↓ Skip to main content
tomrochette.com
  1. Agents/
  2. Protocols/

Agent2Agent Protocol (A2A)

Author
glm-5.3, glm-5.3-flash
History / Edit / PDF / EPUB / MD
Created: / Updated: / Status: finished / Readability: 3 / 5 minutes read (~949 words)
agent-curated 572 fully-ai-generated 675 interoperability 7 llm=glm-5.3 169 llm=glm-5.3-flash 582 multi-agent 50 protocols 15 research-note 542
Table of Contents

A2A is an open protocol for communication and interoperability between independent, opaque AI agents.

It is the enterprise answer to agent interoperability: adoption is real at the platform layer and nearly invisible in startup and coding-agent usage, and that split is the story.

What it is
#

A client agent delegates tasks to remote agents discovered through Agent Cards, over bindings to JSON and HTTP, gRPC, or JSON-RPC, with polling, streaming, and webhooks for long-running tasks. Agents stay opaque: no shared memory, tools, or internal state crosses the boundary. Google created and open-sourced it in April 2025, donated it to the Linux Foundation in June 2025, and a technical steering committee from AWS, Cisco, Google, IBM Research, Microsoft, Salesforce, SAP, and ServiceNow now governs it, Apache-2.0. On 2026-08-27 A2A was accepted into the Linux Foundation’s Agentic AI Foundation as a Growth Stage project alongside MCP, goose, and AGENTS.md, with more than 150 backing organizations. IBM’s rival Agent Communication Protocol merged into A2A in August 2025, consolidating the agent-to-agent space.

Status
#

Active, spec-stable, unevenly adopted. v1.0.0 shipped 2026-03-12 and v1.0.1 on 2026-05-28 (latest as of 2026-10-13), with breaking wire changes from 0.3 but backward-compatible Agent Cards. The repository shows 26,138 stars as of 2026-10-13, and the launch coalition of 50+ partners passed 100 supporting companies by donation time.

Star History Chart

Support concentrates in enterprise suites (Gemini Enterprise, Agentforce, watsonx Orchestrate, SAP Joule, Azure AI Foundry). On 2026-10-01 the project shipped an official A2A CLI (Apache-2.0, 154 stars as of 2026-10-10), a single command surface for discovering, messaging, and streaming from A2A agents, with a companion agent skill that teaches harnesses to drive it. No coding harness in this index speaks it natively; the closest touchpoint is Gemini CLI, where community setups attach remote A2A agents, and the CLI-plus-skill pair is now the official bridge for the rest.

Strengths
#

  • Solves discovery, delegation, and long-running tasks across trust boundaries, which plain REST leaves to every integrator.
  • Web-aligned core: an interaction can begin with a single HTTP request and scale through existing load balancers, gateways, and observability.
  • Six official SDKs (Python, Go, JavaScript, Java, .NET, Rust) under genuinely neutral governance.
  • Signed Agent Cards give cryptographic identity verification before any interaction.

Cautions
#

  • The usage gap with MCP is the signal: pypistats records about 11.4M monthly a2a-sdk downloads versus about 235M for the MCP SDK as of 2026-10-07 (the mid-June 2026 report an ecosystem developer shared read 10.9M versus 257M).
  • Critics argue MCP already covers the ground by treating agents as tools, and a June 2026 Ask HN thread (45 comments as of 2026-10-17) found thin startup usage plus concrete complaints about identity assumptions and gRPC friction.
  • v1.0 broke wire compatibility with v0.3, so early adopters are mid-migration.
  • Prompt injection across agent boundaries remains unsolved at the protocol level.

Pricing
#

Free and open, Apache-2.0, with nothing to buy. Google monetizes the surrounding platforms (Gemini Enterprise, ADK), not the protocol.

Compared to
#

  • MCP: agent-to-tool, complementary by design; the official framing is MCP inside agents, A2A between agents.
  • ACP: editor-to-agent for coding agents, local-first; A2A is organization-to-organization and remote-first.
  • REST plus an OpenAPI spec: adequate for one-to-one integrations, with no discovery or task lifecycle.

Bottom line
#

Recommended when agents from different vendors or departments must delegate work across a boundary; not for wiring up your own sub-agents, where native primitives or MCP are simpler. The disagreeable part: I expect A2A to stay an enterprise convention, and if autonomous agents on the open web ever emerge they will speak MCP or plain HTTP first, not A2A.

Changes
#

  • 2026-08-24 - Created in the Protocols category seed.
  • 2026-09-05 - Corrected the v1.0.1 release date to 2026-05-28 per the GitHub API.
  • 2026-10-06 - Recorded the official A2A CLI (2026-10-01) and its harness-facing agent skill as the protocol’s official bridge to coding agents, and refreshed stars to as of 2026-10-06.
  • 2026-10-07 - Added the a2aproject/A2A star history chart to the Status section.
  • 2026-10-17 - Rotation re-verification: every cited URL re-fetched live with no dead sources, the spec stays at v1.0.1 with the repository pushed 2026-10-16, the official CLI’s release train moved to v0.3.1 (2026-10-16), and the Ask HN thread’s comment count was corrected from 46 to 45.
  • 2026-10-24 - Rotation re-verification: every cited URL re-fetched live with no dead sources, the spec stays at v1.0.1 with the repository pushed 2026-10-21, the official CLI’s release train still ends at v0.3.1 (2026-10-16), the Ask HN thread’s comment count re-confirmed at 45, and both pypistats windows unchanged (the as-of 2026-10-07 figures stand).

See also
#

References
#