function: benchmarking
824 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| AlexsJones/llmfit llmfit is a Rust-based terminal tool (TUI and CLI) that matches LLM models to your hardware by detecting RAM, CPU, and GPU and scoring mode… | 78 | 34236 | active |
| grafana/k6 Grafana k6 is an open-source load and performance testing tool with a Go-based engine and tests written in JavaScript or TypeScript. It sup… | 98 | 31327 | stable |
| GoogleChrome/lighthouse Lighthouse is an open-source automated auditing tool from Google that analyzes web pages for performance, accessibility, SEO, and best prac… | 97 | 30702 | active |
| sharkdp/hyperfine Hyperfine is a cross-platform command-line benchmarking tool written in Rust. It runs shell commands multiple times, performs statistical a… | 65 | 28741 | stable |
| locustio/locust Locust is an open-source load and performance testing framework where test scenarios are written in plain Python code. It supports distribu… | 95 | 28104 | active |
| tsenart/vegeta Vegeta is a versatile HTTP load testing tool and Go library that drills HTTP services with a constant request rate. It is usable both as a … | 58 | 25166 | stable |
| trycua/cua Cua is an open-source framework for computer-use agents, providing background desktop drivers, disposable GUI sandboxes, cross-OS fleets (L… | 83 | 21922 | active |
| recommenders-team/recommenders A Python library and collection of Jupyter notebooks with best practices for building, evaluating, and operationalizing recommendation syst… | 67 | 21864 | active |
| aidenybai/react-scan React Scan is a drop-in tool that automatically detects and visually highlights React component performance issues, such as unnecessary re-… | 68 | 21799 | active |
| catchorg/Catch2 Catch2 is a modern, C++-native unit testing framework supporting TDD and BDD styles, with no external dependencies. It also provides basic … | 95 | 21444 | stable |
| hey hey is a small command-line HTTP load generator written in Go, originally named boom and designed as a replacement for ApacheBench (ab). It… | 59 | 20242 | stable |
| brendangregg/FlameGraph The original open-source FlameGraph tools by Brendan Gregg, a set of Perl scripts that convert profiler stack traces into interactive SVG f… | 23 | 19695 | stable |
| probelabs/goreplay GoReplay is an open-source CLI tool written in Go that captures live HTTP traffic from production servers and replays it against test envir… | 52 | 19318 | active |
| openai/evals OpenAI Evals is a Python framework for evaluating large language models and LLM-based systems, with an open-source registry of benchmark ev… | 66 | 19262 | active |
| vitest-dev/vitest Vitest is a next-generation JavaScript/TypeScript testing framework built on top of Vite, offering Jest-compatible APIs with fast watch mod… | 95 | 17013 | stable |
| wolfpld/tracy Tracy is a real-time, nanosecond-resolution, hybrid frame and sampling profiler for games and other applications. It supports CPU and GPU p… | 99 | 16669 | stable |
| winsiderss/systeminformer System Informer (formerly Process Hacker) is a free, open-source, multi-purpose Windows tool for monitoring system resources, debugging sof… | 67 | 15701 | active |
| vibrantlabsai/ragas Ragas is a Python library for evaluating LLM applications with objective, LLM-driven metrics and systematic experiment loops. It also gener… | 71 | 15485 | active |
| benfred/py-spy py-spy is a sampling profiler for Python programs written in Rust. It visualizes where a running Python process spends time without restart… | 81 | 15445 | stable |
| bloomberg/memray Memray is a memory profiler for Python that tracks memory allocations in Python code, native C/C++ extension modules, and the interpreter i… | 94 | 15204 | active |
| optuna/optuna Optuna is an open-source Python hyperparameter optimization framework with a define-by-run API for dynamically constructing search spaces. … | 90 | 14713 | active |
| EleutherAI/lm-evaluation-harness A Python framework for few-shot evaluation of language models across hundreds of standard benchmarks (HellaSwag, MMLU, BIG-Bench, etc.). It… | 89 | 13803 | active |
| DLR-RM/stable-baselines3 Stable Baselines3 is a Python library providing reliable, well-tested PyTorch implementations of reinforcement learning algorithms with a u… | 91 | 13728 | stable |
| plasma-umass/scalene Scalene is a high-performance CPU, GPU, and memory profiler for Python that runs much faster than many alternatives while providing detaile… | 92 | 13495 | active |
| ShishirPatil/gorilla Gorilla is a UC Berkeley research project for training and evaluating LLMs to make function/tool calls, including the OpenFunctions fine-tu… | 54 | 13006 | active |
| taskflow/taskflow Taskflow is a header-only C++ library for building task-parallel programs using task dependency graphs, with a work-stealing executor for C… | 86 | 12126 | stable |
| dotnet/BenchmarkDotNet BenchmarkDotNet is a powerful .NET library for benchmarking that transforms methods into benchmarks and produces reliable, statistically so… | 85 | 11484 | stable |
| google/dopamine Dopamine is a research framework from Google for fast prototyping of reinforcement learning algorithms, built around a small, easily readab… | 56 | 10900 | active |
| hatoo/oha oha is a small HTTP load generator written in Rust, inspired by rakyll/hey, that sends load to a web application and displays results in a … | 95 | 10510 | active |
| google/benchmark Google Benchmark is a C++ microbenchmarking library for timing small code snippets, with an API similar to unit test frameworks. It support… | 83 | 10370 | stable |
| vwxyzjn/cleanrl CleanRL is a deep reinforcement learning library providing high-quality, single-file implementations of algorithms like PPO, DQN, DDPG, TD3… | 58 | 10326 | active |
| xmrig/xmrig XMRig is a high-performance, open-source, cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight, and GhostRider algorithms, plus a … | 87 | 10097 | active |
| mshumer/gpt-prompt-engineer A Jupyter Notebook-based tool that automatically generates, tests, and ranks LLM prompts for a given task using GPT-4, GPT-3.5-Turbo, or Cl… | 50 | 9675 | active |
| apache/jmeter Apache JMeter is a 100% Java open-source application for load testing and measuring the performance of web applications and other services.… | 66 | 9518 | stable |
| google/pprof pprof is a tool for visualization and analysis of profiling data stored in profile.proto format. It generates text and graphical reports (f… | 77 | 9273 | active |
| async-profiler/async-profiler A low-overhead sampling profiler for Java applications built on HotSpot's AsyncGetCallTrace API and Linux perf_events. It profiles CPU time… | 93 | 9124 | stable |
| onsi/ginkgo Ginkgo is a mature BDD-style testing framework for Go that builds on Go's native testing package. It provides an expressive DSL for structu… | 98 | 9043 | stable |
| flightlessmango/MangoHud MangoHud is a Vulkan and OpenGL overlay that displays real-time performance metrics like FPS, frametimes, CPU/GPU load, and temperatures in… | 90 | 8981 | active |
| HypothesisWorks/hypothesis Hypothesis is the property-based testing library for Python, generating randomized test inputs from user-described strategies and shrinking… | 95 | 8913 | stable |
| esnet/iperf iperf3 is a command-line tool for actively measuring the maximum achievable bandwidth on IP networks over TCP, UDP, and SCTP. It reports th… | 80 | 8718 | active |
| HKUDS/ClawWork ClawWork is an open-source benchmark and framework that turns AI assistants into 'AI coworkers' which must earn income by completing real p… | 47 | 8522 | active |
| mcollina/autocannon A fast HTTP/1.1 benchmarking and load-testing tool written in Node.js, inspired by wrk and wrk2. It can be used from the command line or pr… | 60 | 8502 | stable |
| jesse-ai/jesse Jesse is an open-source Python framework for researching, backtesting, optimizing, and live-trading cryptocurrency trading strategies. It i… | 77 | 8380 | active |
| wg/wrk wrk is a modern HTTP benchmarking tool that generates significant load from a single multi-core machine using a multithreaded design with e… | 32 | 40394 | maintenance |
| TechEmpower/FrameworkBenchmarks The TechEmpower Framework Benchmarks (TFB) project, a suite that measures and compares the performance of web application frameworks across… | 10 | 8105 | active |
| joerick/pyinstrument pyinstrument is a call stack profiler for Python that helps identify why code is slow. It supports profiling scripts, async code, Django ap… | 92 | 8006 | active |
| davebcn87/pi-autoresearch A pi extension that runs autonomous optimization loops: try an idea, benchmark it, keep improvements, and revert regressions. Inspired by k… | 76 | 7868 | active |
| github/scientist Scientist is a Ruby library for carefully refactoring critical code paths by running old and new implementations side by side in production… | 47 | 7754 | stable |
| gaogaotiantian/viztracer VizTracer is a low-overhead debugging and profiling tool that traces and visualizes Python code execution on an interactive timeline. It re… | 80 | 7725 | active |
| OpenMathLib/OpenBLAS OpenBLAS is an optimized open-source implementation of the BLAS (Basic Linear Algebra Subprograms) library, based on GotoBLAS2, with LAPACK… | 93 | 7563 | stable |
| jepsen-io/jepsen Jepsen is a Clojure library and framework for verifying the correctness of distributed systems under fault injection. It sets up systems on… | 89 | 7481 | active |
| krausest/js-framework-benchmark A benchmark suite comparing the rendering performance of ~186 JavaScript web frameworks by measuring DOM table operations, memory usage, an… | 92 | 7470 | active |
| open-compass/opencompass OpenCompass is a Python-based evaluation platform and toolkit for benchmarking large language models across 100+ datasets, supporting model… | 96 | 7365 | active |
| GoogleChrome/lighthouse-ci Lighthouse CI is a suite of tools for continuously running, saving, retrieving, and asserting against Lighthouse audit results in a CI pipe… | 67 | 7060 | active |
| TheTom/turboquant_plus TurboQuant+ is a Python reference implementation of the TurboQuant KV cache compression method (ICLR 2026), using PolarQuant codebooks and … | 56 | 7006 | active |
| gatling/gatling Gatling is an open-source, code-first load testing tool and performance engineering platform. It uses a fully asynchronous, non-blocking ar… | 77 | 6953 | stable |
| ai/size-limit Size Limit is a performance budget tool for JavaScript that calculates the real cost (size and execution time) of your app or library and f… | 92 | 6941 | stable |
| doctest/doctest doctest is a single-header C++ testing framework for unit tests and TDD, supporting C++11 through C++23. It is designed to be the fastest f… | 92 | 6854 | stable |
| codesenberg/bombardier Bombardier is a fast cross-platform HTTP(S) benchmarking tool written in Go, built on fasthttp with an optional net/http client for HTTP/2.… | 79 | 6828 | active |
| NicolasHug/Surprise Surprise is a Python scikit for building and analyzing recommender systems that work with explicit rating data. It provides ready-to-use pr… | 70 | 6808 | stable |
| akopytov/sysbench sysbench is a scriptable, multi-threaded benchmark tool built on LuaJIT, most commonly used for OLTP database benchmarks against MySQL and … | 27 | 6781 | stable |
| jlfwong/speedscope speedscope is a fast, interactive web-based viewer for performance profiles that imports data from many profilers across languages like Jav… | 73 | 6730 | stable |
| pathwaycom/arc-task-gen A Python tool that generates original ARC-AGI-1-style puzzle tasks distribution-matched to the public evaluation set. It produces tasks in … | 56 | 6665 | active |
| masonr/yet-another-bench-script YABS is a self-contained bash script that benchmarks Linux servers by running fio for disk I/O, iperf3 for network throughput, and Geekbenc… | 73 | 6653 | active |
| DEAP/deap DEAP is a Python framework for evolutionary computation that supports genetic algorithms, genetic programming, evolution strategies, and mu… | 67 | 6436 | stable |
| google/perfetto Perfetto is an open-source suite of SDKs, daemons, and tools for production-grade system profiling, app tracing, and trace analysis on clie… | 95 | 6393 | stable |
| axboe/fio Fio is a flexible I/O benchmarking and workload simulation tool that spawns threads or processes performing user-defined I/O patterns via j… | 83 | 6345 | stable |
| JoeDog/siege Siege is an open-source HTTP load testing and benchmarking utility written in C. It simulates many concurrent users hitting one or many URL… | 87 | 6213 | active |
| alexcasalboni/aws-lambda-power-tuning AWS Lambda Power Tuning is an open-source tool built on AWS Step Functions that benchmarks Lambda functions across different memory configu… | 76 | 6052 | active |
| flamegraph-rs/flamegraph A Rust-powered flamegraph generator and cargo subcommand built on the Inferno library, profiling arbitrary binaries without Perl or pipes. … | 98 | 6014 | active |
| microsoft/ethr Ethr is a cross-platform network performance measurement tool written in Go that measures bandwidth, connections/s, packets/s, latency, los… | 63 | 5866 | active |
| AgentOps-AI/agentops AgentOps is a Python SDK and observability platform for monitoring, debugging, and evaluating AI agents and LLM applications. It auto-instr… | 72 | 5797 | active |
| baidu/dperf dperf is a high-performance network traffic generator and load testing tool built on DPDK, capable of tens of millions of HTTP connections … | 66 | 5601 | active |
| google/bloaty Bloaty is a size profiler for binaries that shows what is taking up space inside an executable. It uses custom ELF, DWARF, and Mach-O parse… | 61 | 5536 | active |
| Netflix/vmaf VMAF is Netflix's Emmy-winning perceptual video quality assessment algorithm, provided as a standalone C library (libvmaf) with a wrapping … | 91 | 5460 | stable |
| lm-sys/RouteLLM RouteLLM is a Python framework for serving and evaluating LLM routers that route queries between strong and weak models to cut costs. It pr… | 24 | 5408 | active |
| teddysun/across A collection of shell scripts for Linux VPS/server administration, including WireGuard VPN setup, TCP BBR kernel installation, KMS server d… | 66 | 5368 | active |
| KDAB/hotspot Hotspot is a standalone Qt-based GUI for analyzing Linux perf performance data, providing flame graphs, timelines, caller/callee views, and… | 71 | 5140 | active |
| amanusk/s-tui s-tui is a terminal-based UI that graphically monitors CPU temperature, frequency, utilization, and power, and highlights thermal throttlin… | 90 | 5070 | active |
| sitespeedio/sitespeed.io sitespeed.io is an open-source web performance testing and monitoring tool that drives real browsers (Chrome, Firefox, Edge, Safari) to col… | 94 | 5016 | active |
| jazzband/django-silk django-silk (Silk) is a live profiling and inspection tool for the Django framework. It intercepts and stores HTTP requests and database qu… | 94 | 4991 | active |
| Nixtla/statsforecast StatsForecast is a Python library providing fast, scalable implementations of statistical and econometric univariate time series forecastin… | 93 | 4887 | stable |
| pytorch/ignite PyTorch-Ignite is a high-level library for training and evaluating neural networks in PyTorch flexibly and transparently. It provides an En… | 89 | 4778 | stable |
| microsoft/perfview PerfView is a free Windows-based performance-analysis tool for isolating CPU and memory performance issues, with special support for .NET a… | 95 | 4740 | active |
| session-replay-tools/tcpcopy TCPCopy is a TCP stream replay tool that captures live production traffic and replicates it against a test server. It enables realistic str… | 35 | 4675 | stable |
| nolanlawson/fuite fuite is a CLI tool that finds memory leaks in web apps by launching Chrome via Puppeteer, running scenarios (like clicking links and press… | 48 | 4623 | active |
| thirdlayerinc/autoagent AutoAgent is a Python-based meta-agent harness that autonomously builds and iterates on AI agent harnesses. It edits an agent's system prom… | 48 | 4566 | active |
| plasma-umass/coz Coz is a causal profiler for native code written in C/C++ and Rust. It runs performance experiments to predict how optimizing specific line… | 86 | 4532 | active |
| six-ddc/plow Plow is a high-performance HTTP(S) benchmarking tool written in Go, built on fasthttp for maximum throughput. It reports real-time latency … | 73 | 4518 | active |
| salesforce/Merlion Merlion is a Python library from Salesforce providing an end-to-end machine learning framework for time series intelligence, covering forec… | 10 | 4491 | active |
| DistrictDataLabs/yellowbrick Yellowbrick is a Python library of visual diagnostic tools called Visualizers that extend the scikit-learn API using matplotlib. It helps u… | 26 | 4400 | active |
| link1st/go-stress-testing A stress/load testing tool written in Go that simulates concurrent users with goroutines to measure QPS and connection capacity. It support… | 74 | 4399 | active |
| mstange/samply Samply is a command-line sampling CPU profiler for macOS, Linux, and Windows that records profiles of arbitrary commands and displays them … | 67 | 4392 | active |
| EvolvingLMMs-Lab/lmms-eval lmms-eval is a unified Python framework for evaluating large multimodal models across text, image, video, and audio tasks, with 100+ benchm… | 85 | 4377 | active |
| open-compass/VLMEvalKit VLMEvalKit is an open-source Python toolkit for evaluating large vision-language models (LMMs/LVLMs) across 80+ benchmarks with support for… | 62 | 4359 | active |
| MichaelGrupp/evo evo is a Python package with CLI executables and a small library for evaluating, comparing, and plotting trajectory output from odometry an… | 76 | 4309 | stable |
| facebookresearch/nevergrad Nevergrad is a Python toolbox for gradient-free (derivative-free) optimization, providing many optimization algorithms such as NGOpt and di… | 76 | 4204 | active |
| facebookresearch/dlrm A PyTorch-based implementation of the Deep Learning Recommendation Model (DLRM) from Facebook Research, which processes dense and sparse fe… | 60 | 4065 | stable |
| nakabonne/ali ali is a Go-based HTTP load testing CLI tool that generates HTTP traffic against a target URL and plots performance metrics in real time wi… | 60 | 3937 | active |
| MiniProfiler/rack-mini-profiler Rack middleware that displays a speed badge on every HTML page with detailed performance profiling for Ruby web apps. It provides database … | 74 | 3905 | active |
page 1 / 9 next →