#benchmark

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

Airspeed Velocity: A simple Python benchmarking tool with web-based reporting

Test that your Claude Code skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, activation checks, A/B experiments, CI gates.

Tool for comparing the run time and accuracy of minimizers on fit benchmarking problems

:zap: A collection of common functions for Fiber with better performance, fewer allocations, and fewer dependencies.

High-precision, one-shot and consistent benchmarking framework/harness for Rust. All Valgrind tools at your fingertips.

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Quickly find bottlenecks in Rust - one profiler for CPU, memory, SQL, HTTP, I/O and async code.

Python package for the evaluation of odometry and SLAM

Comprehensive mocking framework for REST, gRPC, GraphQL & WebSockets. Features intelligent RAG-driven data synthesis, latency/fault injection, HTTP bridge, WASM plugins, E2E encryption, workspace sync, and modern admin UI. Production-ready with Docker support.

Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.

A pytest plugin to create benchmarks

Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time

[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents

Ohayou(おはよう), HTTP load generator, inspired by rakyll/hey with tui animation.

A modern iperf3 alternative with a live TUI, multi-client server, and QUIC support. Built in Rust.

🐰 Bencher - Continuous Benchmarking

Research infra for creating RL environments, post-training, and evals.

A tabular data visualization engine from your local to CI/CD pipeline

VPS Fusion Monster Server Test GO Version Aiming to be the most comprehensive server testing project, implemented in Go with zero environment dependencies. VPS融合怪服务器测评项目 GO版本 尽量成为最全能的服务器测评项目，使用 Go 实现，无需任何环境依赖。