Benchmark for tracking model capability after release.

Switch games running natively on iPhone, iPad and Mac: an NSP folder becomes an unsigned IPA (NSO rewriter, Horizon HLE host, NVN→Metal)

Independent source snapshot of storytold/photocraft. Original MIT/Apache-2.0 licenses and attribution retained.

Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more

open-source canvas for thoughtful software design

Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

ZMK Firmware Repository for MoErgo Glove80 and Go60 keyboard

Techniques and numbers for estimating system's performance from first-principles

Make music on your Cardputer: a playable instrument with fretless-style glide, near-impossible wrong notes, and 1-of-1 generative sounds, so no two units sound alike.

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

A reliable coding agent for complex software engineering tasks.

A minimal Neovim config with zero plugins - built on native 0.11+ features

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

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.

The open-source app everyone uses to manage agents at work

AI agent to evaluate and score resumes.

Self-hosted AI workspace.

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

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

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori…

nvpm 🌈 aims to be an editor-agnostic 🫶 package manager 📦 for Tree-sitter parsers, LSP servers, DAP servers, linters and formatters and more.

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

The agent that grows with you

A minimal, lightning-fast typing TUI for your terminal