployment size”.

Footprint. The production guide asks for one Uvicorn worker per pod with 1 vCPU and 4 GiB of memory, PostgreSQL as the only production database, Redis 7.0 or later when running more than one instance, and worker recycling to bound memory growth. Docker images, Helm charts and Terraform modules are published.

Free-edition features. Unified API for more than 100 providers, virtual keys with spend tracking, load balancing, Redis-backed response caching, guardrails and MCP integration. The README cites “8ms P95 latency at 1k RPS”, a vendor figure.

Limits: the PostgreSQL and Redis tiers add operational weight, and the March 2026 supply chain incident, when versions 1.82.7 and 1.82.8 on PyPI carried a credential stealer, is a reminder to pin versions. The official proxy Docker image was not affected. The Frontier Wire review of LiteLLM alternatives covers both issues in detail.

Best for: teams that need the broadest provider coverage and are comfortable running a database-backed Python service.

Kubernetes-native AI gateways

The next two treat the Kubernetes Gateway API as the configuration surface. They suit platform teams that already manage ingress through custom resources.

3. Kuadrant

Kuadrant is a Go operator that adds policy to existing Kubernetes gateways. Its README says it “leverages Gateway API and Policy Attachment to enhance gateway providers like Istio and Envoy Gateway.” The project was originally created by Red Hat and is now a CNCF sandbox project.

License and paid tier. Apache 2.0, in both the operator and the MCP gateway repositories. Red Hat sells Connectivity Link, a commercial product its page describes as unifying “AI gateway, API management, multicluster and multicloud connectivity, and global load balancing,” with Red Hat support and OpenShift integration.

Footprint. A Kubernetes cluster with Istio or Envoy Gateway as the Gateway API provider, installed through Helm or OLM. Enforcement runs in a Wasm module inside Envoy, with Authorino handling authentication and Limitador handling rate limits.

Free-edition features. TokenRateLimitPolicy, introduced in v1.3.0 in October 2025, “enables token-based rate limiting for AI/LLM workloads.” It reads token counts from the responses of OpenAI-compatible servers, Azure OpenAI, Gemini and Bedrock, with limits per user or per tier. AuthPolicy covers API keys, JWT, Kubernetes tokens and x509 certificates, and token usage is exported as Prometheus metrics. A separate MCP gateway, which aggregates MCP servers behind one Envoy-based endpoint, reached v1.0.0 on 25 September 2026, and the v1.6 release candidates bundle it into the operator.

Limits: Kuadrant is a policy layer rather than a full LLM gateway. It has no unified provider API, request translation or cross-provider fallback, so routing comes from the underlying HTTPRoutes. The token policy API is still v1alpha1, and Kubernetes with a Gateway API provider is mandatory.

Best for: platform teams on Istio or Envoy Gateway that want token quotas and authentication for model traffic expressed as Gateway API policies.

4. Agent Router

Agent Router is the new name of Envoy AI Gateway. According to the project announcement, it left the CNCF Envoy project on 10 September 2026 to become a standalone project in the Agentic AI Foundation, with “same code, same maintainers”. CRDs, API groups, CLI names, container images and Helm charts keep their old names.

License and paid tier. Apache 2.0. The README does not mention a commercial edition.

Footprint. This is the heaviest install in the list. The prerequisites page requires Kubernetes 1.32 or later, Envoy Gateway 1.8.1 or later, kubectl and Helm, and recommends a fresh cluster. Rate limiting is installed as an optional add-on with its own values file. A standalone aigw run command exists for local use.

Free-edition features. The README describes an OpenAI-compatible API for hosted providers and self-hosted inference, token-based rate limiting, provider fallback and MCP integration, with credentials and quotas managed by the platform team.

Limits: six releases in six months, the rename means older guides and search results use the Envoy name, and the Kubernetes dependency rules it out for small teams.

Best for: platform teams already running Envoy Gateway who want AI traffic expressed as Kubernetes resources.

API gateways with AI plugins

APISIX, Higress and Kong began as general API gateways and added AI features as plugins. Their strength is consolidation: one proxy for REST APIs and model traffic. The trade-offs between the two kinds of product are covered in the explainer on LLM gateways versus API gateways.

5. Apache APISIX

APISIX is an Apache Software Foundation project written in Lua on OpenResty, the NGINX distribution with an embedded Lua runtime. It is the most active foundation-governed API gateway here, with 519 contributors and a 3.19.0 release on 28 September 2026.

License and paid tier. Apache 2.0. The AI gateway page describes only the open-source project.

Footprint. In its traditional and decoupled modes, APISIX uses etcd as its configuration store. The installation guide also documents a standalone file-driven mode that reads YAML or JSON from disk and needs no etcd, and warns that the example etcd provisioned by Docker and Helm installs is not a production design.

Free-edition features. Seven AI plugins: ai-proxy, ai-proxy-multi for load balancing and semantic routing across model instances, ai-rate-limiting for token quotas, ai-prompt-guard, ai-cache with Redis-backed exact and semantic caching, ai-rag, and ai-lakera-guard.

Limits: the AI gateway page does not mention MCP, the etcd cluster is a real operational cost in traditional mode, and there are no LLM-specific virtual keys or hierarchical budgets.

Best for: teams that want a foundation-governed gateway for both APIs and models with no paid tier in sight.

6. Higress

Higress originated at Alibaba and is now a CNCF sandbox project. It is built on Istio and Envoy, with a Go control plane and plugins compiled to WebAssembly (Wasm) from Go, Rust or JavaScript.

License and paid tier. Apache 2.0. A commercial edition was not covered for this article.

Footprint. The README starts an all-in-one container with one docker run command that opens a UI console on port 8001 and gateway ports 8080 and 8443. Production installs use Helm on Kubernetes, and a standalone mode outside Kubernetes is documented.

Free-edition features. Multi-model load balancing, token-based rate limiting, response caching, observability and hosting of MCP servers through its plugin system. Configuration changes take effect without dropping long-lived connections, which matters for streaming responses.

Limits: AI capability depends on which Wasm plugins you enable and keep current, and the Istio heritage means more moving parts than a single-binary gateway.

Best for: teams on Istio or Envoy who want AI features as Wasm plugins and a console out of the box.

7. Kong Gateway

Kong Gateway is a widely deployed API gateway written in Lua on OpenResty. Its README now calls it an “API, LLM and MCP gateway”.

License and paid tier. The repository is Apache 2.0, and its plugin directory contains six AI plugins: ai-proxy, ai-prompt-decorator, ai-prompt-guard, ai-prompt-template, ai-request-transformer and ai-response-transformer. The AI Proxy plugin supports more than 15 providers. AI Proxy Advanced, which adds weighted, lowest-latency, lowest-usage and semantic load balancing, circuit breakers and priority failover, is documented as “only available as part of our AI Gateway Enterprise offering”.

Footprint. Kong runs in DB-less mode with declarative configuration or with PostgreSQL, and has an official Kubernetes ingress controller.

Project health. This is the main concern. The most recent GitHub releases are 3.9.2 and 3.9.3 from June 2026. A community discussion asking for an open-source 3.10 image has no official reply from Kong maintainers, while the enterprise documentation already refers to 3.10 features.

Limits: the useful AI routing features are enterprise-only, and the open-source release line appears to have stalled at 3.9.

Best for: existing Kong users who want basic AI proxying and prompt guards on a gateway they already operate.

Routing layers and key hubs

The last three are open-source and self-hostable, but each is a narrower tool than the gateways above.

8. Plano

Plano, from Katanemo, was previously called archgw (the old repository name redirects to it). It is an Envoy-based proxy for agentic applications, and its repository is mostly Rust: it routes between agents and between models, applies guardrail filters, and emits OpenTelemetry traces.

License and paid tier. Apache 2.0. The distinctive part is its use of small routing models, such as a 4-billion-parameter orchestrator. The README says these are “hosted free of charge in the US-central region” for a first run, and that production users should run the models locally or ask the company for API keys.

Footprint. The deployment docs describe a native mode (planoai up plano_config.yaml), a Docker Compose mode and a single-container Kubernetes deployment. Fully self-hosting also means serving the routing models yourself.

Limits: 43 contributors, the smallest base here, and a default that sends routing decisions to a hosted model until you change it.

Best for: teams building multi-agent applications who want routing by intent rather than by fixed model name.

9. New API

New API is a Go and React fork of One API, built as a model hub for aggregating providers and redistributing access through keys. It converts between OpenAI, Claude and Gemini request formats and ships a web console with a setup wizard.

License. AGPLv3, with additional terms under Section 7 in its NOTICE file: modified versions that present a user interface must keep the line “Frontend design and development by New API contributors” and a visible link to the original repository. The README offers a separate commercial license for organizations that cannot accept AGPL obligations.

Footprint. One container with SQLite to start. The README lists MySQL 5.7.8+ or PostgreSQL 9.6+ for production, optional Redis for shared rate limits across nodes, and optional ClickHouse for logs.

Limits: every release in the past six months is a v1.0.0 release candidate, the copyleft terms need legal review before modification, and the README devotes space to the regulatory duties of operators reselling API access, which signals the main audience.

Best for: teams that want a self-hosted key-distribution hub with a web console and are comfortable with AGPL.

10. vLLM Semantic Router

vLLM Semantic Router is a routing layer from the vLLM project that chooses a model per request based on signals such as intent, difficulty, modality, risk and user preference. It is Apache 2.0 and written mostly in Go.

What it is not. Its introduction is explicit: it “does not replace the gateway or the model servers. Envoy continues to carry traffic.” It ranks last for that reason. It complements a gateway rather than standing in for one.

Footprint. The installation guide needs Python 3.10+, Docker (or Podman on Linux), and a curl installer that starts the stack, with a dashboard on port 8700. Kubernetes support is through an operator.

Limits: two releases in six months, and no governance features of its own.

Best for: teams running several self-hosted models on vLLM who want quality and cost routing between them.

Operational effort compared

Footprint is where self-hosting costs show up. The table counts the systems you must run, not the features you might enable.

GatewaySmallest production shapeConfig modelExtra systems at scale
BifrostBinary or container with SQLiteWeb UI, API or config.jsonPostgreSQL for multi-replica HA
LiteLLMProxy pods plus PostgreSQLYAML plus databaseRedis, connection pooling, worker recycling
KuadrantKubernetes with Istio or Envoy GatewayPolicy CRDs attached to Gateway API resourcesAuthorino and Limitador components
Agent RouterKubernetes with Envoy GatewayCRDsRate-limit add-on
Apache APISIXAPISIX plus etcd, or file modeAdmin API or YAMLProduction etcd cluster, Redis for AI cache
HigressHelm on KubernetesConsole, Ingress or Gateway APIIstio-style control plane
Kong GatewayDB-less nodeDeclarative YAML or Admin APIPostgreSQL for DB mode
PlanoNative binary or containerYAMLGPU serving for routing models
New APIContainer with SQLiteWeb consoleMySQL or PostgreSQL, Redis, ClickHouse
vLLM Semantic RouterDocker stackDashboard and configAn Envoy-based gateway in front

Two patterns stand out. Gateways that embed SQLite or read a config file (Bifrost, New API, Kong in DB-less mode) are fastest to stand up and easiest to back up. Gateways that depend on Kubernetes controllers (Agent Router, Higress, Kuadrant) cost more to install but fit teams whose change process already runs through GitOps. Whichever shape you pick, plan failover across providers from day one; the guide to LLM failover and load balancing covers the patterns.

Projects considered but not ranked

Several projects that appear in other open-source gateway lists did not make this one, each for a stated reason.

  • TensorZero. Its GitHub repository is marked archived (read-only), and its last release, 2026.6.0, is dated 4 June 2026. An archived repository receives no fixes, which rules it out for new deployments.
  • One API. The MIT-licensed project that New API forked from has had no release since v0.6.10 in February 2025, and its repository has no commits since then.
  • LocalAI. An MIT-licensed engine for running models on local hardware. It serves models rather than governing access to many providers, so it belongs behind a gateway, not in place of one.

Choosing a self-hosted LLM gateway

The right choice depends more on what a team already runs than on feature counts.

  • No existing gateway, want the least to operate: Bifrost. It runs as one process without a database.
  • Need the longest provider list: LiteLLM, accepting PostgreSQL and Redis.
  • Already on Envoy Gateway or Istio: Agent Router, Higress or Kuadrant.
  • Already on an NGINX-based gateway: APISIX, or Kong if you accept that the useful AI routing is paid.
  • Need a key-distribution hub with a web console: New API, after a legal read of AGPL.
  • Routing between self-hosted models by task: vLLM Semantic Router or Plano, behind one of the gateways above.

A good test before committing is to run the shortlisted gateways against your own traffic shape: your payload sizes, your streaming ratio, your provider mix. A survey of open-source LLM gateways for self-hosted deployments covers five of these projects with a deployment-sizing lens and is useful further reading, keeping in mind that it is published by the company behind Bifrost.

Limits of this comparison

No gateway was installed or load-tested for this article. Every statement comes from the project’s license file, README, documentation or release history as read on 5 October 2026. Release data changes daily. Paid-tier boundaries were taken from vendor documentation and can move with any release. The commercial offerings for Higress and APISIX were not reviewed, MCP gateway depth was not compared in detail (the Frontier Wire comparison of MCP gateways does that), and no legal advice is offered on license obligations. A change in Kong’s open-source release policy, a license change at any single-vendor project, or an un-archiving of TensorZero would change this ranking.

Sources

  1. Bifrost source repository (GitHub, Apache 2.0)
  2. Bifrost docs: gateway setup
  3. Bifrost docs: Helm deployment guide
  4. Bifrost docs: benchmarking
  5. Bifrost docs: enterprise overview
  6. Bifrost docs: virtual keys
  7. Bifrost LLM gateway product page
  8. Bifrost AI governance page
  9. LiteLLM source repository and README (GitHub)
  10. LiteLLM license file (MIT, with enterprise directory carve-out)
  11. LiteLLM docs: production best practices
  12. LiteLLM docs: enterprise features
  13. LiteLLM security update: supply chain incident (March 2026)
  14. Apache APISIX source repository (GitHub, Apache 2.0)
  15. Apache APISIX AI gateway
  16. Apache APISIX docs: installation and deployment modes
  17. Kong Gateway source repository and README (GitHub, Apache 2.0)
  18. Kong Gateway open-source AI plugins directory (GitHub)
  19. Kong docs: AI Proxy plugin
  20. Kong docs: AI Proxy Advanced plugin
  21. Kong GitHub discussion #14405: OSS image for 3.10.0
  22. Survey: five open-source LLM gateways for self-hosted deployments

Questions readers ask

What is an open-source AI gateway?

It is a proxy you run on your own infrastructure that sits between applications and model providers. It gives every application one API, usually OpenAI-compatible, and adds provider keys, routing, retries, fallbacks, rate limits, budgets and logging in one place. Open source means the code is published under a license such as Apache 2.0, MIT or AGPL that lets you run and modify it.

Which open-source AI gateway has the fewest dependencies?

Among the ten in this comparison, Bifrost can run as a single process with no external database. Bifrost stores its configuration in embedded SQLite by default, with PostgreSQL optional. New API also starts on SQLite. LiteLLM's production guide asks for PostgreSQL and, with more than one instance, Redis. APISIX in its traditional mode needs etcd, and Agent Router needs Kubernetes and Envoy Gateway.

Are open-source AI gateways free for commercial use?

The license usually allows it, but read the file. Apache 2.0 and MIT permit commercial use with attribution. LiteLLM is MIT except an enterprise directory under a commercial license. New API is AGPLv3 with extra attribution terms, which matters if you modify it and offer it to users over a network. Separately, most projects keep features such as SSO, audit logs or advanced load balancing in a paid edition.

Is Kong Gateway still open source?

The Kong/kong repository remains under Apache 2.0 and contains six AI plugins, including AI Proxy and AI Prompt Guard. Its most recent GitHub releases are 3.9.x patch releases from June 2026, and a community discussion about missing open-source 3.10 images has no official answer from Kong. Advanced AI features such as AI Proxy Advanced are documented as part of the AI Gateway Enterprise offering.

What is the best open-source AI gateway for Kubernetes?

It depends on what else runs in the cluster. Kuadrant and Agent Router both use the Kubernetes Gateway API; Kuadrant adds token-based rate limits and authentication policies to Istio or Envoy Gateway, while Agent Router configures Envoy Gateway and needs Kubernetes 1.32 or later. Higress suits teams already on Istio. Bifrost also ships a Helm chart for teams that want a standalone gateway inside the cluster.

More comparisons