Your AI agent is
Relay shows you exactly why.
A latency profiler that reads your agent codebase, ranks every bottleneck by the time it costs, and applies the fix — all from a single Claude Code conversation.
Profiling that lives in your editor
[ capabilities · 06 ]Runs inside Claude Code
No browser tab, no upload flow. Relay is an MCP server that lives in the editor you already work in.
Reads your actual code
AST analysis over your real .py source — not logs, not traces, not guesses. The true source of bottlenecks.
Ranked by time cost
Findings sorted by the milliseconds they cost, so you fix what matters instead of chasing micro-optimizations.
One-command fixes
Ask Claude Code to apply a fix and Relay patches the file in place, with a diff you approve first.
CI-ready engine
Wire the same engine into a GitHub Action and fail the build when a change regresses agent latency.
Your code stays yours
Analysis runs locally through the MCP server. Only usage metadata syncs — never your source.
Install to fix in under a minute
[ workflow ]Add one config block
Drop the Relay MCP entry into your Claude Code config and paste your API key.
Ask for an audit
Relay parses your code and returns every bottleneck, ranked by the time it costs.
Apply the fixes
Review the ranked findings, then let Relay patch the ones you approve, right in the editor.
Join the waitlist
Be among the first developers to run Relay. Early access, exclusive updates, and a say in what we build next.
- early access before public launch
- priority onboarding & updates
- influence upcoming features
Questions
[ faq ]An MCP server that identifies, ranks, and fixes latency bottlenecks in AI agent code directly inside Claude Code. It is a product of the Arclat studio.
Stop guessing where the latency is.
Join the Relay waitlist and get a ranked audit of your agent codebase, right inside Claude Code.