Latency Python Packages

tcp-latency

Module and command-line tool to measure latency using TCP.

rpcbench

Vendor-neutral RPC benchmark CLI: compare JSON-RPC/REST providers (Ethereum, Solana, and more) for latency, P50/P95/P99, error rate, and freshness. Local reports + Prometheus. Not a security scanner.

net-benchmark

Network benchmarking suite for DNS, HTTP, and SSL — with DNSSEC validation, DoH/DoT support, high‑concurrency testing, and enterprise‑grade reporting

llama

Library for testing and measuring network loss and latency between distributed endpoints.

osaca

Open Source Architecture Code Analyzer

shredstream

Solana ShredStream SDK/Decoder for Python, enabling ultra-low latency Solana transaction streaming via UDP shreds from https://www.shredstream.com

percently

⚡️ Blazing-fast percentile calculator (p50/p95/p99) in Rust — with Python bindings

voice-evals

Reproducible evaluation for voice agents: replay scoring, scripted live probes over WebSocket, and CI gates for WER, latency, barge-in behavior and task outcomes.

pankhllm-server

The LLM gateway that learns to skip the LLM. Trains its own tiny model on your agent's decisions and makes them in 0.2 ms on a CPU, with no LLM call. OpenAI-compatible, one Rust binary. Teach it with your skills and logs in one command.

benchrig

Cross-platform benchmarking and hardware profiling rig for local LLMs across Ollama, Microsoft Foundry Local, ONNX Runtime GenAI, and Prism on Apple Silicon & CUDA.

pankhllm

The LLM gateway that learns to skip the LLM. Trains its own tiny model on your agent's decisions and makes them in 0.2 ms on a CPU, with no LLM call. OpenAI-compatible, one Rust binary. Teach it with your skills and logs in one command.

dns-benchmark-tool

Network benchmarking suite for DNS, HTTP, and SSL — with DNSSEC validation, DoH/DoT support, high‑concurrency testing, and enterprise‑grade reporting

quickthink

quickthink is a local-first CLI and Python library that wraps Ollama-backed LLM calls with a compressed plan-then-answer scaffold and latency-aware routing. It adds a short validated planning step for multi-step prompts and routes simple ones straight through. Local inference control for small models.

bench-my-llm

🏎️ Dead-simple LLM benchmarking CLI - latency, cost, and quality metrics

batchwatch

Measure how long LLM batch jobs actually wait — OpenAI, Anthropic, Gemini. Clients for Python, TypeScript, Go, Rust, Ruby, .NET, PHP, Java, C++.

fastapi-timer

Lightweight FastAPI middleware for measuring API response time and downstream operation latency.

toolkit-cost-optimizer

LLM inference cost and latency optimizer -- log analysis, SLO-based model recommendations, and routing policy simulation.

voicebench

Measure real-time voice agents: response latency, interruption handling and false barge-ins.

loop-timing-witness

FPGA control-loop event witness software and RTL simulation for PolarFire SoC; physical board qualification pending.

aioprox

aioprox – Asynchronous proxy manager for Python. Fetch, test, and filter HTTP/SOCKS proxies with optional latency measurement and custom sources.

edgelens

Stage-level latency, power and deadline profiling for edge AI pipelines — diagnoses why a edge device workload is slow, with measured evidence.

nn-meter

A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.

connmonitor

A persistent monitor and aggregator of network statistics

llmlatency

Regional AI API latency and uptime measurements. Open datasets, JSON API and MCP access; edge TTFB and inference TTFT reported separately.