3. Data, Science & AI

Guides local configuration of data acquisition systems using MCP tools for hardware discovery and YAML parameter editing.

Provides persistent key-value storage for session data, conversation context, and agent state, enabling memory management in AI-driven applications.

Guides Qdrant vector database integration for RAG systems, covering async handling, error management, and performance optimization.

Searches and retrieves context from Airweave collections across connected apps (Slack, GitHub, etc.) to provide answers based on user's company data.

Extracts text and metadata from web pages, storing raw content in the 'raw/' directory for subsequent data distillation processes.

Automates extraction of structured knowledge from raw content including summaries, key points, entities, and patterns, saving results to distilled/ directory.

Captures raw YouTube video transcripts using `ytt`, storing them in raw/ with minimal metadata for downstream data processing.

Library for constructing multi-step AI agents featuring planning, context management, and subagent delegation capabilities.

Provides design patterns for coordinating multi-agent workflows including sequential, parallel, and iterative structures with defined handoffs and dependencies.

Framework for building LLM-powered applications using LangChain in JavaScript/TypeScript, supporting models, chains, tools, and RAG patterns.

Framework for constructing stateful, multi-step AI agents with graph-based workflows, persistence, and human-in-the-loop capabilities.

Analyzes meeting transcripts to identify communication patterns and provide actionable feedback for improving leadership and interpersonal skills.

Enables efficient backtesting of trading strategies using the polars-backtest library for financial data analysis and strategy validation.

Command-line tool for querying, filtering, and transforming JSON data structures efficiently.

Provides structured data processing in nushell with native table handling, multi-format parsing (JSON, YAML, TOML, CSV), and pipeline operations.

Queries Claude Code conversation history and session data via SQL to analyze interactions, token usage, and agent activity patterns.

Provides an in-memory algebraic database structure using ACSets (Attributed C-Sets), a category-theoretic formalism for relational data management and processing.

Guides creation, review, and update of agents and workflows in multi-agent systems using .agent.md files and key patterns like context engineering.

Verifies factual claims by cross-referencing with source documents to ensure responses are grounded in data for accuracy.

Provides GPU-optimized OCR for text extraction from images, PDFs, and multi-language documents with layout analysis and table detection.

Processes transcripts and communications to update a chronological events index with contextual understanding.

Extracts mathematical expressions from images into LaTeX format using AI-driven OCR, ideal for academic and technical documentation.

Real-time monitoring of social media streams using MCP for continuous data ingestion and processing.

Analyzes robustness of qualitative dynamics in dynamical systems under perturbation, a core concept in scientific modeling and system analysis.