How I built Relay: An AST-based latency auditor for Python AI agents

Arclat, a studio focused on developer tools for AI agent teams, has released Relay, an AST-based latency auditor that scans Python AI agent codebases to identify async anti-patterns such as missing awaits, sequential LLM calls that could be parallelized, and blocking I/O inside async functions. The tool suggests fixes and runs as an MCP server, integrating directly with Claude Code to eliminate log files and context switching.

I kept running into the same problem building AI agents. They were slow and I had no idea why. No obvious errors, logs looked fine, but requests were taking way longer than they should. Turns out the codebase was full of async anti-patterns. Missing awaits, sequential LLM calls that could've been parallel, blocking I/O hiding inside async functions. So I built Relay. It uses AST analysis to scan your agent codebase and find exactly these spots. Not just flagging them, it suggests fixes too. And since it runs as an MCP server, it works directly inside Claude Code. No log files, no context switching. pip install relay-arclat or check it out here https://relay.arclat.com built by Arclat, a studio making developer tools for AI agent teams.