Skip to main content

Develop Agents

Build production-ready AI agents on Diagrid Catalyst by combining any of the supported agent frameworks below with Dapr for durable execution, pluggable memory, and swappable LLM providers. Each framework guide shows how to make existing agents crash-proof with durable workflows and how to expose tools over MCP servers. New to agents? Start with the AI agent quickstart to build and deploy your first durable agent in under 15 minutes, then come back here to wire up your preferred framework.

Catalyst works with the following agent frameworks.

Beyond the framework guides, Multi-agent orchestration shows how to coordinate specialist agents across frameworks over Catalyst pub/sub, and Deploy to Kubernetes covers taking any of them to a cluster.

Framework requirements

Every agent on Catalyst runs as a durable workflow, so every integration requires a workflow state store — the managed state store where Catalyst checkpoints and replays each reasoning step and tool call to enable durable execution. It is the one resource all frameworks share.

The Conversation API and a Dapr conversation component that proxies LLM calls are optional for most integrations: third-party frameworks call their LLM provider directly through their own SDK. There are two exceptions: Dapr Agents leads with the Conversation API as its LLM path, and the Microsoft Agent Framework integration routes LLM calls through a conversation component.

FrameworkLanguagePackage / repoRequired resourceConversation API
Dapr AgentsPythondapr/dapr-agentsWorkflow state storeRecommended
LangGraphPythondiagridio/python-aidiagrid[langgraph]Workflow state storeOptional
CrewAIPythondiagridio/python-aidiagrid[crewai]Workflow state storeOptional
StrandsPythondiagridio/python-aidiagrid[strands]Workflow state storeOptional
Pydantic AIPythondiagridio/python-aidiagrid[pydantic_ai]Workflow state storeOptional
OpenAI AgentsPythondiagridio/python-aidiagrid[openai_agents]Workflow state storeOptional
Google ADKPythondiagridio/python-aidiagrid[adk]Workflow state storeOptional
Deep AgentsPythondiagridio/python-aidiagrid[deepagents]Workflow state storeOptional
Claude Agent SDKPythondiagridio/python-aidiagrid[claude_agents]Workflow state storeOptional
HolmesGPTPythondiagridio/python-aidiagrid[holmesgpt]Workflow state storeOptional
Microsoft Agent Framework.NETdiagridio/dotnet-aiDiagrid.AI.Microsoft.AgentFrameworkWorkflow state storeRequired
Spring AIJavadiagridio/java-aiio.diagrid.dapr:dapr-spring-ai-starterWorkflow state storeOptional
LangChainGoGodiagridio/go-aiadapters/langchaingoWorkflow state storeOptional
EinoGodiagridio/go-aiadapters/einoWorkflow state storeOptional

The workflow state store is the only resource the third-party wrappers need — they configure nothing else. Two integrations use more. Dapr Agents is agent-native, so a DurableAgent wires up its own memory, state, and registry stores plus a pub/sub for agent-to-agent messaging (agent-workflow, agent-memory, agent-registry, agent-pubsub in the quickstart). Go agents register themselves into an agent-registry component on startup. In both cases diagrid project create|update <project> --enable-agent-infrastructure provisions the whole set — pub/sub, key-value, workflow, and agent registry — in one step.

Each integration is built on a language-specific durability package that wraps the framework's execution loop in Dapr Workflows: python-ai for the Python frameworks, dotnet-ai for .NET, java-ai for Java, and go-ai for Go. Dapr Agents builds natively on the Dapr workflow runtime, so there is nothing to wrap.

In Go, you build the agent as a graph of nodes and go-ai runs it as a Dapr workflow, so each node becomes a checkpointed activity. The framework plugs in through node constructors — langchaingo.ModelNode or eino.ChatModelNode — which means swapping frameworks leaves your orchestration code untouched. See the go-ai README and the runnable LangChainGo and Eino examples.

note

The Java (java-ai) and Go (go-ai) integrations are in early development — APIs are not yet stable.

Dapr & AI University · Learn this hands-onDapr Agents: Build LLM-powered intelligent applications with tools and workflowsBuild intelligent agents with custom tool calls, MCP integration, and multi-agent collaboration. Requires an OpenAI API key.Intermediate45 minPythonStart the track