a2a-sdk
A2A Python SDK
Decision gist · record as of 2026-08-14
Yes. The SDK is actively maintained, has no known vulnerabilities, uses a permissive Apache 2.0 license, and requires only standard ecosystem dependencies. It is well-suited for anyone building agent-to-agent communication systems that need to follow a standardized protocol. The optional extras allow you to scale from simple local agents to distributed, observable, persistent deployments. Start with the core install and add extras as your use case demands.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; the SDK is built on async Python and expects familiarity with asynchronous programming patterns.
- Low friction install with a pure-Python wheel.
- Active maintenance with a release 23 days old and recent commits.
License · maintenance · safety
Apache-2.0 (permissive) — Apache 2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for proprietary agent applications.
last release 2026-07-22 (23 days) · last repo commit 2026-08-13 · 2,079 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 12,367,877 downloads/mo, #1,323 on PyPI
Alternatives
Verify before relying
pip install a2a-sdk
from a2a_sdk import Agent
agent = Agent()
# Define agent capabilities and handlers- Whether the optional integrations (FastAPI, gRPC, OpenTelemetry, SQL drivers) are included in the core install or require separate extras.
- Performance characteristics and throughput limits for typical agentic workloads.
- Maturity and stability of the A2A Protocol specification itself, given the SDK is at version 1.1.2 and the protocol at 1.0.
What it is and what it does
The A2A SDK is a Python library for building agentic applications that follow the Agent2Agent (A2A) Protocol specification. It provides a framework for agents to communicate asynchronously over multiple transports—JSON-RPC, HTTP+JSON/REST, and gRPC—with built-in support for modern async Python. The core library is lightweight, but the SDK includes optional integrations for HTTP servers (FastAPI, Starlette), distributed tracing (OpenTelemetry), and SQL persistence (PostgreSQL, MySQL, SQLite), allowing you to compose a deployment stack suited to your needs.
The SDK is maintained actively and supports Python 3.10 through 3.14. It implements the A2A Protocol specification version 1.0 with backward compatibility for 0.3, so agents built with this SDK can interoperate with other A2A-compliant implementations. The 8 core runtime dependencies are all established ecosystem packages, and the install is low-friction.
Use it for
- Build a microservice-based agent system where agents communicate over HTTP or gRPC following a standardized protocol.
- Implement an agent that exposes itself as a JSON-RPC server for remote clients to invoke its capabilities.
- Create an agentic application with distributed tracing and observability using OpenTelemetry integration.
- Deploy agents with persistent state backed by PostgreSQL, MySQL, or SQLite without writing custom storage logic.
- Develop multi-agent workflows where agents coordinate via the A2A Protocol across different network transports.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The SDK is actively maintained, has no known vulnerabilities, uses a permissive Apache 2.0 license, and requires only standard ecosystem dependencies. It is well-suited for anyone building agent-to-agent communication systems that need to follow a standardized protocol. The optional extras allow you to scale from simple local agents to distributed, observable, persistent deployments. Start with the core install and add extras as your use case demands.
Install
a2a-sdk on PyPI
Before you install
Low friction install with a pure-Python wheel. Active maintenance with a release 23 days old and recent commits. The 8 runtime dependencies are standard ecosystem packages (pydantic, protobuf, httpx, google-api-core), suggesting a stable, well-integrated foundation.
Requires Python 3.10 or later; the SDK is built on async Python and expects familiarity with asynchronous programming patterns.
License in practice
Apache 2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for proprietary agent applications.
Quickstart
pip install a2a-sdk
from a2a_sdk import Agent
agent = Agent()
# Define agent capabilities and handlersVerify before relying
- Whether the optional integrations (FastAPI, gRPC, OpenTelemetry, SQL drivers) are included in the core install or require separate extras.
- Performance characteristics and throughput limits for typical agentic workloads.
- Maturity and stability of the A2A Protocol specification itself, given the SDK is at version 1.1.2 and the protocol at 1.0.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 8 packagesculsansgoogle-api-coregoogleapis-common-protoshttpxjson-rpcpackagingprotobufpydantic |
| Maintenance | Actively maintained 23 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 12,367,877 / month, #1,323 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Software Development :: Libraries :: Python Modules |
Evidence: a2a_sdk-1.1.2-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “agent to agent protocol python”
- a2a-sdkA Python SDK for building agentic applications that communicate via…
- elastic-agent-clientA Python client library for communicating with Elastic Agent,…
- agent-framework-a2aEnables communication with remote A2A-compliant agents and allows…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also agent-framework-a2a · fasta2a · a2ui-agent-sdk · bedrock-agentcore · agent-client-protocol · a2a · dapr · traia-iatp · ag2 · ag_ui_adk