Ross ROSS = Recommend OSS · open-source software intelligence for agents

function: benchmarking

824 products, primary matches first, then adoption-weighted; health v2 shown.

ProductHealth v2StarsMaturity
awslabs/dgl-ke
DGL-KE is a high-performance Python package built on Deep Graph Library (DGL) for training, evaluating, and inferring knowledge graph embed…
641331active
guonaihong/gout
gout is a Go HTTP client library designed as a 'Swiss Army Knife' for making HTTP requests with a fluent API. It supports multiple body enc…
461329active
lucko/spark
spark is a performance profiler for Minecraft clients, servers, and proxies, combining a lightweight CPU profiler, memory inspection tools …
771323active
giltene/wrk2
wrk2 is a constant-throughput HTTP benchmarking tool based on wrk, modified to produce accurate latency recordings using HdrHistograms. It …
324626maintenance
openai/simple-evals
A lightweight Python library from OpenAI for evaluating language models against benchmarks like MMLU, GPQA, MATH, HumanEval, SimpleQA, Heal…
604612maintenance
pythonprofilers/memory_profiler
A pure Python module for monitoring memory consumption of a process, including line-by-line analysis of memory usage in Python programs. It…
324575maintenance
treosh/lighthouse-ci-action
A GitHub Action that runs Lighthouse audits on URLs and enforces Lighthouse CI assertions or performance budgets within CI workflows. It su…
671289active
greyhaven-ai/autocontext
Autocontext is a recursive self-improving harness that runs AI agents against evaluations, retains useful lessons, and produces traces, rep…
601286active
locuslab/TCN
PyTorch implementation of Temporal Convolutional Networks (TCN) with benchmarks from the paper 'An Empirical Evaluation of Generic Convolut…
324549maintenance
microsoft/waza
Waza is a Go CLI from Microsoft for evaluating AI agent skills through structured benchmarks. Users define test cases and validation rules …
811280active
CXWorld/CapFrameX
CapFrameX is a Windows desktop application for capturing and analyzing frametimes and FPS in PC games, built on Intel's PresentMon with ove…
951279stable
siddharthkp/bundlesize
bundlesize is an npm CLI tool that checks whether your JavaScript bundle files stay under configured size limits, with gzip or brotli compr…
664474maintenance
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…
231262active
mjpost/sacrebleu
SacreBLEU is a Python library and CLI tool for computing shareable, comparable, and reproducible BLEU, chrF, and TER scores for machine tra…
761258active
JonathonLuiten/TrackEval
TrackEval is a Python library for evaluating multi-object tracking (MOT) algorithms, implementing metrics such as HOTA, CLEARMOT, IDF1, VAC…
321255stable
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…
281253stable
VainF/pytorch-msssim
A PyTorch library providing fast, differentiable SSIM and MS-SSIM image quality metrics using separable Gaussian filtering for speed. It ca…
231253stable
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 …
871250active
automl/SMAC3
SMAC3 is a Python library for Bayesian Optimization used to tune hyperparameters of machine learning algorithms and configure arbitrary alg…
811244active
eembc/coremark
CoreMark is EEMBC's industry-standard benchmark for measuring CPU and embedded microcontroller performance, testing core processor features…
671242stable
PauperZ/SSRSpeedN
SSRSpeedN is a Python-based benchmarking platform for proxy servers, forked from SSRSpeed, that supports batch speed testing of nodes. It m…
301241active
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…
731237active
theintern/intern
Intern is a complete JavaScript testing stack supporting unit and functional testing in Node.js and browsers, with built-in code coverage, …
234344maintenance
google/orbit
Orbit is a standalone native application profiler for Windows and Linux that combines callstack sampling with dynamic instrumentation to id…
104316maintenance
ai-dynamo/nixl
NVIDIA Inference Xfer Library (NIXL) is a C++/Python library that accelerates point-to-point communication in AI inference frameworks like …
881227active
hugoduncan/criterium
Criterium is a benchmarking library for Clojure that measures expression computation time while addressing JVM benchmarking pitfalls. It ap…
791224active
google/fuzzbench
FuzzBench is a free Google-run service and framework that rigorously evaluates fuzzers on real-world benchmarks at large scale. It provides…
611205active
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…
731204active
NVIDIA/kvpress
kvpress is a Python library from NVIDIA that implements multiple KV cache compression methods and benchmarks for long-context LLM inference…
861201active
toshas/torch-fidelity
A PyTorch library providing accurate and efficient implementations of generative model evaluation metrics such as FID, Inception Score, KID…
701197active
kornelski/dssim
DSSIM is a Rust CLI tool and library that measures perceptual (dis)similarity between PNG/JPEG images using a multi-scale variant of the SS…
681194active
aspnet/Benchmarks
A collection of benchmark applications and Docker images for measuring ASP.NET Core performance, including TechEmpower Web Framework Benchm…
771192active
xoofx/ultra
Ultra is an advanced sampling profiler for .NET applications on Windows (ETW-based) and macOS Apple Silicon (EventPipe-based). It produces …
851186active
CNugteren/CLBlast
CLBlast is a lightweight, tunable OpenCL BLAS library written in C++11 that implements basic linear algebra subprograms for vectors and mat…
701186stable
ethereum/execution-specs
An executable Python reference implementation of Ethereum's Execution Layer (EELS), including the EVM and consensus-critical behavior, with…
951185active
pydata/bottleneck
Bottleneck is a collection of fast NumPy array functions implemented as C extensions, covering NaN-aware reductions like nanmean and fast m…
661181active
data61/MP-SPDZ
MP-SPDZ is a versatile C++ framework for secure multi-party computation (MPC) supporting many protocols across various security models, inc…
851178active
Spearfoot/disk-burnin-and-testing
A POSIX-compliant shell script that automates burn-in and stress testing of new or re-purposed disk drives. It runs SMART short and extende…
661173active
evan-kolberg/prediction-market-backtesting
A Python/Rust extension for Nautilus Trader providing backtesting tools for prediction market trading strategies, with a focus on Polymarke…
521168active
zilliztech/VectorDBBench
VectorDBBench (VDBBench) is an open-source Python benchmark tool for comparing the performance and cost-effectiveness of vector databases a…
911166active
GaParmar/clean-fid
Clean-FID is a PyTorch library for computing the Frechet Inception Distance (FID) with correct image resizing and quantization steps, fixin…
481166stable
JackHopkins/factorio-learning-environment
An open-source framework for developing and evaluating LLM agents in the game of Factorio, providing an open-ended, non-saturating benchmar…
821156active
NVIDIA-NeMo/Gym
NeMo Gym is a Python library from NVIDIA for evaluating and improving LLM models and agents using environments. It provides infrastructure …
801156active
easystats/performance
An R package from the easystats ecosystem that computes indices of model quality and goodness of fit, such as R-squared, RMSE, ICC, AIC, an…
921151active
PKU-Alignment/omnisafe
OmniSafe is a PyTorch-based infrastructural framework for safe reinforcement learning research, providing a unified modular toolkit and com…
271149active
nvdv/vprof
vprof is a Python package providing rich and interactive visualizations for Python program characteristics such as running time and memory …
233977maintenance
chengtan9907/OpenSTL
OpenSTL is a comprehensive benchmark and modular framework for spatio-temporal predictive learning, covering video prediction methods acros…
541137active
SIPp/sipp
SIPp is a free, open-source SIP (Session Initiation Protocol) protocol testing tool written in C++. It can generate SIP traffic to test, be…
821134active
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…
651124active
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…
931117active
tindy2013/stairspeedtest-reborn
A C++ batch speed testing tool for proxy nodes supporting Shadowsocks, ShadowsocksR, V2Ray, and Trojan. It tests subscription links, logs r…
233839maintenance
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…
931111stable
amazon-science/RAGChecker
RAGChecker is an automatic evaluation framework for diagnosing Retrieval-Augmented Generation (RAG) systems. It provides holistic and diagn…
251110active
ccfos/huatuo
HUATUO is an eBPF-based Linux kernel observability agent that provides kernel-wide metrics, event-driven context capture, autotracing, and …
761107active
prometheus-eval/prometheus-eval
Prometheus-Eval is a Python library for evaluating LLM generation outputs using the Prometheus family of open evaluator models and GPT-4 as…
231107active
ErikEJ/SqlQueryStress
SqlQueryStress is a Windows GUI tool (with a cross-platform CLI companion, sqlstresscmd) for stress-testing SQL Server queries by running t…
941105active
kristiandupont/react-geiger
React Geiger is a React library that audiolizes performance issues by playing click sounds when component re-renders exceed a configurable …
701104active
LAMDA-CL/PyCIL
PyCIL is a PyTorch-based Python toolbox for class-incremental learning, implementing the largest collection of CIL methods for reproducible…
521098active
nolanlawson/marky
A tiny (491 bytes) JavaScript timer library built on the User Timing API's performance.mark() and performance.measure(), with fallbacks to …
631094stable
Emsu/prophet
Prophet is a Python microframework for financial markets analysis that lets programmers model trading strategies, manage portfolios, and ru…
571093active
SCLBD/DeepfakeBench
DeepfakeBench is a comprehensive benchmark framework for deepfake detection, providing a unified platform for data management, implementati…
361093active
SlugLab/CXLMemSim
CXLMemSim is a simulation and emulation framework for CXL 3.0 memory systems, combining a latency/bandwidth/topology/coherency simulator wi…
701092active
openjdk/jol
Java Object Layout (JOL) is a toolbox for analyzing object layout, memory footprint, and references inside JVMs. It uses Unsafe, JVMTI, and…
611088active
GAIR-NLP/LIMO
LIMO is a research project and training framework demonstrating that large language models can achieve strong mathematical reasoning with o…
361083active
mlr
mlr/mlr3 is a machine learning framework for R providing a unified, object-oriented interface to many learning algorithms. It supports resa…
951080active
dotnet/crank
Crank is Microsoft's benchmarking infrastructure used by the .NET team to run performance benchmarks, including TechEmpower web framework s…
771080active
inikep/lzbench
lzbench is an in-memory benchmarking tool that integrates many open-source compression libraries into a single executable to compare their …
861078active
Stonesjtu/pytorch_memlab
A Python library providing line-level CUDA memory profiling and tensor inspection tools for PyTorch. It helps debug out-of-memory errors by…
941077active
autonomousvision/navsim
NAVSIM is a data-driven pseudo-simulation framework and benchmark for autonomous vehicle planning, evaluating driving agents non-reactively…
501076active
chronoxor/CppTrader
CppTrader is a C++ library of high-performance components for building trading platforms, including an ultra-fast matching engine, order bo…
741067active
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…
731062stable
harmonycloud/kindling
Kindling is an eBPF-based cloud native monitoring tool that runs as a DaemonSet in Kubernetes to capture syscalls and tracepoints from kern…
651062active
bytedance/SandboxFusion
A secure, self-hosted code sandbox service from ByteDance that runs and judges code generated by LLMs across 20+ programming languages via …
631060active
bigcode-project/bigcode-evaluation-harness
A framework for evaluating autoregressive code generation language models on benchmarks like HumanEval, MBPP, MultiPL-E, and HumanEvalPack.…
381058active
oblador/react-native-performance
A toolchain implementing the Performance API for React Native, enabling measurement of app performance in development, CI pipelines, and pr…
561055active
PreferredAI/cornac
Cornac is a Python framework for building and comparing multimodal recommender systems, with convenient support for auxiliary data such as …
961053active
segmentio/encoding
A Go library providing high-performance encoders and decoders for data formats, most notably a drop-in replacement for the standard library…
861053active
nmslib/nmslib
NMSLIB is a cross-platform C++ similarity search library with Python bindings for efficient k-nearest-neighbor search in generic and non-me…
573588maintenance
NeuroTechX/moabb
MOABB (Mother of All BCI Benchmarks) is a Python library for reproducible benchmarking of machine-learning algorithms on EEG-based brain-co…
961048active
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…
971047active
centerforaisafety/HarmBench
HarmBench is a standardized, open-source evaluation framework for automated red teaming of large language models, comparing attack methods …
261033active
romkatv/zsh-bench
zsh-bench is a benchmarking tool that measures user-visible latency of interactive zsh, such as input lag and command lag. It also includes…
681028active
python/pyperformance
pyperformance is the official Python Performance Benchmark Suite, providing an authoritative set of real-world benchmarks for Python implem…
841027active
numpy/x86-simd-sort
A C++ template library providing high-performance SIMD-accelerated sorting routines (qsort, qselect, partial sort, argsort, key-value sort)…
631026active
airspeed-velocity/asv
Airspeed Velocity (asv) is a Python benchmarking tool that tracks a project's performance over its git history. It generates an interactive…
841014active
authorjapps/zerocode
Zerocode TDD is an open-source, no-code automated testing framework for REST/SOAP APIs, Kafka data streams, databases, ETL pipelines, and l…
961012active
linux-rdma/perftest
A collection of C-based performance micro-benchmark tools for InfiniBand and RoCE networks, built on the ibverbs API. It measures bandwidth…
851012active
Cloudslab/cloudsim
CloudSim is a Java-based framework for modeling and simulating cloud computing infrastructures and services, including data centers, virtua…
531012active
djkoloski/rust_serialization_benchmark
A benchmark suite comparing Rust serialization frameworks on serialize, deserialize, borrow, size, and compression metrics, including zero-…
771009active
davidtvs/pytorch-lr-finder
A PyTorch library implementing the learning rate range test from Leslie Smith's cyclical learning rates paper, including the fastai-tweaked…
351008active
aragozin/jvm-tools
Swiss Java Knife (SJK) is a command-line tool for JVM diagnostics, troubleshooting, and profiling built on standard JVM diagnostic interfac…
323340maintenance
google/model_search
Model Search is a Google AutoML framework that implements neural architecture search algorithms at scale to find optimal DNN architectures …
103238maintenance
bombomby/optick
Optick is a lightweight C++ profiler designed for games, offering instrumentation, context-switch tracking, sampling, and GPU counters. It …
233161maintenance
GoogleChromeLabs/psi
A Node.js library and CLI wrapper around Google's PageSpeed Insights v5 API that runs mobile and desktop performance tests on deployed site…
103101maintenance
reloadware/reloadium
Reloadium is a Python library and PyCharm plugin providing advanced hot reloading, profiling, and AI-assisted error fixing. It lets develop…
322988maintenance
isaac-sim/IsaacGymEnvs
A collection of example reinforcement learning environments for NVIDIA Isaac Gym, a GPU-accelerated physics simulator. It provides a Gym-st…
102952maintenance
rail-berkeley/rlkit
RLkit is a PyTorch-based reinforcement learning framework and algorithm collection from UC Berkeley RAIL. It provides reference implementat…
322932maintenance
aappleby/smhasher
SMHasher is a C++ test suite that evaluates the distribution, collision, and performance properties of non-cryptographic hash functions. It…
722889maintenance
stanford-crfm/helm
HELM is a Python framework from Stanford's CRFM for holistic, reproducible evaluation of foundation models including LLMs and multimodal mo…
872887maintenance
microsoftarchive/promptbench
PromptBench is a unified Python library from Microsoft for evaluating and understanding large language models across many datasets, models,…
102819maintenance

← prev page 4 / 9 next →