AI & ML

Provides comprehensive guidance for performing symbolic mathematics with SymPy, including algebra, calculus, equation solving, linear algebra, physics calculations, and code generation.

Designs collaborative AI agent teams with CrewAI, covering agent roles, task definitions, crew orchestration, and process types.

Generates images from text prompts using Google Gemini's image generation model, saving them as PNG files for use in UI, documentation, and design assets.

Analyze single-cell RNA-seq data with Scanpy, covering quality control, normalization, clustering, marker gene identification, visualization, and trajectory analysis.

Create publication-quality statistical graphics in Python with dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and multi-panel figures.

Perceives, indexes, and edits video and audio from files, URLs, and live streams, with search, timeline editing, overlays, subtitles, and real-time alerts.

Instrument LLM applications with Langfuse to trace, score, and monitor cost, quality, and latency across OpenAI and LangChain integrations.

Provides reference documentation and code patterns for using Biopython to handle biological sequences, file formats, database access, alignments, structures, and phylogenetics.

Enhances AI agent memory by injecting large external context, auto-summarizing conversations with tone and intent preservation, compressing multi-turn histories, and verifying facts.

Ingests video and audio from files, URLs, RTSP feeds, or desktop capture; indexes and searches moments with timestamps; transcodes, edits timelines, generates media assets, and creates real-time alerts for live streams.

Performs neural web, code, company, and people searches via the Exa MCP server, with usage patterns for quick lookups, code research, and deep dives.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.

Generates images, videos, and audio using fal.ai models via MCP, covering text-to-image, text/image-to-video, text-to-speech, and video-to-audio.

Turn model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Interactive menu for browsing and composing agent teams on demand, supporting flat or domain-subdirectory agent collections.

Patterns and architectures for running Claude Code autonomously in loops, from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.

Generates spectrograms and multi-panel audio feature visualizations (mel, chroma, MFCC) from audio files via a Go CLI.

Generates full songs from lyrics and tags using the open-source HeartMuLa music models, with multilingual support and local GPU or CPU inference.

Creates 3Blue1Brown-style animated explainer videos, algorithm visualizations, and math animations using Manim Community Edition.

Search local knowledge bases, notes, docs, and meeting transcripts with hybrid retrieval combining BM25, vector search, and LLM reranking, all running on-device.

Configure, extend, or contribute to Hermes Agent, an open-source AI agent framework by Nous Research.

Enables zero-shot image classification, image-text matching, and cross-modal retrieval using OpenAI's CLIP model, with code for semantic search, content moderation, and vector database integration.

Provides detailed guidance on Hermes Kanban worker lifecycle, including workspace handling, handoff patterns, retry diagnostics, and edge cases for dispatched workers.

Runs the open-source LLaVA vision-language model for image understanding, captioning, visual question answering, and multi-turn image conversations, including setup, inference, and training guidance.

Run ML workloads on Modal's serverless GPU cloud: deploy models as auto-scaling APIs, run batch jobs, and schedule tasks with pay-per-second GPU pricing.

Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.

Builds production RAG and semantic search systems with Qdrant, covering collection setup, vector indexing, filtered and hybrid search, and integration with LangChain and LlamaIndex.

Operate Hugging Face Hub repositories, models, datasets, and Spaces via the hf CLI, including downloads, uploads, authentication, and compute jobs.

Checks on-chain agent trustworthiness, discovers agents for tasks, profiles agents, looks up wallet/identity records, contacts or dispatches agents, and reads or writes hosted metadata via the 8K4 Protocol (ERC-8004).

Provides a local-first agent framework for observable execution, composable tool use, and multi-agent orchestration with policy-guarded execution.

Integrates Clock Address Naming with MCP agents to locally stamp, verify, and log tool outputs with hashes and timestamps.

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python, including wrapping APIs, databases, or files as tools and exposing resources or prompts.

Trains and analyzes Sparse Autoencoders (SAEs) with SAELens to decompose neural network activations into interpretable features, covering loading pre-trained SAEs, training custom ones, and feature steering.

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

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