#40 · Primary category: MLOps & Evaluation
oha
Ohayou(おはよう), HTTP load generator, inspired by rakyll/hey with tui animation.
Project last updated:08/23/26
GitHub Stars
10.5K
Forks
296
Contributors
54
License
MIT
Why we included this project
oha is a small, single-binary command-line tool for load testing: you point it at a web endpoint and it fires a configurable stream of requests while showing progress in a live terminal dashboard. The output covers throughput, latency percentiles, and timing details, which is what you need when estimating how much traffic a service can actually handle or comparing two deployments side by side. It works over HTTP/1 and HTTP/2 by default, with rate limiting built in and experimental HTTP/3 available behind a feature flag. The real-time TUI is part of the point: you can watch a run progress and spot problems before it finishes instead of waiting for a final report. Teams that want a quick, repeatable benchmark without pulling in a heavy toolchain will find.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, FLUX and more.
LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
airflow
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
langfuse
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
netron
Visualizer for neural network, deep learning and machine learning models