WSO2 is now Choreo LabsLearn more

Trusted AI Governance
Build

Create agents and AI apps with the tools and languages your teams already use.

Connect

Link agents securely to your APIs, data, models and business systems.

Run

Deploy, observe and operate agents and AI apps reliably at any scale.

Govern

Control identity, access, cost and policy for every agent in production.

Agent Management

Developer Platform

  • API Management Cloud

    Design, secure and publish APIs with governance and analytics built in.

    Sign Up Now
  • Integration Cloud

    Connect apps, data and AI agents with low-code and pro-code integration.

    Sign Up Now
  • Identity & Access Management Cloud

    Secure sign-in and access for customers, partners, workforce and agents.

    Sign Up Now
  • Agent Management Cloud

    Build, run and govern AI agents with full visibility and control.

    Sign Up Now
  • Developer Platform Cloud

    Ship cloud-native apps faster on an internal developer platform.

    Sign Up Now

Self-Hosted

Full control over your stack. Deploy directly to your own servers, bare metal, cloud, or Kubernetes environment. Your data never leaves your perimeter.

Product Downloads
Choreo Labs
AI Governance
Platform
Solutions
Resources

One gateway for LLMs, MCP tools, and agents

Control access to models and tools, apply guardrails, and enforce usage budgets. Run the open-source AI Gateway in your own infrastructure or through Choreo Cloud.

GartnerChoreo Labs (formerly WSO2) named a Leader in the 2026 Gartner® Magic Quadrant™ for API ManagementRead the report

Trusted by enterprises worldwide

Wipro
University of Exeter
Travis Perkins
JLR
TM
Saudi Aramco
Sacem
Perkin Insurance
Kotak
Discovery
NYS Department of Health
CBM
CareMetx

LLMs, MCP tools, and agents through one gateway

One AI Gateway with three proxies. Govern how applications call models, how agents call tools, and how agents call each other, with one policy model and one view of usage.

LLM Proxy: govern every model call

  • Token and dollar budgets with organizational controls
  • Semantic caching and adaptive routing across providers
  • An OpenAI-compatible endpoint for hosted and open-weight models
  • Usage attributed per user, team, and application, across any gateway

MCP Proxy: secure every tool call

  • Generate MCP servers from existing APIs in a few clicks
  • Add authentication and authorization to MCP tools in a few clicks
  • Govern and enforce usage of third-party MCP servers
  • Token limits that keep agents and apps within quota
  • Publish MCP servers to the AI Hub for discovery

A2A Proxy: govern agent-to-agent calls

  • Authentication and authorization for agent-to-agent interactions
  • Selective exposure of agent skills through the agent card
  • Rate limits on agent calls, globally and per operation
  • Monitoring, tracing, and analytics for agent calls
  • Streaming A2A for long-running agent interactions

Capabilities

Usage and spend

Apply request, token, and cost limits at the gateway. Use semantic caching to reduce repeated model calls.

  • Token and dollar budgets per user, team, and app, with caps per provider, proxy, and consumer, enforced at the gateway
  • Semantic caching answers repeated prompts without paying for a second model call
  • Every call metered at the gateway. Connect gateway telemetry to Analytics and Monetization to attribute usage and support chargeback.

Guardrails

Install guardrails from the Policy Hub, connect supported content-safety services, or build your own policies in Go or Python.

  • PII masking and redaction, prompt validation, output checks, and enforced prompt templates
  • AWS Bedrock Guardrails and Azure Content Safety integrations; custom guardrails in Go
  • Applied globally or per endpoint, versioned and managed as code through Policy Hub

Routing and resilience

Distribute requests across configured providers using weighted routing and failover.

  • Load balancing and automatic failover across providers, weighted to your cost or capacity preferences

AI Analytics

Track model and tool usage, latency, errors, and estimated cost with AI Analytics, powered by Moesif.

  • Token consumption, cost, and latency by provider, model, app, and user
  • Tool-level and server-level MCP usage, with anomalous agent patterns flagged
  • End-to-end tracing, with prompt and tool-call logs kept where you decide
Usage and spend

70+ AI guardrails and policies. Ready when you are.

Install guardrails from the Policy Hub or build your own in Go or Python. Policies ship independently of the gateway runtime, so new guardrails reach production without waiting for a gateway upgrade.

Browse the Policy Hub

Built-in guardrails

  • Regex-based PII masking
  • Semantic prompt guard
  • URL validation
  • Schema validation
  • And more in the Policy Hub

Third-party integrations

  • AWS Bedrock Guardrails
  • Azure Content Safety

Build your own

  • Write policies in Go or Python
  • Version them like code
  • Ship them independently of the gateway

Consolidate AI sprawl onto one gateway

Replace the DIY proxies. Keep the API gateways you already run.

Replace

  • Open-source and DIY LLM proxies
  • Per-team API keys
  • Point LLM gateways
  • Per-cloud AI gateways
  • Shadow AI apps

Keep and federate

  • Kong, AWS, Azure, and Envoy gateways
  • Your existing API Manager

Get one view

  • One AI cost and policy view
  • Analytics across 14 vendors

Analyst recognition

Leader, 2026 Gartner® Magic Quadrant™ for API Management

Choreo Labs (formerly WSO2) was named a Leader in the 2026 Gartner® Magic Quadrant™ for API Management.

Read the report

Leader and Customer Favorite, The Forrester Wave™: API Management Software, Q3 2026

Choreo Labs scored a 5.00 in the Analytics and reporting criterion in The Forrester Wave™: API Management Software, Q3 2026.

Read the report

Customer examples

ICA, Sweden's leading grocery retailer, uses Choreo API Management to expose AI to agents safely and control AI spend, at 3 billion transactions a month.

Qantas exposes AWS Bedrock to its applications through the AI Gateway and Agent Control Plane with centralized governance.

Connects to

Managed from Agent Control Plane. Feeds Analytics and Monetization for chargeback and billing, and publishes to the API Portal & AI Hub. Built on the same Go runtime and policy engine as the API Gateway. Runs on Kubernetes or VMs: SaaS, hybrid, self-managed, or air-gapped.

Start with the AI Gateway

Add Agent Control Plane when the AI team needs its own console. Add Analytics and Monetization for chargeback.

Gartner, Magic Quadrant for API Management, 2026. GARTNER is a registered trademark and service mark of Gartner, Inc. and/or its affiliates in the U.S. and internationally, and MAGIC QUADRANT is a registered trademark of Gartner, Inc. and/or its affiliates and are used herein with permission. All rights reserved. Gartner does not endorse any vendor, product or service depicted in its research publications, and does not advise technology users to select only those vendors with the highest ratings or other designation. Gartner research publications consist of the opinions of Gartner's research organization and should not be construed as statements of fact. Gartner disclaims all warranties, expressed or implied, with respect to this research, including any warranties of merchantability or fitness for a particular purpose.