AI & ML

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on limited GPU memory.

Enables fast similarity search and clustering of dense vectors using FAISS, covering index types, GPU acceleration, and integrations with LangChain and LlamaIndex.

Translates raw genomic data into personalized health, longevity, and pharmacogenomic protocols for AI agents.

Scouts market opportunities, identifies gaps, and surfaces recent demand signals with evidence and next actions via the MSX API.

Interact with the QFC blockchain: manage wallets, query chains, stake, deploy contracts, handle ERC-20/NFT tokens, swap on DEX, and run AI inference.

Transcribe and translate audio across 99 languages using OpenAI's Whisper model, with options for model size, language detection, timestamps, and batch processing.

Fetches and summarizes the latest ORF news in German, focusing on Austrian and international politics, and generates a themed studio image.

Generates structured VGL JSON prompts for Bria's FIBO image generation models, covering text-to-image, editing, inpainting, outpainting, and captioning with a deterministic schema.

Connects agents to the GSTD Grid via MCP tools for autonomous payments, task discovery, and shared knowledge storage.

Extracts YouTube video transcripts and produces structured summaries with main points, key arguments, and conclusions.

Generates AI images via Ideogram, Leonardo, or Flux using plugin scripts, or delivers an optimized prompt when no API key is configured. Requires explicit cost confirmation before each paid generation.

Mantém a coerência visual entre peças geradas por IA usando modelo fixo, prompt base, seed e referência de estilo, com teste de coerência e biblioteca de prompts.

Forces one deeper, more creative pass on an answer or plan while preserving the original escalation prompt verbatim.

Performs AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter, providing grounded answers with source citations.

Build or modify a RAG retrieval pipeline with vector store search, corpus routing, citation rendering, and book fidelity enforcement.

Scaffolds a new OpenAI Agents SDK agent with instructions, tools, API route, and bridge wiring, following existing project conventions.

Builds Google Stitch UI projects and generates screens from feature descriptions or export files by calling Stitch MCP tools directly, following Stitch prompting best practices.

Provides domain knowledge on the Causal Dynamics Architecture (CDA), an alternative AI computing architecture based on causal graphs and Hamiltonian dynamics, with references for deep dives.

Provides data-driven endurance cycling coaching using Intervals.icu data, including fitness assessment, workout planning, and power curve analysis.

Creates a temporary bot email address and checks its inbox via API, useful for testing signup flows, receiving verification codes, and automating email workflows.

Design, simulate, and run quantum circuits on Google Quantum AI hardware and other providers using Cirq, including noise modeling and characterization experiments.

Provides a reference for building real-time voice and multimodal AI agents with Pipecat, covering pipeline architecture, speech services, LLM integration, transports, and deployment.

Provides comprehensive guidance for symbolic mathematics in Python using SymPy, covering algebra, calculus, equation solving, linear algebra, physics, and code generation.

Ingest, index, search, and edit video and live streams with timestamps, subtitles, overlays, and real-time alerts.

Create, analyze, and visualize complex networks and graphs in Python using NetworkX, including graph construction, algorithms, generators, I/O, and plotting.

Generates copyable scientific figure prompts from research documents, papers, and reference images for AI illustration models.

Inspect and adjust the agent's runtime state, including model, context window, iteration limits, token usage, workspace configuration, subagent status, and request routing metadata.

Perform fast genomic interval operations (overlap, nearest, merge, coverage, cluster, complement, subtract, count-overlaps), multi-format bioinformatics I/O, DataFusion SQL, and pileup on Polars DataFrames via the polars-bio library, serving as a scalable alternative to bioframe and bedtools.

Predicts chromatin state across 919 tracks (histone marks, DNase, TF binding) for DNA sequences via the hosted Genomic Intelligence API, producing a report and JSON results.

Establishes a three-layer knowledge distillation architecture for an Obsidian-based wiki, defining categories, projects, page templates, and operational workflows for maintaining a persistent knowledge base.

Discovers and executes bioinformatics tools from the Galaxy ecosystem via natural language, with multi-signal scoring, workflow templates, and reproducibility bundles.

Search, install, update, and list agent skills from the ClawHub public registry using natural-language queries.

Generate or edit images through ClawRouter's local API, with automatic payment via x402 and support for multiple models.

Launches a model evaluation batch with parameter collection, pre-flight checks, execution, and post-run analysis for interactive or foreground runs.

Verifies that every number, comparison, and scope claim in a research paper matches raw result files, using a fresh cross-model reviewer with no prior context to prevent confirmation bias.

Recommends the optimal Claude model tier (Opus, Sonnet, or Haiku) for a given task by analyzing reasoning depth, blast radius, domain expertise, output length, and correctness cost, and suggests parallelization opportunities.