5 ways to connect AI agents across frameworks with the A2A protocol (26.4k stars)
goyalshaliniuk · x · 2026-11-05
A2A (Agent2Agent) is an open protocol hosted by the Linux Foundation (26.4k GitHub stars) that lets agents built on LangGraph, CrewAI, Semantic Kernel or custom stacks communicate, delegate tasks, and exchange results — without exposing internal memory, tools, or proprietary logic. The author walks through 5 uses:
- Agent discovery via Agent Cards describing capabilities and skills.
- Task delegation: a coordinator agent assigns sub-tasks to specialized agents (research, coding, analysis) and gets results back.
- Messages & artifacts: structured messages, task updates, and exchange of generated files/reports across agents.
- Async long-running tasks: task states (submitted/working/completed/failed) let clients poll progress without holding connections open.
- Real-time streaming: SSE-based progress updates for live research assistants, coding agents, and interactive workflows.
A2A complements MCP: MCP connects agents to tools and data, A2A connects agents to agents.
More from coding & agent
- GitHub Next's PDD Kit uses formal methods to prove AI-generated web app code is correct — 0xkarasy · 2026-11-05
- Meta's JiTTesting deploys LLM-generated tests to catch bugs pre-merge, cutting human review 70% — AxSaucedo · 2026-11-05
- Built an app in a weekend with AI, now spending 3 weeks figuring out what it does — kylegawley · 2026-11-05
- Developer seeks open-source guardrails against malicious file uploads to LLM chatbots — SnooCupcakes982 · 2026-11-05
- Dev predicts 180Hz screen-frame models will make vibe coders obsolete within a year — ryunuck · 2026-11-05
- Agents ace isolated tasks but drop to ~38% at maintaining codebases over time — FullStackFrenzy · 2026-11-05