Rank #6 of 7 in Model Gateways & Routers

Kong AI Gateway

Name: Kong AI Gateway
Author: Kong Inc.

Kong Inc. · commercial

konghq.com ↗Try it →

PA Score19/100 AGENT-READY47/100 BUILT-IN AI0/100 API0/100

MCP✓CLI✓API~

no public signals

ArenasModel Gateways & Routers#6/7

Access

Open app ↗API docs ↗CLI docs ↗

Compare head-to-head

vs Cloudflare AI Gateway

vs Requesty

Alternatives to Kong AI Gateway →

Products

Kong, product by product →

Kong ships more than one product — each judged line competes in its own arena on the same stories as everyone else.

Line	Arena	Rank	PA Score	Agent-ready
Kong Gateway & Konnect	API platforms	#2/5	36/100	48/100
AI Gatewaythis page	Model Gateways & Routers	#6/7	19/100	47/100
Insomniaacquired	API platforms	#4/5	34/100	37/100

Not yet judged (9 — no arena where they compete): Kong Mesh · Event Gateway · Ingress Controller & Operator · Dev Portal · Service Catalog & MCP Registry · Kong Identity · decK & kongctl · Metering & Billing · Volcano SDK

Try itExperimental

See what an agent can do with Kong AI Gateway before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$curl -s https://developer.konghq.com/ai-gateway.md | head -8recorded session — replayed, not live

▋

recorded 2026-09-14 · exit 0 · captured verbatim by our probe harness, secrets redacted · pure-HTTP probe — ▶ run live re-runs it from our edge

Verified integrations

No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.

By theme — the product's score on each story themeBy theme

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

29.6/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

15.0/100

Caching performance — stories about caching performance in this arenaCaching performanceevidence →

Stories about caching performance in this arena

55.0/100

Cost controls — stories about cost controls in this arenaCost controlsevidence →

Stories about cost controls in this arena

36.0/100

Key management — stories about key management in this arenaKey managementevidence →

Stories about key management in this arena

33.8/100

Observability — seeing what the system is doing — logs, metrics, traces, alertsObservabilityevidence →

Seeing what the system is doing — logs, metrics, traces, alerts

80.0/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

15.0/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

4.0/100

Routing resilience — stories about routing resilience in this arenaRouting resilienceevidence →

Stories about routing resilience in this arena

31.0/100

Streaming tools — stories about streaming tools in this arenaStreaming toolsevidence →

Stories about streaming tools in this arena

49.7/100

Unified api — stories about unified api in this arenaUnified apievidence →

Stories about unified api in this arena

43.5/100

Story verdicts — every judged story with its evidenceStory verdicts

Sorted by importance (agentic first) (high → low) · 50/50 stories · click a row’s chevron for the rationale and evidence


Connect an agent via an official MCP server G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	3	full	8/10	C claimed
Drive the product through a documented public API G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	3	partial	6/10	T probed
Plug MCP servers into this product so it can use their tools G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	3	partial	6/10	C claimed
Delegate tasks to a built-in AI assistant inside the product G Agentic features	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	3	n/a	untested		none yet
Point an agent at llms.txt or agent-oriented docs G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	full	8/10	T probed
Use an official CLI G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	full	7/10	T probed
Run the product headlessly / in CI for automation G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	partial	6/10	T probed
Issue scoped/least-privilege API credentials for an agent G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	partial	5/10	C claimed
Build against official SDKs G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	none	0/10
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	none	0/10
Explore an interactive API reference with runnable examples G Api quality	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	none	0/10
Get AI-generated insights and suggestions from my data inside the product G Agentic features	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	none	0/10
Operate the product with natural-language commands G Agentic features	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	none	0/10
Rely on versioned APIs with a documented deprecation policy G Api quality	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	none	0/10
Set up automations that run autonomously in the background G Agentic features	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	n/a	untested		none yet
Subscribe to events via webhooks G Agent access	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	2	n/a	untested		none yet
Test against a sandbox environment without touching production data G Api quality	ai-native user	Agenticness — how well agents can access and operate the productAgenticness	1	none	untested		none yet
Call many model providers through one consistent API C One endpoint	developer	Unified api — stories about unified api in this arenaUnified api	3	full	8/10	C claimed
Inspect logged requests and responses with latency, token counts, and cost attached C Logs	platform engineer	Observability — seeing what the system is doing — logs, metrics, traces, alertsObservability	3	full	8/10	C claimed
Stream token-by-token responses through the gateway from any provider C Streaming	developer	Streaming tools — stories about streaming tools in this arenaStreaming tools	3	full	8/10	C claimed
Track spend per model, key, team, or user across all providers in one place C Spend tracking	platform engineer	Cost controls — stories about cost controls in this arenaCost controls	3	partial	7/10	C claimed
Make tool and function calls across different providers with a consistent schema C Tool calling	developer	Streaming tools — stories about streaming tools in this arenaStreaming tools	3	partial	6/10	C claimed
Mint gateway-managed keys for teams and apps without exposing raw provider keys C Virtual keys	platform engineer	Key management — stories about key management in this arenaKey management	3	partial	6/10	C claimed
Point existing OpenAI-compatible code at the gateway by changing only the base URL and key C Compatibility	developer	Unified api — stories about unified api in this arenaUnified api	3	partial	6/10	C claimed
Configure automatic fallback to another model or provider when one fails C Fallbacks	platform engineer	Routing resilience — stories about routing resilience in this arenaRouting resilience	3	partial	5/10	C claimed
Define rules that trigger actions automatically on events G	ai-native user	Automation depth — how much of the product can run unattendedAutomation depth	3	partial	5/10	C claimed
My agent can switch models mid-task by policy — cost, capability, or availability — through gateway routing rules C Policy routing	ai-native user	Routing resilience — stories about routing resilience in this arenaRouting resilience	3	partial	5/10	C claimed
Provision gateways, keys, and budgets programmatically through an admin API C Programmatic admin	ai-native user	Key management — stories about key management in this arenaKey management	3	partial	5/10	C claimed
Self-host the core product G	ai-native user	Openness — open source, data portability, and self-hosting storiesOpenness	3	partial	5/10	C claimed
Set hard budgets and spend limits per key, team, or user C Budgets	platform engineer	Cost controls — stories about cost controls in this arenaCost controls	3	partial	5/10	C claimed
Export all of my data in open formats and leave G	ai-native user	Openness — open source, data portability, and self-hosting storiesOpenness	3	none	0/10
Prevent my data from being used to train AI models G	ai-native user	Privacy posture — data-handling and privacy storiesPrivacy posture	3	none	untested		none yet
Cache responses at the gateway to cut cost and latency on repeated requests C Caching	developer	Caching performance — stories about caching performance in this arenaCaching performance	2	full	8/10	C claimed
Bring my own provider API keys and have the gateway use them for my traffic G Byok	developer	Key management — stories about key management in this arenaKey management	2	partial	6/10	C claimed
Give an autonomous agent its own key with budget and rate guardrails so it cannot run away on spend C Agent guardrails	ai-native user	Cost controls — stories about cost controls in this arenaCost controls	2	partial	6/10	C claimed
Load-balance traffic across providers, deployments, or keys by weight, latency, or cost C Load balancing	platform engineer	Routing resilience — stories about routing resilience in this arenaRouting resilience	2	partial	6/10	C claimed
Smooth provider rate limits by spreading traffic across keys and queuing or throttling requests C Rate limits	platform engineer	Routing resilience — stories about routing resilience in this arenaRouting resilience	2	partial	6/10	C claimed
Do everything through the API that I can do in the UI G	ai-native user	Openness — open source, data portability, and self-hosting storiesOpenness	2	partial	5/10	T probed
Run traffic through gateway infrastructure that adds minimal latency overhead to provider calls C Latency	platform engineer	Caching performance — stories about caching performance in this arenaCaching performance	2	partial	5/10	C claimed
Set automatic retry policies for transient provider errors C Retries	platform engineer	Routing resilience — stories about routing resilience in this arenaRouting resilience	2	partial	4/10	C claimed
Choose where my data is stored (region/residency) G	ai-native user	Privacy posture — data-handling and privacy storiesPrivacy posture	2	partial	3/10	C claimed
Browse or query a catalog of available models with pricing and context-window metadata G Catalog	developer	Unified api — stories about unified api in this arenaUnified api	2	none	0/10
Control data retention and deletion G	ai-native user	Privacy posture — data-handling and privacy storiesPrivacy posture	2	none	0/10
Perform bulk operations across many items at once G	ai-native user	Automation depth — how much of the product can run unattendedAutomation depth	2	none	0/10
Opt out of telemetry and usage tracking G	ai-native user	Privacy posture — data-handling and privacy storiesPrivacy posture	2	none	untested		none yet
Read the product's source under an open license G	ai-native user	Openness — open source, data portability, and self-hosting storiesOpenness	2	none	untested		none yet
Schedule recurring jobs or workflows G	ai-native user	Automation depth — how much of the product can run unattendedAutomation depth	2	n/a	untested		none yet
Export gateway logs and traces to my own observability stack G Integrations	developer	Observability — seeing what the system is doing — logs, metrics, traces, alertsObservability	1	full	8/10	C claimed
Version, review, and roll back my automations G	ai-native user	Automation depth — how much of the product can run unattendedAutomation depth	1	none	0/10
Request structured JSON-schema outputs across providers C Tool calling	developer	Streaming tools — stories about streaming tools in this arenaStreaming tools	1	none	untested		none yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 38 stories with headroom

What would move Kong AI Gateway’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave
nonemoves PA Scoreimpact 30
Kong AI Gateway/Konnect is a SaaS-hosted control plane with configuration, logs, and analytics data, so data portability/export-and-leave is a fair axis to ask, but the evidence pack contains no mention of a bulk data export feature, open-format export of configs/logs/analytics, or a documented migration-out path in open standards.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
Kong AI Gateway is an enterprise routing/governance layer for LLM traffic, so control over how provider data is used is a fair question, but the evidence pack contains no mention of training-data opt-out, zero-retention guarantees, or contractual terms preventing model providers from using proxied data for training — only general DLP/PII redaction and content-safety features are documented, which don't address this specific claim.
Agenticness — how well agents can access and operate the productGet AI-generated insights and suggestions from my data inside the product
nonemoves Built-in AIimpact 30
Kong AI Gateway provides usage analytics, logs, and cost/latency metrics (docs-3, docs-9, docs-10), but these are raw operational metrics/dashboards, not AI-generated insights or suggestions derived from the user's own data.
Agenticness — how well agents can access and operate the productOperate the product with natural-language commands
nonemoves Built-in AIimpact 30
Kong AI Gateway's documentation covers proxying LLM/CLI/A2A/MCP traffic, observability, and cost tracking, but there is no evidence that the gateway itself can be configured or operated via natural-language commands (its control plane relies on kongctl CLI and declarative config, not NL commands).
Agenticness — how well agents can access and operate the productBuild against official SDKs
nonemoves agent-readyimpact 30
The evidence pack contains no mention of official SDKs for building against Kong AI Gateway (only a CLI 'kongctl' and REST API references), and probes explicitly show no OpenAPI/SDK artifacts (404s for openapi.json, swagger.json, etc.).
Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples
nonemoves API qualityimpact 30
Evidence shows Kong publishes API reference content (e.g., list-ai-gateways endpoint docs) but there is no indication of an interactive reference with runnable/try-it-out examples; probes for OpenAPI/swagger specs on the docs site all returned 404, suggesting no such interactive tooling is exposed.
Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)
nonemoves API qualityimpact 30
Evidence includes API reference pages (e.g.
Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy
nonemoves API qualityimpact 30
The evidence shows an API reference exists (e.g., 'v1' Konnect AI Gateway API) but there is no documentation of a versioning scheme or deprecation policy for the AI Gateway APIs, and OpenAPI spec probes returned 404s.

Showing the top 8 of 38 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map7 surfaces · 30 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

AI gateway docs29 stories

Point an agent at llms.txt or agent-oriented docs
Run the product headlessly / in CI for automation
Plug MCP servers into this product so it can use their tools
Connect an agent via an official MCP server
Use an official CLI
Issue scoped/least-privilege API credentials for an agent
Define rules that trigger actions automatically on events
Cache responses at the gateway to cut cost and latency on repeated requests
Run traffic through gateway infrastructure that adds minimal latency overhead to provider calls
Give an autonomous agent its own key with budget and rate guardrails so it cannot run away on spend
Set hard budgets and spend limits per key, team, or user
Track spend per model, key, team, or user across all providers in one place
Bring my own provider API keys and have the gateway use them for my traffic
Provision gateways, keys, and budgets programmatically through an admin API
Mint gateway-managed keys for teams and apps without exposing raw provider keys
Export gateway logs and traces to my own observability stack
Inspect logged requests and responses with latency, token counts, and cost attached
Do everything through the API that I can do in the UI
Self-host the core product
Choose where my data is stored (region/residency)
Configure automatic fallback to another model or provider when one fails
Load-balance traffic across providers, deployments, or keys by weight, latency, or cost
My agent can switch models mid-task by policy — cost, capability, or availability — through gateway routing rules
Smooth provider rate limits by spreading traffic across keys and queuing or throttling requests
Set automatic retry policies for transient provider errors
Stream token-by-token responses through the gateway from any provider
Make tool and function calls across different providers with a consistent schema
Point existing OpenAI-compatible code at the gateway by changing only the base URL and key
Call many model providers through one consistent API

Plugins docs6 stories

Define rules that trigger actions automatically on events
Cache responses at the gateway to cut cost and latency on repeated requests
Run traffic through gateway infrastructure that adds minimal latency overhead to provider calls
Give an autonomous agent its own key with budget and rate guardrails so it cannot run away on spend
Set hard budgets and spend limits per key, team, or user
Smooth provider rate limits by spreading traffic across keys and queuing or throttling requests

Kongctl docs4 stories

Run the product headlessly / in CI for automation
Use an official CLI
Drive the product through a documented public API
Do everything through the API that I can do in the UI

API reference4 stories

Run the product headlessly / in CI for automation
Drive the product through a documented public API
Provision gateways, keys, and budgets programmatically through an admin API
Do everything through the API that I can do in the UI

Products docs3 stories

Plug MCP servers into this product so it can use their tools
Connect an agent via an official MCP server
Make tool and function calls across different providers with a consistent schema

OpenAPI spec2 stories

Drive the product through a documented public API
Do everything through the API that I can do in the UI

llms.txt1 story

Point an agent at llms.txt or agent-oriented docs

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$curl -s https://developer.konghq.com/ai-gateway.md | head -8reproduced

$ curl -s https://developer.konghq.com/ai-gateway.md | head -8
---
title: "Kong AI Gateway"
description: This page is an introduction to AI Gateway.
url: "/ai-gateway/"
canonical_url: "/ai-gateway/"
content_type: landing_page
min_version:
  ai-gateway: '2.0'

proves: Point an agent at llms.txt or agent-oriented docsrecorded 2026-09-14

$curl -s https://developer.konghq.com/llms.txt | grep -A 4 '## AI Gateway'reproduced

$ curl -s https://developer.konghq.com/llms.txt | grep -A 4 '## AI Gateway'
## AI Gateway

- [Kong AI Gateway](https://developer.konghq.com/ai-gateway.md): This page is an introduction to AI Gateway.
- [A2A Traffic Gateway](https://developer.konghq.com/ai-gateway/a2a.md): Observe Agent-to-Agent (A2A) protocol traffic through AI Gateway.
- [AI Gateway audit log reference](https://developer.konghq.com/ai-gateway/ai-audit-log-reference.md): AI Gateway provides a standardized logging format for AI Policies, enabling the emission of analytics events and facilitating the aggregation of AI usage analytics across various providers.
--
## AI Gateway Policies

- [ACL Policy](https://developer.konghq.com/ai-gateway/policies/acl.md): Control which AI Consumers and AI Consumer Groups can access entities
- [ACL Policy Configuration Reference](https://developer.konghq.com/ai-gateway/policies/acl/reference.md): Control which AI Consumers and AI Consumer Groups can access entities
- [ACME Policy Configuration Reference](https://developer.konghq.com/ai-gateway/policies/acme/reference.md): Let's Encrypt and ACMEv2 integration with Kong AI Gateway

proves: Point an agent at llms.txt or agent-oriented docsrecorded 2026-09-14

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

1 of 13 testable claims verified · 0 contradicted → integrity 8/100

24 distinct capability claims found in Kong AI Gateway’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

Verified

Unverified

Contradicted

Undersold

Verified (1)

“kongctl CLI includes an AI Gateway conversion extension to migrate existing configurations”
Use an official CLI full proof ↗

Unverified (13)

“Serves AI models from many providers through one provider-agnostic API”
Call many model providers through one consistent API full proof ↗
“Logs and analytics capture request/response payloads, token usage, model details, latency, and cost”
Inspect logged requests and responses with latency, token counts, and cost attached full proof ↗
“Calculates exact per-request LLM cost matching what the provider actually bills”
Track spend per model, key, team, or user across all providers in one place partial proof ↗
“Proxies traffic from AI command-line tools to LLM providers, centralizing logging, cost tracking, and rate limiting”
Track spend per model, key, team, or user across all providers in one place partial proof ↗
“Performs semantic caching, routing, and content filtering using semantic similarity queries”
Cache responses at the gateway to cut cost and latency on repeated requests full proof ↗
“Provides an advanced rate-limiting plugin specifically for AI/LLM traffic”
Smooth provider rate limits by spreading traffic across keys and queuing or throttling requests partial proof ↗
“AI MCP Server entity turns any REST API into an MCP server/tool without requiring an LLM”
Connect an agent via an official MCP server full proof ↗
“AI MCP Proxy can front and expose existing upstream MCP servers through the gateway”
Plug MCP servers into this product so it can use their tools partial proof ↗
“Admin API endpoint to list all AI Gateways in an organization”
Provision gateways, keys, and budgets programmatically through an admin API partial proof ↗
“Streams LLM responses token-by-token back to clients in real time”
Stream token-by-token responses through the gateway from any provider full proof ↗
“Load balances requests across multiple LLM models”
Load-balance traffic across providers, deployments, or keys by weight, latency, or cost partial proof ↗
“AI Vault entity lets providers, auth strategies, agents, and MCP servers reference secrets from external backends like AWS Secrets Manager or HashiCorp Vault”
Bring my own provider API keys and have the gateway use them for my traffic partial proof ↗
“Exports OpenTelemetry (OTLP) metrics for generative AI, MCP, and A2A traffic”
Export gateway logs and traces to my own observability stack full proof ↗

Undersold (17)

Point an agent at llms.txt or agent-oriented docs full proof ↗
Run the product headlessly / in CI for automation partial proof ↗
Drive the product through a documented public API partial proof ↗
Issue scoped/least-privilege API credentials for an agent partial proof ↗
Define rules that trigger actions automatically on events partial proof ↗
Run traffic through gateway infrastructure that adds minimal latency overhead to provider calls partial proof ↗
Give an autonomous agent its own key with budget and rate guardrails so it cannot run away on spend partial proof ↗
Set hard budgets and spend limits per key, team, or user partial proof ↗
Mint gateway-managed keys for teams and apps without exposing raw provider keys partial proof ↗
Do everything through the API that I can do in the UI partial proof ↗
Self-host the core product partial proof ↗
Choose where my data is stored (region/residency)partial proof ↗
Configure automatic fallback to another model or provider when one fails partial proof ↗
My agent can switch models mid-task by policy — cost, capability, or availability — through gateway routing rules partial proof ↗
Set automatic retry policies for transient provider errors partial proof ↗
Make tool and function calls across different providers with a consistent schema partial proof ↗
Point existing OpenAI-compatible code at the gateway by changing only the base URL and key partial proof ↗

Claims outside our story set (10)

Real capability claims found in Kong AI Gateway’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

“Quickstart script spins up a demo AI Gateway instance almost instantly”
source ↗
“Supports Azure Managed Identity / User-Assigned Identity for provider authentication when running on Azure”
source ↗
“Acts as a control and observability layer for agent-to-agent (A2A) traffic, routing requests and rewriting agent card URLs”
source ↗
“AI Auth Strategy can authenticate A2A clients on AI Agent entities, with size-limiting policies for agent traffic”
source ↗
“Provides content safety features and Prompt Guards on chat/completion requests across providers”
source ↗
“Single gateway can govern LLM, MCP, and A2A traffic together”
source ↗
“Authenticates enterprise users via existing identity providers (Okta, Azure AD, Google, OIDC) without manual key management”
source ↗
“Same AI capabilities can be configured via plugins attached to Services and Routes”
source ↗
“Supports AWS Guardrails to validate requests and responses before forwarding to/from upstream LLMs”
source ↗
“Applies safety and DLP policies to block toxic content and strip personally identifiable information”
source ↗

Suggest a story for these →

Business model

open-sourceusage-basedenterprise-custom

The core AI Proxy plugin ships free in open-source Kong Gateway; advanced routing, semantic caching, and LLM analytics are Enterprise features, and Konnect Plus meters AI Gateway usage per LLM model.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Scoretracked since Sep 14 '26 — no movement recorded yet

Agent-readytracked since Sep 14 '26 — no movement recorded yet

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown /llms.txt

Data

Evidence (JSON)Verdicts (JSON)

Kong AI Gateway

Products

Try itExperimental

Verified integrations

By theme — the product's score on each story themeBy theme

Story verdicts — every judged story with its evidenceStory verdicts

🤖Agenticness — how well agents can access and operate the productAgenticness

⚙️Automation depth — how much of the product can run unattendedAutomation depth

⚡Caching performance — stories about caching performance in this arenaCaching performance

💲Cost controls — stories about cost controls in this arenaCost controls

🔑Key management — stories about key management in this arenaKey management

📡Observability — seeing what the system is doing — logs, metrics, traces, alertsObservability

🔓Openness — open source, data portability, and self-hosting storiesOpenness

🔒Privacy posture — data-handling and privacy storiesPrivacy posture

🔌Routing resilience — stories about routing resilience in this arenaRouting resilience

🔁Streaming tools — stories about streaming tools in this arenaStreaming tools

🔌Unified api — stories about unified api in this arenaUnified api

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 38 stories with headroom

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map7 surfaces · 30 covered stories

Probe proofs — replayable recordings from the probe harnessProbe proofs

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

Business model

Score trend

Agenticness — how well agents can access and operate the productAgenticness

Automation depth — how much of the product can run unattendedAutomation depth

Caching performance — stories about caching performance in this arenaCaching performance

Cost controls — stories about cost controls in this arenaCost controls

Key management — stories about key management in this arenaKey management

Observability — seeing what the system is doing — logs, metrics, traces, alertsObservability

Openness — open source, data portability, and self-hosting storiesOpenness

Privacy posture — data-handling and privacy storiesPrivacy posture

Routing resilience — stories about routing resilience in this arenaRouting resilience

Streaming tools — stories about streaming tools in this arenaStreaming tools

Unified api — stories about unified api in this arenaUnified api