witkeepNo gateway
Witkeep provides an AI gateway and the collaborative workspace.
IT integration
Connect Witkeep to your infrastructure: API gateways, AI gateways, managed AI / LLM services and local models.
Start with your existing infrastructure
An API gateway
Keep your API management. Route your AI requests through Witkeep.
An AI gateway
Keep your AI gateway. Connect Witkeep to it for a collaborative AI workspace and full business governance, including value tracking.
Managed AI / LLM services
Use the model endpoints of your managed services in Witkeep.
Already using managed AI / LLM services?
Witkeep connects to every model available through your managed services, to manage costs, usage and adoption.
- AWS
Amazon Bedrock
- Google Cloud
Vertex AI
- Microsoft Azure
Microsoft Foundry
- Hugging Face
Inference Endpoints
And other managed services, depending on their model access APIs.
Your AI infrastructure. A workspace for every team.
Give non-technical teams a single prompt area to use the models and tools you make available. They choose their business context, create deliverables and share their work.
Explore the collaborative workspace
IT defines access. Teams work together.
Deploy in your environment
A dedicated cloud instance or an on-premise deployment, on Kubernetes.
Keep your monitoring tools
Track usage with Prometheus and OpenTelemetry, alongside your existing monitoring tools.
Your integration questions
Read the full FAQWhat is an API gateway?
An API gateway is an entry point between applications and services. It lets you control access, apply rules to requests and monitor how those exchanges work.
What is the difference between an API gateway and an AI gateway?
An API gateway controls exchanges between applications and services, whatever their purpose. An AI gateway applies functions specific to model requests: model selection, token tracking, costs and usage policies. These are different scopes that can coexist. An AI gateway does not replace the management of your business APIs.
We already have an API gateway. Can we use Witkeep?
Yes. Witkeep can fit into an architecture that already has an API gateway. You keep your infrastructure; Witkeep adds AI usage management and a business workspace. The integration covers the AI requests you route through Witkeep.
Our gateway already has an AI module. What does Witkeep add?
Witkeep adds the business layer: work contexts, reusable methods, shared deliverables and conversations, plus usage and value tracking. The aim is to connect technical AI management with the work your teams actually do.
Can we use Witkeep without another gateway?
Yes. You do not need an existing gateway to use Witkeep as an access and control point for your AI usage. Witkeep combines this role with a collaborative workspace. Its scope is AI usage, rather than every API in your information system.
Do we have to use Witkeep’s chat interface?
No. An existing interface can connect to Witkeep if it supports configuring a compatible AI service. Witkeep’s interface brings business contexts, deliverables and team sharing together; these features are not automatically available in a third-party interface.
Can we use our managed AI / LLM services with Witkeep?
Yes. You can connect model access from your managed services to Witkeep: Amazon Bedrock, Google Vertex AI, Microsoft Foundry or Hugging Face Inference Endpoints. Witkeep adds business context, usage policies and monitoring for the requests routed through it.
We have none of this: our employees just have access to Claude. Is Witkeep useful?
Yes, and it is the right time. You are moving from experimentation to company-wide adoption. Witkeep centralises usage in a single tool: your teams use the leading models on the market (Claude, GPT, Gemini, Mistral) without switching tools, share what works, and you keep visibility on costs and adoption.
We already have a token provider: what does Witkeep add?
Witkeep connects to your current provider, so you keep buying tokens wherever you want. It adds what model access alone does not provide: a collaborative workspace for every team, shared business contexts and skills, usage rules, and tracking of costs, adoption and value created.