Diagrid brings agentic durable execution to Goose. New Diagrid Catalyst integration for Goose, alongside support for LangChainGo, Mastra and other leading agent frameworks, lets agents survive crashes and resume at the last committed step on any Kubernetes cluster. Oct 23, 2026 Prev Next 1 of 43,839 Diagrid, developer of the world's most reliable foundation for mission-critical workflows and autonomous AI agents and the company behind the Distributed Application Runtime (Dapr), announced a new Diagrid Catalyst integration for Goose, an open source project hosted by the Agentic AI Foundation (AAIF), extending agentic durable execution to the open-source general-purpose AI agent, while also adding support for LangChainGo and Mastra. This release extends Catalyst's support to over 15 agent frameworks for Python, TypeScript, Java and C#. With Catalyst, a Goose recipe commits each step - every LLM call, extension tool call and sub-recipe invocation - before the next one begins. If the process or the node dies, the recipe resumes at the last committed step. Production agents run for minutes, hours or days. Containers are redeployed, nodes fail and API calls time out. Without durable execution, any of those events restarts the run from the beginning; every completed LLM call, tool call and API request executes again, and the organization pays for the same tokens twice. Catalyst commits each step before the next one begins, so when a process dies, the workflow resumes at the exact step that failed. Diagrid Catalyst adds durable execution underneath Goose recipes and subagents, so a long-running run resumes at the last committed step instead of restarting. Catalyst plugs into Goose through its standard extension mechanism, so no changes to Goose itself are required. Goose gives developers an open, extensible agent runtime that can operate through desktop, CLI and API interfaces, connect to external tools and systems through model context protocol (MCP) extensions and orchestrate work through reusable recipes and subagents. With Catalyst, a Goose recipe commits each step - every LLM call, extension tool call and sub-recipe invocation - before the next one begins. If the process or the node dies, the recipe resumes at the last committed step. Work already completed is not repeated and is not paid for twice. The result is a clean separation between the agent experience and the durability layer: developers keep Goose's recipes, sub-recipes, subagents and MCP extensions exactly as they are, and Catalyst supplies the execution durability beneath them. Added Support Built for Kubernetes Diagrid has also added integrations with LangChainGo and the TypeScript framework Mastra, bringing durable execution to organizations developing and deploying agents to Kubernetes backends. Some agent platforms tie durability to a single hosting environment, but Catalyst takes a different approach. It runs on Dapr, the Cloud Native Computing Foundation (CNCF)-graduated open-source project used in production at thousands of organizations, making agent workloads portable across AWS, Azure, Google Cloud and on-premises clusters. Teams avoid vendor lock-in, with no need to rewrite anything when they move. "Go and TypeScript agents on Kubernetes hit the same failure every long-running process hits: something breaks, and the work starts over," said Yaron Schneider, co-founder and CTO of Diagrid and chair of the Agentic AI Foundation Workflows Working Group. "These integrations let developers keep the framework they chose and gain a runtime that picks up where the agent stopped. And since Catalyst is built on Dapr, the same durability runs on any Kubernetes environment, in any cloud or on-premises."

Diagrid promotes Sam Yang to CEO as Mark Fussell shifts to product leadership. September 30, 2026 Diagrid has promoted President Sam Yang to Chief Executive Officer as the enterprise software company focuses on helping organizations move autonomous AI agents and mission-critical workflows into production. Yang succeeds Diagrid co-founder Mark Fussell, who is transitioning to Chief Product Officer and will concentrate on product development, including the company's Diagrid Catalyst platform. Co-founder Yaron Schneider will remain Chief Technology Officer, leading the company's technical strategy across Catalyst and the open-source Distributed Application Runtime, or Dapr. Yang joined Diagrid as President earlier this year. As CEO, he will help set the company's business direction and lead its go-to-market strategy around the infrastructure enterprises need to operate AI agents reliably in production. "A surprisingly low number of enterprises are actually running agents reliably in production, where a crash, timeout or audit request can inadvertently undo weeks of work," Yang said. "This is the business problem Diagrid is made to solve." Diagrid is positioning its infrastructure around the operational challenges that emerge when AI agents move beyond prototypes into long-running enterprise workloads. Those requirements include maintaining state, coordinating workflows, managing service-to-service communication, controlling access and creating verifiable records of agent activity. Its flagship Catalyst platform combines durable workflows with identity, access controls and zero-trust-style governance. The system is designed to support long-lived AI and cloud-native workloads while reducing the risk that failures or interruptions cause agents to lose their execution state. Yang brings more than two decades of enterprise software go-to-market experience to the CEO position. Before joining Diagrid, he led global sales at Zilliz and served as President of Field Operations at People.ai. He previously ran the go-to-market organization at data.ai, formerly App Annie, and has held positions at Microsoft, Hewlett-Packard and PeopleSoft. Yang said his immediate priority will be expanding adoption of the technology developed by Fussell and Schneider as more companies attempt to deploy AI agents in operational environments. "Mark and Yaron laid the foundation with Dapr and Catalyst, and now my job is to get it in front of every team trying to fully leverage the power of AI agents in production," Yang said. Fussell's move to Chief Product Officer will allow him to focus more directly on Catalyst and the technical requirements for building durable and verifiable AI agents. "Taking on the chief product officer role will let me spend every day on the work I care about most," Fussell said. "Sam has the proven ability to help us scale the business, which will free me to go deeper on how teams can build durable, verifiable agents." Fussell and Schneider originally co-created Dapr, an open-source runtime designed to simplify the development of distributed applications. The project has since graduated within the Cloud Native Computing Foundation and is used in production across thousands of companies. Schneider also chairs the Agentic AI Foundation's Workflows Working Group. Diagrid builds infrastructure for distributed systems and AI agents, providing capabilities including durable execution, AI orchestration, secure service-to-service communication and cryptographic verification. The company works with organizations in regulated industries such as financial services and healthcare, where agent workflows can require detailed access controls and auditable records of actions across infrastructure. The leadership changes give Yang responsibility for scaling the commercial business while allowing Diagrid's founders to concentrate on product and technical development as the company targets the infrastructure requirements involved in moving enterprise AI agents from experimentation into production.

Diagrid has launched Catalyst 2.0, enabling developers to add cryptographic trust and automatic failure recovery to AI agents built on major frameworks without rewriting code. The platform supports LangGraph, Microsoft Agent Framework, Google Agent Development Kit, AWS Strands, OpenAI Agents SDK, CrewAI, and others. Catalyst 2.0 combines durable execution with verifiable execution, allowing agents to automatically resume from failure points whilst cryptographically signing each step. The multi-cloud solution can run in air-gapped environments and improves open-source Dapr performance by up to 10 times, supporting millions of concurrent agent workflows. Developers integrate a Diagrid code package directly into their chosen framework to gain durable workflows immediately. The platform addresses the lack of built-in recovery guarantees in most agent frameworks, which typically require manual intervention when long-running workflows fail.