Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
Algorithm powering the For You feed on X
High availability implementation of AWS NAT instances.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Curated coding interview preparation materials for busy software engineers
The Python micro framework for building web applications.
A smarter cd command. Supports all major shells.
The agent that grows with you
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Learn it. Build it. Ship it for others.
Show usage stats for OpenAI Codex and Claude Code, without having to login.
Teams-first Multi-agent orchestration for Claude Code
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
A flexible distributed key-value database that is optimized for caching and other realtime workloads.
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
A fast, secure CLI tool for managing Kubernetes kubeconfig files.
OpenChoreo is an internal developer platform for Kubernetes
PostgreSQL connection pooler, load balancer and database sharder.
pprof is a tool for visualization and analysis of profiling data
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.