Dapr Agents

Python framework for LLM-powered agents, built on the Dapr distributed systems runtime.

Infrastructure by Dapr (CNCF)

IndexedApache-2.0★ 764

Install

Pick your client. Read the repository before you give any tool access to your data.

pip install dapr-agents

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Dapr Agents is a developer framework for building production-grade resilient AI agent systems, built on the Dapr project. Agent tasks run on Dapr's durable workflow engine, so failed tasks are retried and recover their state. It is Kubernetes-native, can scale agents to zero and connects to over 50 enterprise data sources. The project is vendor-neutral and open source.

Use cases: agent-orchestration, backend-development

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category: Durable execution · agent runtime
Self-host: Yesraw.githubusercontent.com
Open source: Yesraw.githubusercontent.com
Works with: claude-agent-sdkdocs.dapr.io
Protocols: mcp

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Signals

Stars: 764
Forks: 157
Open issues: 30
Weekly downloads: 7,086
Last commit: Oct 22, 2026 (5 days ago)
Last release: Oct 9, 2026 (19 days ago)
Last package publish: Oct 9, 2026 (19 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Packages: pypi dapr-agents
License: Apache-2.0
Repository: github.com/dapr/dapr-agents
Website: docs.dapr.io/developing-ai/dapr-agents/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README Website github-graphql