AI & ML

Generates speech, transcribes audio, clones voices, and builds real-time voice agents using ElevenLabs, OpenAI TTS, Whisper, and Vapi.

Generates short AI videos from text or images across Runway, Kling, Sora, Pika, Seedance, Grok Imagine, and Veo, with provider-specific APIs and prompt guidance.

Routes AI model requests to the optimal provider based on task, cost, latency, and capability requirements, managing multi-provider LLM deployments.

Creates fully automated AI podcasts that research, write, and narrate complete episodes, with guidance on monetization and building a podcast network.

Guides building LLM applications on the Dify platform, covering visual workflows, knowledge bases, agents, and API deployment.

Builds AI skills from documentation, repos, PDFs, videos, and other sources using the Skill Seekers MCP server, with source detection, scraping, enhancement, packaging, and vector DB export.

Manage vector database operations across Pinecone, Weaviate, Qdrant, and ChromaDB, including embedding generation, index creation, metadata filtering, hybrid search, and production deployment for RAG and similarity search.

Build multi-agent conversation systems with AutoGen, including two-agent chats, group chats, function calling, and nested conversations with code execution and human-in-the-loop options.

Deploy and serve LLMs in production with vLLM, Ollama, TGI, and llama.cpp, including quantization and GPU optimization.

Evaluates the agent's own work, catches mistakes, and improves permanently through self-reflection, self-criticism, and learning from corrections.

Unified multimedia generation API for images, videos, and text-to-speech, replacing separate providers for a single workflow.

Integrates on-device and cloud machine learning into Flutter apps with TensorFlow Lite and Firebase ML Kit, covering image classification, object detection, OCR, face detection, and barcode scanning.

Executes Python code iteratively via an MCP bridge to produce verified results for calculations, data analysis, and task decomposition.

Coordinates multiple agents with spatial memory and swarm navigation for collective task execution.

Index local folders and search documents with BM25, vector, or hybrid queries, plus AI answers with citations and a web UI.

Ingests EPUB and ebook files into a local vector index and provides a command-line interface for asking questions about the books.

Provides a persistent memory CLI for LLM agents, installed via npx.

Connects agents to the GSTD Grid for decentralized compute, hive memory, and blockchain-based economic settlement via MCP tools.

Orchestrates three frontier models to debate a question and synthesizes their best insights into a single superior answer.

Build applications with Gemini API hosted models, including multimodal content, function calling, and structured outputs, using the latest SDKs and model specifications.

Filters user-generated content for safety using Google Model Armor via the gws CLI.

Integrates WordPress 7.0's WP AI Client for provider-agnostic AI generation, covering prompt building, model preferences, structured JSON, media generation, and safe feature gating.

Writes Python and TypeScript code that calls the Gemini Interactions API for text generation, chat, multimodal understanding, image generation, streaming, research, function calling, and structured output, including migration from the legacy generateContent API.

Processes and analyzes multiple physiological signals (ECG, respiration, EDA, EMG, PPG, EOG) together using NeuroKit2, including cross-signal features like RSA and event-related analysis.

Configure MCP servers in .claude/.mcp.json with examples for memory, filesystem, search, and browser automation, plus environment variable handling and validation rules.

Guides downloading and configuring RVC voice conversion models, including HuBERT and index files, and running voice conversion scripts.

Reference for configuring and using LangChain4j vector stores, covering setup, search, filtering, and ingestion.

Guides feature extraction and preprocessing for time series data using aeon transformers, covering collection and series transformers with code examples.

Offload sub-tasks to other agents, specialist models, or background jobs, with guidance on choosing the right method and verifying results.

Generates Xiaohongshu (Little Red Book) posts — titles, body copy, and cover images — and manages publishing, searching, and interacting with the platform through a local MCP service.

Converts text to speech and generates MP3 audio files using the Hume AI or OpenAI API, printing the file path for delivery.

Generates video clips from text prompts using Google Veo models, with options for duration, aspect ratio, and model selection.

Generates structured VGL JSON for Bria FIBO models, giving deterministic control over objects, lighting, camera, composition, and style instead of natural language prompts.

Transcribes audio from URLs or local files to text using the Speech is Cheap API, with options for speaker diarization, timestamps, and multiple output formats.

Ingests EPUBs and ebooks into a local vector index, then answers questions and searches passages via a command-line interface.

Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.