a2aproject/a2a-python

Official Python SDK for the Agent2Agent (A2A) Protocol

Hosted by Linux Foundation

View on GitHub ↗Jump to charts ↓Open shareable report →

a2aproject/a2a-python has 2k+ stars and 500+ forks on GitHub, is written in Python, and was last pushed on Oct 17, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 20 minutes ago
Added to GitGenius on October 15th, 2026
Created on May 9th, 2025
Open Issues & Pull Requests: 83 (+0)
GitHub issues: Enabled
Number of forks: 518
Total Stargazers: 2,205 (+0)
Total Subscribers: 27 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 20.7 hours
Mean response time: 5.4 days
90th percentile: 12.0 days
Tracked items: 310

Maintainer activity

52 people did triage or write work on this repository in the last 12 months.

At least 10% of a2a-python's 52 maintainers work at Google. 18 say where they work, and 5 of those are Google.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 18, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits. How this is counted.

How this project is maintained

Practically every issue opened in the past year has drawn a reply. 79% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 84% of issues opened in the past year have been closed, leaving a working backlog. Three people close 60% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 33
New in 7 days: 5
Closed in 7 days: 5
Avg open age: 117 days
Stale 30+ days: 12
Stale 90+ days: 8

Recent activity

Opened in 7 days: 5
Closed in 7 days: 5
Comments in 7 days: 7
Events in 7 days: 42

Top labels

  • component: server (47)
  • status:awaiting response (26)
  • maintainers-only (25)
  • status:stale (24)
  • component: core (17)
  • component: client (16)
  • status: needs review (10)
  • question (9)

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

a2a-python is a Python SDK for building agentic applications as A2A Servers following the Agent2Agent Protocol.

The SDK addresses the need for standardized communication between autonomous agents by implementing the A2A Protocol specification. It provides a framework for building agent applications that can interoperate across different systems and transports. The tool handles protocol compliance, message routing, and agent lifecycle management, allowing developers to focus on agent logic rather than protocol implementation details.

Developers should adopt this SDK if they are building agent-based systems that need to communicate via the A2A Protocol or integrate with other A2A-compliant agents. It suits projects requiring multi-agent coordination, whether deployed as HTTP services, gRPC endpoints, or JSON-RPC servers. The SDK's modular design means you can install only the components you need—the core library alone, or with optional integrations for FastAPI, gRPC, OpenTelemetry tracing, and SQL database backends including PostgreSQL, MySQL, and SQLite. The tool supports both the current protocol specification and maintains backward compatibility with an earlier version, making it suitable for both new projects and those migrating from older implementations.

The project maintains active development with regular updates addressing protocol compliance and feature additions. The codebase includes comprehensive examples demonstrating common patterns, and the maintainers provide migration documentation for users upgrading between major versions. The SDK is built on asynchronous Python primitives, enabling high-performance concurrent agent operations. The project's extensibility is a core design principle, allowing custom implementations of communication protocols and database backends beyond the included integrations.