Memory for coding agents — Claude Code, Codex, Cursor and 17 others. Indexes the sessions they already wrote to disk, including months from before you installed it, and recalls them in any of them. No LLM, no embeddings, one local Go binary.

Complete reverse-skill (85 SKILL.md) as a DeepSeek Harness (dsh) Cordis plugin — reverse engineering, authorized pentesting and security research skill pack.

900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.

DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.

DSH mobile-friendly web UI plugin (PiUI chat-pager mode): on narrow screens the stock three-column frame becomes a horizontal scroll-snap pager — sidebar | chat — with the chat column rendered completely untouched as a flush rounded card with a PiUI-style 3D flip; swipe or the top-left button flips pages, a settle re-snap always lands on a whole page, and the sidebar page shares the chat background. Safe-area + virtual-keyboard insets, touch-sized controls, hidden scrollbars on coarse pointers. Pure client-side adaptation over the stock frame — zero core changes, works on official rc.2 distributions.

A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-performance systems.

One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.