Fertige KI-Automatisierungen

Jede Technologie von Grund auf implementieren — Git, Redis, Shell, Docker und mehr

CMDOP-Skill-Wrapper-für-SDKRouter — vereinigte-AI-Dienste-SDK

Query Google NotebookLM notebooks for source-grounded answers using Gemini, with browser automation and library management.

Manage and use local Ollama models for inference, embeddings, and tool use.

Generate speech from text via OpenAI's Text-to-Speech API, with customizable voices, models, and formats.

Long-term semantic memory backed by ChromaDB and local Ollama embeddings, with auto-recall and manual search capabilities.

Personal knowledge base powered by Ensue for capturing and retrieving understanding.

Turn your AI into JARVIS with voice, wit, and personality using sherpa-onnx offline TTS and ffmpeg audio processing.

Automatically route tasks to the cheapest Claude model that works correctly, saving 50-90% on API costs.

Generate PPT files using Baidu's AI-powered tool, providing themes, templates, and customizable options.

Long-term semantic memory via ChromaDB and local Ollama embeddings, with auto-recall and manual search capabilities.

Aggregates and summarizes the latest AI news from multiple sources, providing concise news briefs with direct links to original articles.

A Christian alignment layer for AI agents, grounding them in the absolute moral authority of the King James Version (KJV) Holy Bible (1769).

AI-powered PDF generator for legal documents, pitch decks, and reports. Supports various document types and integrates with AI agents like Claude, GPT, and Copilot.

Generate AI images with GPT Image, Gemini Nano Banana, FLUX, Imagen, and top providers using prompt engineering, style control, and smart editing.

Neural web search and code context via Exa AI API, requires EXA_API_KEY.

Persistent memory system for AI agents, inspired by the hippocampus in the brain, with automatic encoding, decay, and semantic reinforcement.

ElevenLabs Text-to-Speech integration for OpenClaw, generating realistic AI voices with emotional audio tags.

Automatically route tasks to the cheapest Claude model that works correctly, saving 50-90% on API costs.

Local speech-to-text using faster-whisper, a CTranslate2 reimplementation of OpenAI's Whisper, for 4-6x faster transcription with identical accuracy.