- Apache 2.0Open source
- Linux FoundationMember
- Agentic AI FoundationMember
- ISO 27001Certified environment
- SOC 2 Type 2Audited environment
01What OAK does
Six stages every agent request passes through
Each one is switched on with a few lines of configuration, not built from scratch.
Build
Write agents in the framework you already know. OAK wraps them with one API, so the agent logic stays yours.
Learn more- Adapters for eight agent frameworks, side by side in one runtime
- Tools written once as plain Python and bound to any framework
- Structured output, multimodal input and multi-agent handoffs
from agents import Agent as OpenAIAgent
from agentkernel.cli import CLI
from agentkernel.openai import OpenAIModule
assistant = OpenAIAgent(
name="assistant",
instructions="Give short and direct answers.",
)
# Register the agent with OAK
OpenAIModule([assistant])
if __name__ == "__main__":
CLI.main()
02Architecture
One runtime between your channels and your agents
Requests arrive from any channel or protocol. OAK runs your framework-native agents with sessions, guardrails, queues and sandboxes, on whichever cloud you choose.
The runtime
Request inBuildConnectRememberGuardScaleObserveResponse out
03Works with
Plug in what you already run
75 integrations, and every one is an adapter. Swap one without touching the others.
01Build
Build with the framework you already know
Agent frameworks8
Model gateway1
Coding assistants5
02Connect
Connect to the channels your users are on
03Remember
Remember in the stores you already run
Session and state stores5
Knowledge4
04Guard
Guard with your identity provider and your policies
05Scale
Scale on the cloud you already use
06Observe
Observe and test with the tools you trust
04Deployment
Deploy anywhere
Run the same agent code on AWS, Azure, GCP or your own Kubernetes cluster. Terraform modules and a Helm chart are included.
Amazon AWS
Serverless or containerized deployments with Terraform modules.
- AWS Lambda (serverless)
- AWS ECS on Fargate (containerized)
Microsoft Azure
Container Apps with Cosmos DB session storage.
- Azure Container Apps (containerized)
- Queue mode over Azure Service Bus
Google Cloud
Cloud Run serverless or containerized deployments with Firestore session storage.
- Cloud Run (serverless)
- Cloud Run (containerized)
On-prem Kubernetes
The official Helm chart, for any Kubernetes cluster.
- Bare metal or a self-hosted cluster
- AWS EKS (Pod Identity, with SQS, NATS or Kafka)
- KEDA autoscaling on queue depth
- Air-gapped installs (mirrored images)
05Choose your path
OAK, explained for your level of expertise
Three guided tours of the same stack. Pick how deep you want to go.
- 01The outcomeNo code requiredBusiness leaderYou want agents that work inside real business workflows, without owning the technical detail.
- 02The codeSome codingDeveloperYou build software and want to ship a first robust agent without learning a new stack.
- 03The runtimeDeep techAI engineerYou already work with LLMs and agent frameworks, and need a production runtime that stays out of your way.
06Questions
Questions we hear a lot
What OAK is, what it costs, and how it fits with the tools you already use.
Ship your first agent today
Free and open source under Apache 2.0. No licensing costs and no lock-in.







