- Rosenheim / Munich
- https://a-ratz.github.io/
- @a_ratzenberger
- in/ratzenberger
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
Prove your coding agent starts with nothing of yours before you measure it: a clean room for Claude Code and Codex that starts only when its probe reads tare: 0.00, so your evals measure the skill,…
Orchestrate multiple coding agents from desktop and mobile
A Vibe Benchmark. Compare coding agents through the apps they actually deliver. Try the builds, inspect the source, and form your own opinion.
Multimodal MiniMax H3 prompt writer for ComfyUI with local and API providers.
Ghidra is a software reverse engineering (SRE) framework
Headless Ghidra MCP server — giving AI agents deep reverse-engineering capabilities.
Arkana - Your entire malware analysis lab, behind one AI prompt. 250+ MCP tools for binary analysis with Claude Code or other MCP
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Production-grade engineering skills for AI coding agents.
Skills for Real Engineers. Straight from my .agents directory.
Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.
an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions
Superseded by tare (github.com/a-ratz/tare). Ran Codex with stripped, bias-light homes.
Evidence-bounded review chains that make planning documents restartable.
Evidence-first evaluation and creation for Agent Skills.
A culinary agent for Claude Code: design and cook a dish through 7 phases, grounded in regional cooking knowledge with dynamic ingredient curation.
User-invoked soft autopilot for recoverable, issue-driven AI coding workflows
Run Claude in self-improving loops to optimize measurable goals.
What if AI agents could form teams as fluidly as humans? Spawn specialists in milliseconds, share discoveries in real-time, review each other's work, and remember everything across sessions. Watch …
iloom: a developer workflow system delivered as a CLI and a VS Code extension for structured AI-assisted development. The CLI is the system of record, running tasks in isolated workflows and persis…
Inspired by Battle Chess for DOS 1988 - Using Gemini3, Nano Banana3, and Veo3 to reimagine Battle Chess
A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC (no affilia…
Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.
Lightweight Image Video Action Generation Inference Framework
GitHub CLI extension for managing sub-issues (child issues)





