diagrid-labs

Dapr Reliable Agentic Systems — AI skill for Claude Code

AI community

Use Dapr Workflow and the Dapr Conversation API to run agentic AI applications reliably.

How to install Dapr Reliable Agentic Systems

This entry records only its repository, not the path inside it, so there is no exact command to give. Open diagrid-labs/dapr-reliable-agentic-systems and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Dapr Reliable Agentic Systems does

Use Dapr Workflow and the Dapr Conversation API to run agentic AI applications reliably.

Alternatives in AI

AI Engineering Hub — In-depth tutorials on LLMs, RAGs and real-world AI agent applications 37.2k ★
Bot On Anything — A large model-based chatbot builder that can quickly integrate AI models (including ChatGPT, Claude, Gemini) i 4.2k ★
Peekaboo — Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, o 3.2k ★

README

Build reliable agentic systems with Dapr Workflow

This repository demonstrates how to build reliable agentic systems by combining Dapr Workflow orchestration with LLM-powered activities using the Dapr Conversation API.

Overview

The demos showcase the patterns described in [Building Effective Agents](https://www.anthropic.com/engineering/building-effective-agents) by Anthropic, implemented using Dapr Workflow to orchestrate reliable multi-step processes and the Dapr Conversation API to interact with LLMs. Ollama is used as the local LLM provider for all demos.

Benefits of Dapr Workflow and Conversation API

Dapr Workflow

Deterministic control over task execution with structured error handling and retries
Durable state management that persists across failures and restarts
Built-in orchestration patterns for complex multi-step processes
Reliable execution with automatic recovery and compensation logic

Dapr Conversation API

Flexibility and natural language understanding through LLM integration
Provider-agnostic interface supporting OpenAI, Azure OpenAI, Ollama, and more
Simplified LLM integration with consistent API across different providers
Built-in caching to optimize performance and reduce costs

Combined Power

By combining deterministic workflows with the probabilistic nature of LLMs, you can build agentic systems that are both reliable and flexible, leveraging the best of both worlds.

Agentic Patterns

Pattern	Demo Project
Prompt Chaining	AnomalyAnalysis
Routing	GalacticAnomalyClassifier
Parallelization	StarshipDiagnostics
Orchestrator-Workers	SpaceColonyPlanner
Evaluator-Optimizer	AlienTranslator
Autonomous Agent	SpaceDebrisAgent