Skip to content

Python A2A is a powerful, easy-to-use library for implementing Google's [Agent-to-Agent (A2A) protocol](https://google.github.io/A2A/). It enables seamless communication between AI agents, creating interoperable agent ecosystems that can collaborate to solve complex problems.

active 2025-04-102026-07-03 (UTC)

Partial coverage11,258 / 11,987 hourly files (94%) · 2 absent upstream · 726 failed, retryable2025-03-292026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
742
Pushes
36
Pull requests
15
Issues
46
Stars
490
Forks
72

Activity over time

Daily event counts in the loaded window

Line chart, 450 days from 2025-04-10 to 2026-07-03. Pushes: 36 total, peak 16 in a day. Pull requests: 15 total, peak 3 in a day. Issues: 46 total, peak 7 in a day. Comments: 53 total, peak 11 in a day. Stars: 490 total, peak 76 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#92failsafesecurity2026-07-03 02:26
    fix: replace CORS wildcard with explicit origin allowlist
  • Issue comment#91Joshua-Medvinsky2026-05-24 01:36
    fix: add optional API key authentication to all mutating HTTP endpoints
  • Issue#84codyz1232026-03-07 22:26
    Integration idea: Schelling Protocol for agent discovery & coordination
  • Issue#83magicbrighter2025-12-10 10:24
    Add Unified HTTP Request Path Prefix for a2a Server
  • Issue#80harshays982025-09-09 08:30
    How to pass timeout parameters if an agent taking time to respond
  • Pull request#792qov3b2025-09-07 09:15
  • Issue comment#74themanojdesai2025-09-06 08:17
    MCPToolConversionError: Failed to get tools from MCP server: 404
  • Issue comment#66themanojdesai2025-09-06 08:16
    Fail to connect with A2A demo/ui
  • Issue#66themanojdesai2025-09-06 08:16
    Fail to connect with A2A demo/ui
  • Issue comment#66themanojdesai2025-09-06 08:14
    Fail to connect with A2A demo/ui
  • Issue#77themanojdesai2025-09-06 08:13
    Not fully compatible with A2A
  • Issue comment#77themanojdesai2025-09-06 08:13
    Not fully compatible with A2A
  • Issue comment#77themanojdesai2025-09-06 08:12
    Not fully compatible with A2A
  • Issue comment#66taoari2025-08-31 07:44
    Fail to connect with A2A demo/ui
  • Issue comment#74JayantSeth2025-07-22 16:52
    MCPToolConversionError: Failed to get tools from MCP server: 404
  • Issue comment#50ghalibansari2025-07-18 17:45
    langgraph can use A2A?
  • Issue comment#74furas2025-07-18 11:36
    MCPToolConversionError: Failed to get tools from MCP server: 404
  • Issue#74JayantSeth2025-07-18 04:15
    MCPToolConversionError: Failed to get tools from MCP server: 404
  • Issue comment#66insanesac2025-06-13 06:32
    Fail to connect with A2A demo/ui
  • Issue#67shriyanskapoor2025-06-10 09:39
    How to support langgraph's short term memory?
  • Issue comment#66tobegit3hub2025-06-09 23:11
    Fail to connect with A2A demo/ui
  • Issue comment#60themanojdesai2025-06-09 15:32
    connect to other A2A agent with python-a2a sdk issue.
  • Issue#58themanojdesai2025-06-09 15:32
    Cannot connect from external google/A2A client to A2AServer of this framework
  • Issue#65leotraven2025-06-09 15:27
    FastAPI app that serves as MCP server (used by FastMCP) does not expose proper endpoint
  • Issue#64rgstephens2025-06-08 15:19
    Add LiteLLM Support

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 490 stars here means stars gained during the window, not the repo's star count.