New release lets developers add cryptographic trust and automatic failure recovery to AI agents built on any major framework, without rewriting application code.

Agentic durable execution combines durable execution with cryptographic verification, so agents recover from failure and produce a tamper-proof record of every step. See how Diagrid Catalyst adds both under the agent framework you already use.

An agent acting under its own identity holds the union of everyone's permissions. On-Behalf-Of delegation binds every call to the person who actually asked.

How Dapr implements the microservices patterns cataloged on microservices.io, from the microservice chassis and sidecar to saga, transactional outbox, and service discovery.

The Diagrid Dev Dashboard is a free, open-source companion for local Dapr development. Get a live view of your running apps, inspect and debug workflows, and build components and resiliency policies without hand-writing YAML.

Enterprises rarely know which agents reach their MCP servers or what they can do. See how Diagrid Catalyst governs MCP access with per-tool, default-deny authorization.

Diagrid Catalyst now controls which MCP servers and tools each agent can reach, and separates archiving from purging so you keep required workflow history and still reclaim database space.

The EU AI Act's high-risk rules need proof and control that observability can't reach. See how Diagrid Catalyst makes agent records tamper-evident and actions governed at runtime.

Agents in production act with shared keys and no record of which agent made which call. See how Diagrid Catalyst gives every workload a verifiable identity and enforces access in the data plane.

Agent spend is set at runtime by the agent's own decisions. See how per-task records in Diagrid Catalyst let a finance team model and bound the cost of running agents.

Find, inspect, and safely intervene on workflows that are running, failed, or waiting on an external event, using workflow operations in Diagrid Catalyst.

When an agent crashes at step forty-seven, it should resume there, not start over. Why durable execution belongs in the runtime, where framework checkpointers fall short, and how Catalyst on Dapr recovers crashed agent workflows automatically.

Why durable execution isn't enough for agent systems, and how Diagrid Catalyst, built on Dapr, brings verifiable execution lineage to agent workflows.

Catalyst now shows where workflows fail and reruns them in bulk from the failed step, finds workflows waiting on human input so you can unblock them, and runs in Catalyst Cloud or inside your own Kubernetes cluster.

Dapr 1.18 brings workflow history propagation, tamper detection, access policies, global concurrency limits, and secure MCP, so production workflows and agents stay trustworthy, controlled, and auditable. All these features are available in Catalyst today.

Latest release enables organizations to prove the authenticity, integrity, and lineage of workflow and AI agent execution. New capabilities digitally sign execution history, propagate trusted provenance across services, and generate attestations that allow auditors to verify exactly how work was performed.

Most agent projects stall before production, and the model is rarely the cause. The four failure modes behind it: durability, security, cost, and observability.

A recap of the May 20, 2026 Diagrid webinar on why agents need cryptographically attestable identity, why MCP gateways are not enough, and how SPIFFE, Dapr, and Catalyst bring zero trust to agentic systems.