🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers

Skills for Real Engineers. Straight from my .agents directory.

ESP-IDF project that build LightMyInk Binaries

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Deterministic CLI to translate AI coding agent plugins between ecosystems (Claude Code -> Gemini CLI)

Universal tool to convert Claude Code skills to Gemini CLI extensions and vice versa

The AI Language Learning Kit for Claude Code and others

Web research for pi with smart and safe tooling + agent system

28,721 GitHub repositories analyzed for AI instruction quality across Claude, Codex, Copilot, Cursor, and Gemini. Full dataset behind "The State of AI Instruction Quality."

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

MCP, CLI, Skills for searching and downloading academic papers from multiple sources like arXiv, PubMed, bioRxiv, etc.

Automated collection of Claude Code plugin adoption metrics across GitHub repositories using n8n workflows

Interactive subagents for pi — spawn, orchestrate, and manage sub-agent sessions in cmux terminals

🪨 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

Make Pi sessions feel endless

LEAN (LLM-Efficient Adaptive Notation) — token-optimized serialization format for structured data in LLM context windows

Pi extension for async subagent delegation with truncation, artifacts, and session sharing

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

An extension suite that turns Pi into a multi-agent orchestration platform

The agent that grows with you

Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.

Autonomous experiment loop extension for pi

SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture

This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.