November 20, 2026

ClearRoute Reveals runkora, an Agentic AI Control Plane for Software Engineering

10168

Global platform engineering consultancy, ClearRoute, today announces the alpha release of runkora, an open-source, cloud-agnostic agentic AI control plane for running agent factories in production. Unveiled at PlatformCon Live Day in Sydney, runkora was developed by ClearRoute’s Australian engineering team to help organisations manage the growing compliance and governance challenges of agentic AI in software engineering and DevOps, without slowing deployment. ClearRoute’s decision to release runkora as open source ensures the platform will continue to support any AI agent an organisation wants to deploy, rather than being tied to a specific agent framework or cloud ecosystem.  

“We’ve already seen how AI can speed up writing code, but that’s only 20% of the software development lifecycle. The bottleneck occurs with what comes next, because the remaining 80% requires testing, security, compliance, governance and release orchestration before any software can safely go into production,” says James Jarvis, CEO, ClearRoute.  

runkora uses ClearRoute’s platform engineering approach to govern AI agents throughout the end-to-end journey of getting software from initial idea into production and, ultimately, into customers’ hands. This journey is called the Route to Live and includes the processes, tools, and cultural practices that enable or impede delivery excellence.  

“Our Route to Live research shows that some organisations are still waiting four to eight weeks just for change approvals. AI might help developers produce code faster, but unless businesses address the engineering processes around it, they risk accelerating development without actually improving their time to market.” Jarvis continues. 

“Organisations think they can keep deploying AI agents to tackle the problem. However, if humans are struggling with complex processes, adding AI agents won’t necessarily solve the problem and could make it worse. As the number of agents grows, ensuring they only perform authorised actions gets really difficult, really quickly,” adds Jarvis. 

The scale of the problem shouldn’t be underestimated. Gartner predicts that by 2028, an average global Fortune 500 enterprise will have over 150,000 AI agents in use, while only 13% of organisations believe that they have the right AI agent governance in place. As AI evolves from generating code to autonomously interacting with enterprise systems, platform engineering provides a way to embed consistent governance across the Route to Live. runkora enables this through a common control plane, rather than requiring separate controls for every individual agent. 

“If you consider the fine-grained access these AI agents need, with just 10 agents deployed you will be rotating 20-30 secrets every month. Imagine updating passwords, API keys, certificates, tokens, and other access credentials with 150,000 AI agents – it quickly becomes impossible or at least very expensive to manage. runkora solves this by centrally controlling agent identities, credentials, permissions and actions, confining agents to authorised environments while giving humans visibility of any attempted activity outside those boundaries,” says Justin Wilkin, Global Head of Engineering and AI, ClearRoute. 

This is particularly pertinent as enterprises adopt ‘dark factories’, where AI agents operate autonomously in the background. Without effective controls, organisations risk either restricting these processes or exposing themselves to security breaches. 

“A lot of vendors are talking about agentic AI control planes when they really should be referring to them as agentic AI gateways, which assume agents will follow prescribed boundaries and controls. As AI becomes more autonomous, businesses need enforceable boundaries built on zero-trust principles. Rather than simply acting as a gateway, runkora enforces controls on agents themselves, providing a secure, compliant ‘golden path’ for them to operate alongside human developers,” says Wilkin. “This is where platform engineering becomes critical, making secure, compliant ways of working the easiest and most consistent path for every agent, rather than expecting individual teams to build and maintain controls themselves.” 

runkora covers eight key requirements in enforcing boundaries for agentic work, governing how work enters, how agents execute, which resources they can reach, and the evidence produced through their actions: 

  • Identity and delegation: every agent receives a verifiable workload identity, together with the authority under which it acts. 
  • Context and discovery: services, repositories, ownership, dependencies, standards and operational state become discoverable to agents through governed sources of enterprise context. 
  • Policy and authorisation: determines which systems an agent can access, which actions it may perform and the conditions that apply. 
  • Secure credentials and access: credentials and tokens are exchanged at controlled boundaries and supplied only for the duration of the task. 
  • Isolated execution: agents execute in controlled, disposable environments, which limits the blast radius of unexpected behaviour. 
  • Model and inference access: gives agents access to approved models and providers through a common enterprise boundary.  
  • Enterprise connectivity: provides governed connectivity to systems and services across the enterprise estate, with identity, credential handling, policy and audit applying consistently across those routes. 
  • Observability and audit: every agent action produces evidence to trace what the agent did, which resources it accessed, which tools and models it used, what changed and whose authority applied to the work. 

“AI is amplifying the strengths of high-performing engineering organisations, but also exposing the weaknesses of those still reliant on manual processes and fragmented infrastructure. Despite the accelerated use of AI in software development, enterprise delivery still typically takes 30 to 45 days. runkora provides the foundational control plane for all non-human work for organisations to create a truly governable, AI-augmented, automated delivery ecosystem at scale and turn faster development into faster delivery of business value,” Jarvis concludes.  

Image Source: Magnific