Komodor announced a new extensibility framework that transforms its Klaudia AI technology into a universal multi-agent platform for troubleshooting and optimizing the performance of complex cloud native infrastructures and applications.
This new architecture enables organizations to extend Klaudia AI with their own tools, services and agents, and combine these with more than 50 specialized agents already provided by Komodor. These new multi-agent orchestration capabilities enable teams to automate investigation and remediation of operational issues across all infrastructure layers including Kubernetes, GPUs, networking, and storage.
The announcement marks the next step in Komodor’s evolution from automated troubleshooting to a fully extensible autonomous AI SRE platform.
“Most AI tools for operations focus on summarizing telemetry rather than resolving incidents, but complex outages require specialists from multiple domains working together to understand what’s happening across the stack,” said Itiel Shwartz, Co-Founder and CTO of Komodor. “The Komodor platform’s new extensible architecture replicates this collaborative process using specialized agents that encode operational knowledge and work together to diagnose and resolve issues.”
The Komodor platform introduces a modular architecture that orchestrates multiple AI agents, each responsible for a specific operational role. Workflow agents coordinate key reliability engineering processes such as detection, investigation, and remediation. They can also dynamically invoke specialized Subject Matter Expert Agents (SMEs) that bring deep expertise in specific technologies or domains such as Kubernetes, AWS services, GPUs, or deployment tools.
This architecture allows Klaudia AI to retrieve precise context exactly when it is needed, avoiding the hallucinations and data overload that often limit general-purpose AI assistants. Using this extensible architecture, Komodor has already developed more than 50 specialized agents across operational domains, enabling the platform to troubleshoot issues that extend far beyond Kubernetes clusters and into the broader cloud-native infrastructure stack.
Komodor’s extensibility framework enables organizations to bring their own services, tools and agents via MCP or an OpenAPI specification. Klaudia AI orchestrates these alongside its native specialists as part of the same investigation workflow to gain a better understanding of the issue and run remediation plans.
Early adopters are already using the framework to extend Klaudia AI with custom agents tailored to their environments. Examples include agents that:
- Cross-reference CI/CD pipelines to correlate failures with recent code or configuration changes across microservices
- Integrate with database management tools to determine whether application latency traces back to query performance or connection pool exhaustion
- Query past incident channels to surface how similar symptoms were resolved in previous outages
The multi-agent framework for Klaudia AI is available immediately.
The Latest
I've spent a lot of time in the channel, and one thing I keep coming back to is this: a partner program is only as good as what it looks like in the field. Many programs look great on paper, but when a partner is in front of a customer navigating a complex hybrid environment or trying to make the case for AI-powered observability, the gap between what a vendor promises and what it actually delivers becomes very clear, very fast ...
Enterprises today operate in a real-time environment where uninterrupted access to trusted data has become a baseline expectation for users, applications and automated systems. Traditional DataOps models, built on manual effort and human triage, cannot keep pace with this always active demand. AI agents are emerging as the operational backbone, ensuring consistent data availability, reinforcing trustworthiness and enabling a level of scale that manual processes cannot achieve ...
For decades, trust in the digital workplace rested on familiar signals. We trusted faces on video calls, voices on the phone, and emails that appeared to come from people we knew. These cues felt human and intuitive. They anchored how decisions were made, approvals were granted, and access was authorized. AI-powered deepfakes have quietly broken that model ...
Cloud migration was supposed to be a one-way door. For most enterprises, it turns out it isn't. Cloud data repatriation is a real and growing trend. A new survey ... finds that 89% of organizations plan to expand their on-premises infrastructure footprint over the next two years — and 75% have already moved at least some workloads back from public cloud in the past 24 months. The findings point to a broad rethinking of where data belongs ...
Over the past few years, large language models (LLMs) have revolutionized the software industry. Given their ability to excel at multi-step reasoning, LLMs have helped enterprises streamline workflows and adapt to the unknown. However, employing such models comes with sky-high costs, latency issues, and limited flexibility. In the realm of IT operations, it is generally wiser to employ smaller, domain-specific models instead ...
For years, DevOps teams operated under a simple assumption: collect enough telemetry, and you can find and fix any problem. That assumption is breaking down. Modern enterprises now operate across microservices, hybrid cloud environments, APIs, Kubernetes, and highly automated delivery pipelines. Releases happen continuously, dependencies shift constantly, and failures spread faster than teams can diagnose them ...
New Relic surveyed IT and engineering leaders from the media and entertainment (M&E) sector to understand what's working — and where challenges persist with their observability practices. The findings reveal how M&E organizations are navigating rising platform complexity, audience expectations, and AI-driven change. Below are five takeaways that stand out ...
Let me start with something I've seen play out more times than I can count. A team hits a wall with the cloud. Costs creep up, then spike. Performance starts to feel inconsistent. Someone in finance asks a simple question like "why did this double?" and nobody has a clean answer ... Maybe this isn't the right place for everything. That realization feels like a breakthrough, like you've identified the problem. In reality, you've just identified the starting line ...
In MEAN TIME TO INSIGHT Episode 24, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network observability tool sprawl ...
In cloud-native systems, scaling is often as simple as moving a slider. For on-premise databases, the stakes are different. Over-provisioning hardware is expensive. Under-provisioning leads to performance bottlenecks that are difficult to fix once the equipment is in the rack ...