Havuz

⚡ Pi, the coding agent, compiled ahead of time to one native executable. 10× faster to start, 7× less CPU and 4.5× less memory than Pi on No

🚀 Rust 全量重构的 Claude Code - 性能提升 2.5x，体积减少 97% | High-performance Rust implementation of Claude Code with 2.5x faster startup and 97% smaller

Lightweight desktop tool for Call of Duty: Modern Warfare 4. Smart FPS optimization, performance tuning, process management and real-time mo

30KB Markdown-native WYSIWYG editor for React, built for AI streaming, human editing, huge files, macOS, Web, and agent workflows.

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

Word-sized charts for React, made for LLMs and humans — 106 chart types, zero runtime dependencies, accessible by default, RSC-safe.

Frontier: A Discrete-Event Simulator for Modern LLM Serving

Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGU

Find what's slowing your database down: a free desktop app, CLI and MCP server for SQL Server, PostgreSQL, YugabyteDB, TimescaleDB, MySQL, M

Help your agents find the smoking gun they're looking for. Optimization evidence for agents: find complexity hotspots.

"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, c

Unity Editor performance profiling agent: captures frames, produces rule-based findings with evidence chains and one-click fix plans, option

Frame-budget compiler and diagnostics for three.js games: batches naive scenes, measures every frame cost, explains what to fix. CLI and MCP

Claude Code skill that audits any Shopify theme for performance, SEO, AEO, and GEO in 90 seconds. 80+ checks, scored report, paste-in Liquid

AI coding runtime hygiene for Codex, Claude Code, Cursor, Windsurf, MCP servers, and safe workspace caches. Try: npx z-clean audit

Live DevTools for your running React + TanStack app — driven from the terminal by your AI agent, through one CLI

Chinese AI video micro-expression and emotional acting prompt skill

An accelerator that reviews a Microsoft Fabric tenant end-to-end through metadata-only scans across governance, cost, capacity, performance,

Seven Agent Skills for NestJS implementation, architecture, OOP, code and feature audits, runtime performance, and safe Git publication.

Your SvelteKit app's code health, checked before it ships. Statically, no browser — SEO, Performance, Correctness, Security, Architecture, A

A menu-bar macOS agent loop: every N minutes it asks Claude/Codex what's overloading your Mac and suggests one-click, risk-checked fixes.

On-demand .NET runtime diagnostics for live CoreCLR apps — no code changes. Ships an MCP server (let an LLM drive the investigation), a stan

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

CDP-powered perf CLI: goes beyond Lighthouse scores, builds causal degradation graphs. Tells you why it's slow, not just that it is.

A zero-allocation, header-only C++ BPE tokenizer for Qwen, built for maximum inference throughput.

Fix and optimize Claude Code performance the easy way

MCP server for iOS leak hunting and performance investigation. 28 MCP tools, 34-pattern retain-cycle classifier with Swift fixTemplate snipp