Starred repositories
Trigger.dev – build and deploy fully‑managed AI agents and workflows
A user-friendly, extensible Python-based simulator for analyzing routing algorithms in LEO satellite constellations
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
🇺🇦🇵🇱 A static analysis tool for OpenTelemetry Collector configurations. Built on OPA/Rego, it validates your pipelines, receivers, processors, and exporters against customizable policy rules – catc…
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
An agentic skills framework & software development methodology that works.
A keyboard-first menubar app to monitor and jump between AI coding sessions. Supports Claude Code, pi, opencode, and Codex
Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents
Low earth orbit (LEO) satellite network simulation framework.
nono - a capability-based, multiplexing sandbox tool, built for developers - lift'n'shift seamless path to prod. Run agents securely without needing any additional infra, zero setup, zero latency.
Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured
nice-dag is a lightweight javascript library, which is used to present a DAG diagram.
GoShip is a Go-based, control plane for project-scoped virtual machines, managing applications via VM-resident agents and enabling Confidential Computing experimentation.
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
Opinionated defaults, documentation, and workflows for Claude Code at Trail of Bits
A modular graph-based Retrieval-Augmented Generation (RAG) system
Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity
SCAM - Security Comprehension Awareness Measure | Open-source benchmark that tests AI agents' security awareness during realistic, multi-turn workplace tasks.
Hundreds of models & providers. One command to find what runs on your hardware.
Synthetic monitoring engine with Playwright and Prometheus metrics
Cloud Native Agentic AI | Discord: https://bit.ly/kagentdiscord
⏱️ Thyme - High-throughput log collection distribution for OpenTelemetry Collector benchmarking
PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.
Easing functions implemented in lua (Functions from http://www.robertpenner.com/easing/ )