Dimitris

claude-code-guide. The Complete Claude Code CLI Guide - Live & Auto-Updated Every 2 Days

roam-code. Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 commands, 224 MCP tools, change-safety gates, audit evidence, zero API keys.

chatbot-injections-exploits. ChatBot Injection and Exploit Examples: A Curated List of Prompt Engineer Commands - ChatGPT

super-hermes. Skills that teach Hermes Agent to write its own analytical prompts

deep-research. Turn any question into multi-agent exploration. Recursive Claude agents that spawn sub-agents.

agi-in-md. Cognitive prisms for structural analysis — any domain, any model. 1000+ experiments, 58 prisms, 27 scan modes. The cheapest model + right prism beats the most expensive without one. Cross-architecture validated: Claude + Gemini converge on the same structural laws.

grouped-simd-hashtable. High-performance C++ hash table using grouped SIMD metadata scanning. Beats SOTA at scale.

tieredsort. A fast, header-only C++17 sorting library for numeric types. 3.6x faster than std::sort, up to 21x on dense data

Simple-ChatGPT-API-Desktop. Simple ChatGPT API for Desktop

agentskb-mcp.

mzip. Store the formula, not the data. Detection-based compression: 32KB for 1MB of sequential IDs (32768x). Beats zstd/brotli/bzip2 on structured data.

chameleon-cache. A variance-aware cache replacement policy that beats TinyLFU by +5.09pp through the Basin of Leniency

prism-oracle. Structural trust analysis for infrastructure code. 9 targets, 7 conservation laws, 19K+ lines of analysis. Synthesis Hackathon 2026.

hugo-profile. A highly customizable and mobile first Hugo template for personal portfolio and blog.

roam-agent-eval. AI Agent Code Quality Benchmark — How well do AI coding agents write code? Measured by roam-code.