在Dapr上运行持久化的AI代理工作流
Use Dapr sidecars and workflows to give AI agents durable execution, state, messaging, approvals, and recovery across languages and platforms.
Prerequisites
Dapr CLI, Docker or Kubernetes runtime, application language SDK or HTTP/gRPC client
Installation
Requirements and caveats from upstream:
- [![Go Report][go-report-badge]][go-report-url] [![OpenSSF][openssf-badge]][openssf-url] [![Docker Pulls][docker-badge]][docker-url] [![Build Status][actions-badge]][actions-url] [![Test Status][e2e-badge]][e2e-url] [!...
- [docker-badge]: https://img.shields.io/docker/pulls/daprio/daprd?style=flat&logo=docker
- [docker-url]: https://hub.docker.com/r/daprio/dapr
Basic usage or getting-started notes:
- Dapr is an open-source runtime for building distributed applications, workflows, and AI agents. It provides durable execution, secure service-to-service communication, state management, event-driven messaging, and...
- Whether you're building AI agents, business-critical workflows, microservices, or event-driven systems, Dapr lets you focus on business logic instead of plumbing. Dapr runs as a sidecar, so every capability is availab...
- AI agents need far more than model inference. To run in production they need state, orchestration, recovery, secure communication, and governance.
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/dapr/dapr/HEAD/README.md
Documentation
- https://dapr.io
