The A2A CLI and Rust: The Same Code, Three Ways to Serve It

7.5 relevance

A2A CLI with Rust agents on v1.0, three serving patterns benchmarked

AI/ML dev.to

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For a platform engineer evaluating agent orchestration patterns, this benchmark quantifies the latency trade-offs between native A2A SDK agents, zero-code exec wrappers, and LLM-coordinated agents, directly informing architecture decisions for multi-agent systems.

Key Takeaways

Use `a2a server --exec` to wrap existing CLI tools as A2A agents with sub-5ms overhead, but avoid LLM coordinators for latency-sensitive tasks unless model inference time is acceptable.

The A2A CLI and Rust: The Same Code, Three Ways to Serve It

Summary

The A2A CLI v0.3.1 and Rust SDK (a2a-*-lf crates v0.4.2/0.5.3/0.2.9) serve the same Lucas-Lehmer Mersenne prime test three ways: via the official A2A Rust SDK on port 8104, as a 30-line stdin/stdout program wrapped by `a2a server --exec` on port 8105, and behind an ADK coordinator on Gemini (gemini-3.5-flash/3.8-flash) on port 8106. Benchmarking shows the SDK agent adds 0.55–1.40 ms per call from a Rust client, the exec wrapper adds 3.33–5.05 ms, and the ADK coordinator adds a median 1328–2283 ms due to Gemini latency. All three agents correctly computed primes through N=26.

Author

xbill