--- title: Diagrid Catalyst 2.0 Adds Durable and Verifiable... description: Diagrid released Catalyst 2.0 on 28 July 2026, adding durable execution and cryptographic verification to AI agents built with LangGraph, Microsoft Agent... canonical: https://daily.dev/posts/diagrid-catalyst-2-0-adds-durable-and-verifiable-execution-for-ai-agents-vd1bgrxjp twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Diagrid Catalyst 2.0 Adds Durable and Verifiable Execution for AI Agents | daily.dev og:description: Diagrid released Catalyst 2.0 on 28 July 2026, adding durable execution and cryptographic verification to AI agents built with LangGraph, Microsoft Agent... og:url: https://daily.dev/posts/diagrid-catalyst-2-0-adds-durable-and-verifiable-execution-for-ai-agents-vd1bgrxjp og:image: https://api.daily.dev/og/posts/vd1bgRXJP.png og:image:alt: Diagrid Catalyst 2.0 Adds Durable and Verifiable Execution for AI Agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Diagrid Catalyst 2.0 Adds Durable and Verifiable Execution for AI Agents **[InfoQ](https://daily.dev/sources/infoq)** · 4 min read · 0 upvotes · 0 comments ## Summary Diagrid released Catalyst 2.0 on 28 July 2026, adding durable execution and cryptographic verification to AI agents built with LangGraph, Microsoft Agent Framework, Google ADK, Dapr Agents and six other frameworks. Model and tool calls become durable workflow activities so interrupted runs resume without repeating completed work, using Dapr 1.18's new signed workflow history to detect tampering. Signing is disabled by default, gated behind a feature flag, requires mTLS, and cannot be applied retroactively to existing workflow history. Diagrid claims up to 10x the performance of open-source Dapr, though the basis for that comparison is unspecified. ZEISS Group is cited as an early adopter. The release enters a market already served by LangGraph persistence, Temporal and Restate, differentiating itself via call-granularity durability spanning multiple frameworks rather than graph-boundary checkpointing. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What new capabilities does Diagrid Catalyst 2.0 add for AI agent workflows? Catalyst 2.0, announced by Diagrid on 28 July 2026, adds durable execution and cryptographic verification to agents built with LangGraph, Microsoft Agent Framework, Google ADK, Dapr Agents and six other frameworks. It represents model and tool calls as durable workflow activities using Dapr, letting interrupted runs resume without repeating completed work, and adds Dapr 1.18-based signed workflow history for tamper detection. _daily.dev surfaces releases like this for teams weighing durability and audit trails in agent architectures._ ### Is workflow history signing enabled by default in Dapr 1.18? No, workflow history signing is disabled by default in Dapr 1.18. It sits behind the WorkflowHistorySigning feature flag and requires mTLS, with daprd refusing to start if signing is enabled while mTLS is off. Signing is also a one-way decision per workflow: there is no retroactive signing of existing history, and toggling it on an in-flight workflow triggers a verification error. _Engineers rolling out Dapr 1.18 security features can track config gotchas like this on daily.dev._ ### How does Diagrid Catalyst's durability model differ from LangGraph persistence, Temporal, and Restate? Catalyst applies a single Dapr-based recovery and attestation model spanning multiple agent frameworks, checkpointing at the granularity of individual model and tool calls rather than graph superstep boundaries. LangGraph persistence checkpoints at graph superstep boundaries and resumes from the last successful checkpoint, while Temporal and Restate provide replay or journal-based execution for long-running applications and can already host agent workflows. _Teams comparing agent durability tools can follow architecture trade-offs like this on daily.dev._ ## Similar posts on daily.dev - [Diagrid gives failed AI agents a way to resume](https://daily.dev/posts/diagrid-gives-failed-ai-agents-a-way-to-resume-rkj1ibpwu) · The New Stack · 1 upvotes · 0 comments - [Durable, flexible multi-agent systems](https://daily.dev/posts/durable-flexible-multi-agent-systems-megbkitj3) · Temporal · 1 upvotes · 0 comments - [Dapr 1.18 Introduces Verifiable Execution, Bringing Cryptographic Trust to AI Agents and Workflows](https://daily.dev/posts/dapr-1-18-introduces-verifiable-execution-bringing-cryptographic-trust-to-ai-agents-and-workflows-ho3i1opbx) · InfoQ · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#workflow-orchestration](https://daily.dev/tags/workflow-orchestration), [#langgraph](https://daily.dev/tags/langgraph) [View this post on daily.dev](https://daily.dev/posts/diagrid-catalyst-2-0-adds-durable-and-verifiable-execution-for-ai-agents-vd1bgrxjp) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Diagrid Catalyst 2.0 Adds Durable and Verifiable Execution for AI Agents","url":"https://daily.dev/posts/diagrid-catalyst-2-0-adds-durable-and-verifiable-execution-for-ai-agents-vd1bgrxjp","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/diagrid-catalyst-2-0-adds-durable-and-verifiable-execution-for-ai-agents-vd1bgrxjp"},"datePublished":"2026-08-26T07:03:11.455Z","dateModified":"2026-08-27T11:45:39.507Z","description":"Diagrid released Catalyst 2.0 on 28 July 2026, adding durable execution and cryptographic verification to AI agents built with LangGraph, Microsoft Agent...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f9960ab1913325b9fecec15d3e5ae8ee?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f9960ab1913325b9fecec15d3e5ae8ee?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"InfoQ","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"InfoQ","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/afc3bced3e1e4b188dd9127017a60e0c","url":"https://daily.dev/sources/infoq"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/diagrid-catalyst-2-0-adds-durable-and-verifiable-execution-for-ai-agents-vd1bgrxjp","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,workflow-orchestration,langgraph","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"InfoQ","item":"https://daily.dev/sources/infoq"},{"@type":"ListItem","position":3,"name":"Diagrid Catalyst 2.0 Adds Durable and Verifiable Execution for AI Agents"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/diagrid-catalyst-2-0-adds-durable-and-verifiable-execution-for-ai-agents-vd1bgrxjp#faq","mainEntity":[{"@type":"Question","name":"What new capabilities does Diagrid Catalyst 2.0 add for AI agent workflows?","acceptedAnswer":{"@type":"Answer","text":"Catalyst 2.0, announced by Diagrid on 28 July 2026, adds durable execution and cryptographic verification to agents built with LangGraph, Microsoft Agent Framework, Google ADK, Dapr Agents and six other frameworks. It represents model and tool calls as durable workflow activities using Dapr, letting interrupted runs resume without repeating completed work, and adds Dapr 1.18-based signed workflow history for tamper detection. daily.dev surfaces releases like this for teams weighing durability and audit trails in agent architectures."}},{"@type":"Question","name":"Is workflow history signing enabled by default in Dapr 1.18?","acceptedAnswer":{"@type":"Answer","text":"No, workflow history signing is disabled by default in Dapr 1.18. It sits behind the WorkflowHistorySigning feature flag and requires mTLS, with daprd refusing to start if signing is enabled while mTLS is off. Signing is also a one-way decision per workflow: there is no retroactive signing of existing history, and toggling it on an in-flight workflow triggers a verification error. Engineers rolling out Dapr 1.18 security features can track config gotchas like this on daily.dev."}},{"@type":"Question","name":"How does Diagrid Catalyst's durability model differ from LangGraph persistence, Temporal, and Restate?","acceptedAnswer":{"@type":"Answer","text":"Catalyst applies a single Dapr-based recovery and attestation model spanning multiple agent frameworks, checkpointing at the granularity of individual model and tool calls rather than graph superstep boundaries. LangGraph persistence checkpoints at graph superstep boundaries and resumes from the last successful checkpoint, while Temporal and Restate provide replay or journal-based execution for long-running applications and can already host agent workflows. Teams comparing agent durability tools can follow architecture trade-offs like this on daily.dev."}}]} ```