Open-source performance software
1333 open-source libraries, tools and applications tagged performance, ranked by how closely performance is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
1333 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| fraillt/bitsery Bitsery is a header-only C++ binary serialization library designed for real-time networking, especially in games. It produces compact, meta… | 49 | 1269 | stable |
| smart-test-ti/SoloX SoloX is a real-time performance data collection tool for Android and iOS applications, gathering metrics like CPU, memory, FPS, network, a… | 23 | 1266 | active |
| benchmark-action/github-action-benchmark A GitHub Action that collects benchmark results from many benchmarking tools and tracks them across CI runs. It stores results on a GitHub … | 91 | 1264 | active |
| VoidStar2077/workspace A lightweight, header-only C++11 asynchronous task execution framework providing dynamic and static thread pools. It supports general async… | 42 | 1261 | active |
| aras-p/ClangBuildAnalyzer A command-line tool that aggregates Clang -ftime-trace JSON reports across a whole C/C++ build and summarizes what took the most compile ti… | 25 | 1261 | stable |
| JosephSilber/page-cache A Laravel package that caches HTTP responses as static HTML files on disk, allowing the web server to serve pages directly without booting … | 61 | 1259 | active |
| AvdLee/Xcode-Build-Optimization-Agent-Skill A collection of open-source Agent Skills that benchmark and optimize Xcode build performance, covering clean and incremental builds, compil… | 70 | 1253 | active |
| pakrym/jab Jab is a compile-time dependency injection container for C# implemented as a Roslyn source generator. It generates strongly-typed service p… | 47 | 1253 | active |
| emeryberger/Hoard Hoard is a fast, scalable, and memory-efficient drop-in replacement for malloc that works on Linux, Mac OS X, and Windows. It dramatically … | 67 | 1252 | stable |
| Tencent/GT GT (Great Tit) is a portable on-device debugging tool from Tencent that acts as an Integrated Debug Environment running directly on smartph… | 23 | 4395 | maintenance |
| pawurb/rails-pg-extras A Ruby gem providing PostgreSQL performance diagnostics for Rails applications, ported from Heroku PG Extras. It exposes rake tasks, a Ruby… | 68 | 1247 | active |
| myzhan/boomer Boomer is a Go library that acts as a high-performance load generator for Locust, spawning thousands of goroutines to run test code concurr… | 70 | 1237 | active |
| seiflotfy/cuckoofilter A Go library implementing cuckoo filters, a space-efficient probabilistic data structure for approximate set-membership queries that suppor… | 32 | 1235 | stable |
| Monad The execution component of a Monad blockchain node, written in C++. It contains a custom EVM implementation, a purpose-built database (Mona… | 97 | 1234 | active |
| redhat-performance/tuned TuneD is a Linux daemon that monitors system devices and applies adaptive tuning profiles for performance or power savings. It is controlle… | 86 | 1234 | stable |
| apache/incubator-pagespeed-ngx ngx_pagespeed is an Apache-licensed Nginx module (originally from Google, incubated at Apache) that automatically applies web performance b… | 10 | 4333 | maintenance |
| alibaba/PhotonLibOS PhotonLibOS is a high-performance C++ library providing a stackful coroutine runtime with a symmetric scheduler and non-blocking IO engines… | 92 | 1230 | active |
| google/orbit Orbit is a standalone native application profiler for Windows and Linux that combines callstack sampling with dynamic instrumentation to id… | 10 | 4313 | maintenance |
| tbenthompson/cppimport cppimport is a Python library that lets you import C++ files directly as Python extension modules, compiling them transparently on first im… | 65 | 1228 | active |
| hugoduncan/criterium Criterium is a benchmarking library for Clojure that measures expression computation time while addressing JVM benchmarking pitfalls. It ap… | 72 | 1225 | active |
| dtolnay/no-panic A Rust attribute macro that makes the compiler prove at link time that a marked function can never panic, failing compilation with a linker… | 85 | 1220 | stable |
| klauspost/cpuid A pure-Go library that detects CPU features and information (vendor, cores, caches, instruction set support) at startup for fast access. Su… | 91 | 1219 | stable |
| Zefan-Cai/R-KV R-KV is a training-free, redundancy-aware KV cache compression method for reasoning LLMs, discarding repetitive tokens on-the-fly during de… | 64 | 1214 | active |
| rNeomy/auto-tab-discard Auto Tab Discard is a browser extension that uses the native tab discarding API (chrome.tabs.discard) to automatically discard inactive tab… | 65 | 1212 | active |
| klauspost/pgzip A Go library providing parallel gzip compression and decompression as a drop-in replacement for the standard compress/gzip package. It spli… | 87 | 1211 | stable |
| facebook/FBRetainCycleDetector An iOS library by Facebook that detects retain cycles causing memory leaks through runtime analysis of object graphs. It inspects objects a… | 67 | 4223 | maintenance |
| ianlancetaylor/libbacktrace A C library that can be linked into C/C++ programs to produce symbolic backtraces, supporting ELF, PE/COFF, Mach-O, and XCOFF executables w… | 74 | 1202 | stable |
| google/double-conversion A C++ library providing efficient binary-decimal and decimal-binary conversion routines for IEEE doubles, extracted from the V8 JavaScript … | 72 | 1196 | stable |
| xoofx/ultra Ultra is an advanced sampling profiler for .NET applications on Windows (ETW-based) and macOS Apple Silicon (EventPipe-based). It produces … | 79 | 1195 | active |
| aspnet/Benchmarks A collection of benchmark applications and Docker images for measuring ASP.NET Core performance, including TechEmpower Web Framework Benchm… | 76 | 1195 | active |
| bytedance/memory-leak-detector MemoryLeakDetector (Raphael) is a native memory leak monitoring library for Android apps, developed by ByteDance's Xigua video team. It hoo… | 23 | 1195 | active |
| CNugteren/CLBlast CLBlast is a lightweight, tunable OpenCL BLAS library written in C++11 that implements basic linear algebra subprograms for vectors and mat… | 77 | 1193 | stable |
| pytorch/cpuinfo A C/C++ library that detects CPU information essential for performance optimization, including supported instruction sets, cache details, c… | 71 | 1189 | stable |
| zilliztech/VectorDBBench VectorDBBench (VDBBench) is an open-source Python benchmark tool for comparing the performance and cost-effectiveness of vector databases a… | 94 | 1188 | active |
| SukkaW/nolyfill nolyfill is a CLI tool that detects redundant JavaScript polyfill packages in a project's dependencies and replaces them with lightweight a… | 72 | 1186 | active |
| Fabulously-Optimized/fabulously-optimized Fabulously Optimized is a Minecraft modpack for the Fabric mod loader that focuses on performance improvements and OptiFine feature parity.… | 95 | 1184 | active |
| pydata/bottleneck Bottleneck is a collection of fast NumPy array functions implemented as C extensions, covering NaN-aware reductions like nanmean and fast m… | 65 | 1182 | active |
| vladmihalcea/flexy-pool FlexyPool is a Java library that wraps existing JDBC connection pools (HikariCP, DBCP, C3P0, Tomcat CP, Vibur, Druid, Atomikos) to add metr… | 60 | 1181 | active |
| madmann91/bvh A header-only C++20 library for constructing and traversing bounding volume hierarchies (BVH), with multiple SAH-based builders, a reinsert… | 77 | 1177 | active |
| wilsonzlin/minify-html minify-html is an extremely fast HTML minifier written in Rust that also minifies inline JS and CSS via oxc and lightningcss. It is availab… | 56 | 1176 | active |
| luis-almeida/unveil Unveil is a very lightweight (under 1KB) jQuery/Zepto plugin for lazy loading images, delaying image loading until the user scrolls them in… | 32 | 4085 | maintenance |
| sindresorhus/memoize A TypeScript library for memoizing functions, caching results of calls with identical input to speed up consecutive invocations. It support… | 75 | 1165 | active |
| retronx-team/sys-clk sys-clk is a Nintendo Switch homebrew system module that lets users set custom CPU, GPU, and memory clock speeds per application and per do… | 53 | 1164 | active |
| researchgate/react-intersection-observer A declarative React component that wraps the browser's IntersectionObserver API for detecting element visibility in the viewport. It handle… | 66 | 1159 | stable |
| inducer/pyopencl PyOpenCL is a Python wrapper providing Pythonic access to the OpenCL parallel computation API, letting you run kernels on GPUs and other ma… | 97 | 1156 | stable |
| scoder/lupa Lupa embeds the Lua and LuaJIT runtimes into CPython via Cython, allowing Python code to execute and interoperate with Lua code. It support… | 79 | 1155 | active |
| mosn/holmes Holmes is a self-aware Go library that automatically collects runtime metrics (goroutine count, RSS memory, CPU usage) and dumps pprof-styl… | 27 | 1147 | active |
| nvdv/vprof vprof is a Python package providing rich and interactive visualizations for Python program characteristics such as running time and memory … | 23 | 3976 | maintenance |
| lzpong/threadpool A minimal (~300 line) C++11 header-only thread pool that accepts variadic functions and lambdas and returns std::future results. It feature… | 73 | 1143 | stable |
| hpyproject/hpy HPy is a new C API and ABI specification for extending Python that is implementation-agnostic, working across CPython, PyPy, and GraalPy. I… | 65 | 1142 | active |
| fast/fastrace Fastrace is a high-performance timeline tracing library for Rust, claiming to be 10-100x faster than other tracing libraries. It supports l… | 63 | 1141 | active |
| uncomplicate/neanderthal Neanderthal is a fast Clojure library for matrix and linear algebra computations built on optimized native BLAS and LAPACK routines, suppor… | 73 | 1130 | active |
| laixintao/flameshow Flameshow is a terminal-based Flamegraph viewer written in Python that renders and lets you interactively explore profiling data. It suppor… | 83 | 1128 | active |
| lewissbaker/cppcoro CppCoro is a C++ library providing general-purpose coroutine abstractions built on the Coroutines TS, including task and generator types, a… | 32 | 3888 | maintenance |
| needle-tools/compilation-visualizer A Unity Editor plugin that visualizes assembly compilation on a timeline, hooking into editor events to show how long each assembly takes t… | 61 | 1125 | active |
| kimwalisch/primesieve primesieve is a fast command-line program and C/C++ library for generating prime numbers and prime k-tuplets up to 2^64 using a segmented s… | 95 | 1124 | stable |
| zherczeg/sljit SLJIT is a platform-independent, low-level JIT compiler library written in C, designed for translating bytecode into machine code. It suppo… | 76 | 1124 | stable |
| jhawthorn/vernier Vernier is a next-generation sampling profiler for Ruby 3.2.1+ that tracks time, allocations, multiple threads, GVL activity, GC pauses, an… | 91 | 1122 | active |
| juanjoDiaz/serverless-plugin-warmup A Serverless Framework plugin that eliminates AWS Lambda cold starts by creating scheduled warmer functions. The warmer invokes your select… | 67 | 1120 | active |
| ErikEJ/SqlQueryStress SqlQueryStress is a Windows GUI tool (with a cross-platform CLI companion, sqlstresscmd) for stress-testing SQL Server queries by running t… | 92 | 1114 | active |
| shadow3aaa/fas-rs fas-rs is a userspace implementation of Frame Aware Scheduling (FAS) for Android, written in Rust. It monitors frame rendering to dynamical… | 71 | 1111 | active |
| shuding/better-all better-all is a TypeScript library that provides an improved Promise.all with automatic dependency optimization. Tasks are declared in an o… | 76 | 1105 | active |
| just-js/just Just is a very small JavaScript runtime for Linux built directly on V8 and system calls, designed for writing system software with near-nat… | 23 | 3804 | maintenance |
| intel/isa-l Intel's Intelligent Storage Acceleration Library (ISA-L) is a C library of SIMD-optimized low-level functions for storage applications, inc… | 82 | 1104 | stable |
| kristiandupont/react-geiger React Geiger is a React library that audiolizes performance issues by playing click sounds when component re-renders exceed a configurable … | 70 | 1104 | active |
| nalepae/pandarallel Pandaral·lel is a Python library that parallelizes pandas operations across all available CPU cores by changing only one line of code (e.g.… | 23 | 3798 | maintenance |
| inikep/lzbench lzbench is an in-memory benchmarking tool that integrates many open-source compression libraries into a single executable to compare their … | 90 | 1100 | active |
| openjdk/jol Java Object Layout (JOL) is a toolbox for analyzing object layout, memory footprint, and references inside JVMs. It uses Unsafe, JVMTI, and… | 57 | 1098 | active |
| rviscomi/capo.js capo.js is a tool that analyzes the ordering of elements in an HTML document's <head> to identify elements that may hurt perceived page per… | 94 | 1095 | active |
| zeman/perfmap PerfMap is a bookmarklet and Chrome extension that overlays a performance heatmap on a webpage, visualizing when images finished loading du… | 32 | 3761 | maintenance |
| Winds-Studio/Leaf Leaf is a high-performance fork of the Paper Minecraft server software, balancing performance optimizations, vanilla mechanics, and stabili… | 98 | 1091 | active |
| nolanlawson/marky A tiny (491 bytes) JavaScript timer library built on the User Timing API's performance.mark() and performance.measure(), with fallbacks to … | 60 | 1091 | stable |
| hyperion-mc/hyperion Hyperion is a Rust-based Minecraft game engine built on the flecs ECS, designed to support 10,000+ players in a single world. It targets ma… | 70 | 1089 | active |
| ivopetkov/responsively-lazy A tiny dependency-free JavaScript library (2.5kb gzipped) for truly lazy loading responsive images, background images, and HTML. It is SEO … | 38 | 1089 | stable |
| fastos/fastsocket Fastsocket is a scalable Linux kernel TCP socket implementation that delivers linear performance scaling on multicore machines, transparent… | 23 | 3735 | maintenance |
| dkorunic/betteralign betteralign is a Go static analysis tool that detects structs whose fields could be reordered to reduce memory usage, and can optionally re… | 98 | 1087 | active |
| Kobzol/cargo-wizard cargo-wizard is a Cargo subcommand that applies predefined profile and config templates to Rust projects to optimize for fast compilation, … | 66 | 1087 | active |
| xerial/snappy-java A Java port of Google's Snappy fast compressor/decompressor, using JNI to achieve near-native performance. It bundles native libraries for … | 52 | 1084 | stable |
| dotnet/crank Crank is Microsoft's benchmarking infrastructure used by the .NET team to run performance benchmarks, including TechEmpower web framework s… | 76 | 1083 | active |
| GRIN Compiler GRIN (Graph Reduction Intermediate Notation) is a compiler back-end and optimizer for lazy and strict functional languages, providing whole… | 31 | 1080 | active |
| hnes/libaco libaco is a blazing fast, lightweight C asymmetric coroutine library supporting the Sys V ABI on Intel386 and x86-64. It offers standalone … | 23 | 3704 | maintenance |
| luben/zstd-jni JNI bindings for the Zstandard (Zstd) lossless compression library, usable from Java and all JVM languages including Android. It exposes st… | 77 | 1078 | stable |
| performancecopilot/pcp Performance Co-Pilot (PCP) is a mature, cross-platform framework and toolkit for system-level performance monitoring and management. It uni… | 98 | 1077 | stable |
| microsoft/bf-tree Bf-Tree is a read-write-optimized concurrent range index (key-value store) written in Rust, from Microsoft Research, designed to work effic… | 61 | 1077 | active |
| chronoxor/CppTrader CppTrader is a C++ library of high-performance components for building trading platforms, including an ultra-fast matching engine, order bo… | 73 | 1076 | active |
| Atoptool/atop Atop is an ASCII full-screen performance monitor for Linux that reports system-level activity (CPU, memory, swap, disks, network) and per-p… | 85 | 1074 | active |
| sebbbi/OffsetAllocator A fast hard-realtime O(1) offset allocator in C++ with minimal fragmentation, using 256 floating-point-distributed bins and two-level bitfi… | 32 | 1072 | active |
| graysky2/profile-sync-daemon Profile-sync-daemon (psd) is a small shell-based pseudo-daemon that moves browser profile directories into tmpfs (RAM) via symlinks and per… | 69 | 1066 | active |
| kavehtehrani/cloudflare-speed-cli A Rust CLI tool that runs internet speed tests against Cloudflare's speed test service, showing download/upload throughput, latency, and ne… | 84 | 1062 | active |
| tsliwowicz/go-wrk go-wrk is an HTTP benchmarking and load-testing CLI tool written in Go, inspired by the wrk tool. It uses goroutines for concurrent async I… | 69 | 1061 | stable |
| KarypisLab/METIS METIS is a C library and set of serial programs for partitioning graphs and finite element meshes, and for computing fill-reducing ordering… | 67 | 1060 | stable |
| oblador/react-native-performance A toolchain implementing the Performance API for React Native, enabling measurement of app performance in development, CI pipelines, and pr… | 87 | 1059 | active |
| segmentio/encoding A Go library providing high-performance encoders and decoders for data formats, most notably a drop-in replacement for the standard library… | 80 | 1056 | active |
| redis/memtier_benchmark memtier_benchmark is a command-line load generation and benchmarking tool for NoSQL key-value databases, developed by Redis. It supports bo… | 99 | 1054 | active |
| carrotsearch/hppc HPPC (High Performance Primitive Collections) is a Java library providing maps, sets, lists, and stacks of primitive types, tuned for maxim… | 86 | 1054 | stable |
| google/zopfli Zopfli is a C library implementing a compression algorithm that produces highly optimized, deflate-compatible output (deflate, zlib, and gz… | 66 | 3598 | maintenance |
| ned14/llfio LLFIO is a low-level file I/O and filesystem library for C++17/20, originally proposed for the C++ standard (P1031). It provides zero-copy,… | 79 | 1050 | stable |
| scrya-com/rotorquant RotorQuant is a KV cache compression method for LLM inference that replaces full d×d orthogonal rotations with block-diagonal Clifford roto… | 47 | 1049 | active |
| spatie/fork A lightweight PHP library for running code concurrently by forking the main PHP process into child tasks. It lets you pass multiple closure… | 91 | 1048 | active |
| g1mv/density Density is a pure Rust lossless compression library focused on extreme compression speed while maintaining good compression ratios, using a… | 72 | 1047 | active |