productivity▌

LangGraph builds stateful, multi-actor agent applications using a graph-based architecture:

Production-grade framework for building stateful, multi-actor AI applications with explicit graph structure. \n \n Supports graph construction with StateGraph, conditional routing, cycles, and branching for complex agent workflows \n Includes state management with reducers, checkpointers for persistence, and human-in-the-loop patterns \n Handles tool integration, streaming, and async execution across multiple agents sharing state \n Requires Python 3.9+, langgraph package, and LLM API access (Op

Automate Google Calendar and Outlook scheduling, time blocking, meeting prep, and daily digests with Slack and Sheets integration. \n \n Supports five core workflows: daily calendar digests to Slack, one-hour-before meeting prep automation, smart weekly time blocking, Calendly booking synchronization, and calendar analytics reporting \n Includes pre-built templates for maker and manager schedules, with configurable time blocking rules (minimum gaps, max meetings per day, focus block allocation)

Direct SQLite access using GRDB.swift — a toolkit for SQLite databases with type-safe queries, migrations, and reactive observation.

Daily briefing of active focus areas, priorities, and recent knowledge changes for cross-session continuity. \n \n Load at the beginning of each session to understand current context and recent work across tools \n Surfaces active focus areas ranked by recent activity, flagged priorities, and unresolved contradictions or stale information \n Works via nmem wm read CLI command for both local and remote knowledge bases, with fallback to local file access \n Includes deep links to specific memories

Help users craft and deliver compelling presentations using proven techniques from product leaders. \n \n Guides narrative development before slide design, focusing on identifying the single takeaway the audience should remember \n Teaches structural patterns including \"what is vs. what could be\" contrast, descriptive slide titles as conclusions, and state changes every 3-5 slides to maintain engagement \n Covers delivery techniques: breathing exercises, maintaining eye contact, managing prese

Web-based slidedecks for developers with Markdown, Vue components, code highlighting, and interactive features. \n \n Supports syntax-highlighted code with line animations, Monaco editor integration, and live code execution within slides \n Includes diagrams (Mermaid, PlantUML), LaTeX math, presenter notes, recording mode, and timer functionality \n Exports to PDF, PPTX, PNG, or builds as a static SPA for hosting; requires playwright-chromium for export \n Built-in layouts (cover, two-cols, imag

Programmatic Power Automate flow management via FlowStudio MCP server. \n \n List, read, and monitor cloud flows directly from the Power Automate API without UI or manual steps \n Inspect run history, per-action error details, and trigger outputs; resubmit failed runs or cancel active executions \n Update flow definitions, manage connections, and retrieve HTTP-triggered flow callback URLs \n Requires FlowStudio MCP subscription with JWT token authentication; Python or Node.js helper functions pr

Academic research documents with peer-reviewed sources, IEEE citations, and scholarly rigor. \n \n Supports multiple document types: research papers, literature reviews, theses, dissertations, conference papers, and technical reports with standard academic structure \n Integrates source discovery from Google Scholar, IEEE Xplore, PubMed, ACM Digital Library, and arXiv with built-in verification for peer-review credibility and author credentials \n Generates IEEE-format references automatically w

Orchestrates multi-source web research by delegating to subagents, synthesizing findings, and producing cited reports. \n \n Breaks research questions into 2–5 distinct subtopics, creates a research plan file, and spawns up to 3 subagents in parallel for efficient investigation \n Each subagent performs 3–5 web searches per subtopic and writes findings to local files with key facts, quotes, and source URLs \n Synthesizes results by reading local findings files, integrating insights across subtop