# CodSpeed (ChatGPT App)

> Optimize code performance

- Type: app
- Publisher: CodSpeed (official)
- Categories: Development
- Website: https://chatgpt.com/plugins/plugin_asdk_app_6ab6de6dd34c8191afd2b8eebdc9cfed
- Open in ChatGPT: https://chatgpt.com/plugins/plugin_asdk_app_6ab6de6dd34c8191afd2b8eebdc9cfed
- Version: 1.0.0
- Listed: 2026-10-04

## About

CodSpeed helps users optimize code with measured performance data. Inspect benchmark runs, compare changes, and analyze flamegraphs to find bottlenecks and verify improvements. The plugin also includes skills for setting up benchmarks and guiding iterative optimization.

## How to use

1. **Add it in ChatGPT** Open CodSpeed in ChatGPT's Plugin directory (button above), select + to add it and sign in if asked.

2. **Use it in a chat** Type @ in the composer and pick CodSpeed, or start your message with its name. ChatGPT may also suggest it when it fits what you ask.

## Skills

- **codspeed-optimize**: Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement. Use this skill whenever the user wants to make code faster, reduce CPU usage, optimize memory, improve throughput, find performance bottlenecks, or asks to 'optimize', 'speed up', 'make faster', 'reduce latency', 'improve performance', or points at a CodSpeed benchmark result wanting improvements. Also trigger when the user mentions a slow function, a regression, or wants to understand where time is spent in their code.
- **codspeed-setup-harness**: Set up performance benchmarks and CodSpeed harness for a project. Use this skill whenever the user wants to create benchmarks, add performance tests, set up CodSpeed, configure codspeed.yml, integrate a benchmarking framework (criterion, divan, pytest-benchmark, vitest bench, go test -bench, google benchmark), or when the user says 'add benchmarks', 'set up perf tests', 'create a benchmark', 'benchmark this', or wants to measure performance of their code for the first time. Also trigger when the optimize skill needs benchmarks that don't exist yet.

## Example prompts

- "Which function regressed in our latest release? Compare with the previous release and inspect the flamegraph."
- "Improve this project's performance: benchmark it, optimize the hottest code path, and measure the gain."
- "Analyze this PR's performance impact: compare it with the base branch and explain regressions and gains."

## Related

- [GitHub](https://chatgptplugins.directory/apps/github.md): Triage PRs, issues and CI across your repositories
- [Figma](https://chatgptplugins.directory/apps/figma.md): Create designs, diagrams and FigJam boards and ship them to code
- [MCP App Basics (Apps SDK example)](https://chatgptplugins.directory/apps/apps-sdk-mcp-app-basics.md): Eleven interactive widgets that each teach one MCP Apps API
- [Cards Against AI (Apps SDK example)](https://chatgptplugins.directory/apps/apps-sdk-cards-against-ai.md): Card game driven by ChatGPT with a real-time synced widget
- [Authenticated Server (Apps SDK example)](https://chatgptplugins.directory/apps/apps-sdk-authenticated.md): Demonstrates tools that require different levels of OAuth
- [Shopping Cart (Apps SDK example)](https://chatgptplugins.directory/apps/apps-sdk-shopping-cart.md): Keeps cart state in sync across tool calls with widgetSessionId

---
Source: https://chatgptplugins.directory/apps/codspeed · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.