AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

This is my implementation of Karpathy's LLM Wiki. A key highlight is the use of agent skills to enforce workflow rigidity and mitigate agent behavioral deviation.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

Continuous background code review database for agents, work faster and smarter with accountability for every line of generated code.

The best-benchmarked open-source AI memory system. And it's free.

A multi-round co-design skill for publication-ready paper framework diagrams and method overview figures.

Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more

LLM inference in C/C++

llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% throughput).

Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper.

OpenAI-compatible proxy that stacks the free tiers of 16 LLM providers (~1.7B tokens/month) behind one /v1 endpoint — plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, …

Generate draw.io diagrams from natural language — 6 presets, vision self-check + up to 5-round refinement, codebase-to-diagram, 10,000+ official shapes & 321 AI/LLM brand logos. Exports PNG/SVG/PDF…

Academic Research Skills for Claude Code: research → write → review → revise → finalize

Autonomous Hacking Agent for Red Team

Open-source, low-cost 10.5 GHz PLFM phased array RADAR system

Generate beautiful dark-themed system architecture diagrams as standalone HTML/SVG files. Works as a Claude AI skill.

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chem…

Agent Skill for AI-assisted manuscript writing review, based on Dr. Kristin Sainani's "Writing in the Sciences" methodology.

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and pub…

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge managem…

Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server, 65 tok/s Qwen 3.5 122B, Llama 3.3 70B, Gemma 4 31B. Private, offline, airgap-ready. Built for NDA / l…