dapr
Dapr is the durable execution runtime for workflows and AI agents. A graduated CNCF project whose APIs keep work running through crashes, restarts, and outages.
dapr at a Glance
- How you use it
- APIs over HTTP or gRPC, with applications running on Kubernetes or self-hosted
- Who it's for
- Developers building distributed applications and AI agents
- Works with
- Kubernetes RabbitMQ Kafka Microsoft Azure AWS Google Cloud
dapr Key Features
- agent execution recovery
- durable workflows
- pub/sub messaging
- service invocation
- state management
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
dapr Alternatives
sandbox-agent
A durable process per agent, with memory that survives restarts - rivet-dev/agents
reshapr
reShapr is the open source runtime that turns your existing REST, GraphQL, and gRPC APIs into governed, LLM-optimized MCP tools, without rebuilding them.
Inferable
Open-source agent runtime for building distributed automations
k8e
K8E is an open-source Agentic AI Sandbox Matrix — a CNCF-conformant Kubernetes distribution in a single binary under 100MB, built to run untrusted AI agent code in isolated gVisor, Kata or Firecracker sandboxes with persistent PVC workspaces.
Open Multi-Agent
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it. - open-multi-agent/open-multi-agent
Activepieces
Chat, agents, flows, tables, and 770+ apps in one workspace, so your whole team works with AI in the tools they already use. Open source at the core.