C

claude-code

Specification graph manager for AI-augmented projects, on the nomograph-claim substrate.

A self-hosted AI platform — inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, and more — behind a single OpenAI-compatible endpoint. One docker-compose up.

My opinionated Claude Code config. No—I do not vibe code nor will I ever pay for these services, however some clients provide access and request that I work with it.

Claude Code in Docker. Drop-in OpenAI-compatible API, MCP server, Telegram bot, and CLI — five interfaces, one image. Persistent sessions, file ops, always-on skill injection, and a full dev toolchain (Go, Python, Node, K8s, Terraform, databases) or a minimal image with just the basics.

Agent-agnostic base image for putting any terminal AI coding agent (claude-code, pi, opencode...) on the network. Bolt on a 20-line adapter, get an HTTP API, OpenAI-compatible /v1/chat/completions, MCP server, Telegram bot, and cron scheduler. One container. Same surfaces. Swap the brain — you don't fork this, you FROM it.

Agent-shape testing harness that measures how an LLM-driven agent uses a tool's CLI, scored by an LLM judge.

Fast BM25 full-text search for code repositories with CLI and MCP integration for AI coding agents.

Custom skills for Claude Code to extend its capabilities

Go-REST-API-Backend für MOSAIK Campus – die datenschutzfokussierte Web-App zur Digitalisierung der Elternbeirats-Organisation. PostgreSQL-Datenhaltung, Scope-Isolation & feldweise Verschlüsselung personenbezogener Daten.

A Go-based Open Source Universal Memory server that exposes a Model Context Protocol (MCP) interface for LLM clients. It provides semantic document search (for user documents), agent memory management, and a knowledge graph - backed by PgVector or ChromaDB - enabling AI agents to store, retrieve, and interconnect knowledge across sessions.

A corral for unbroken horses. corral wraps Lima to give every project its own agent VM — real kernel boundary, persistent per-workspace memory, full dev toolchain inside, no host home or SSH agent visible. Optional HAProxy + pf egress filter restricts outbound HTTPS to a per-workspace allowlist. Rootless containerd ships in every VM. macOS, Apple Silicon or Intel.

Structural biology agent skill — PyMOL, ChimeraX, AlphaFold DB, and Rosetta automation for AI coding agents

Forked from: https://github.com/dgriffith/bad-daves-robot-army

Repository for Claude Code artifacts, including subagents, slash commands, and hooks