curiosity-stack

Start a guided layer-by-layer decomposition of any technology or market signal.

Find Indian companies at each layer of any global value chain. Runs the india-proxy-agent autonomously — fetches NASSCOM Deep Tech, DPIIT, GeM portal, 12 VC portfolios, BSE SME, NSE Emerge, and specialist publications. Returns a structured HTML research table.

Open your Domain Knowledge manager — browse, add, edit, and remove seeded company intelligence used by the India Proxy Agent

Browse, search, and manage your saved decompositions

Unified Running Horse Agent for volume profile + momentum based stock analysis. Quick mode for fast scans; Deep mode for institutional-grade multi-timeframe conviction scoring. Emphasizes Volume Profile (HVN/LVN/POC), volume behavior, QCE-IM phases, and Darvas structure.

Autonomous agent that finds Indian companies at each layer of any global value chain. Activates when user says "find India proxies", "what Indian companies play here", "India angle", or after L5 in any decomposition. Also activates on /curiosity-stack:india-proxy. Runs fully autonomously — no further input needed after triggering.

Unified Running Horse Agent with selectable analysis depth. Supports two modes: - Quick Mode: Fast scanning with essential filters (Volume Profile + Volume + Structure) - Deep Analysis Mode: Comprehensive institutional-grade analysis with detailed Volume Profile, multiple timeframe patterns, and deeper conviction scoring. Follows "Running Horse Philosophy" with strong emphasis on Volume Profile and volume behavior.

Autonomous agent for watchlist monitoring. Activates when Cowork is opened and watchlist cadence has elapsed. Runs research across all watchlist items, checks trigger conditions, compiles digest, and delivers via Gmail. Uses web_search and web_fetch tools. Do not activate if cadence has not elapsed — check local.md first.

Fires when user says hello, hi, help, get started, what can you do, how does this work, or sends any vague first message. Also fires when curiosity-stack.local.md is unconfigured. Orients the user instantly using plain text + a small inline copy-ready topic list. Never generates a full artifact on welcome — too slow.

Activate when user wants to find actual companies in a value chain layer, especially Indian proxies for global themes. Always check connected sources first. Always apply SEBI compliance — research framing only.

The core 6-layer decomposition framework. Activates when a user describes any topic, technology, market signal, or global event. Also activates when a scenario card is clicked via sendPrompt, or when /curiosity-stack:decompose is run. Guides the user through L0 to L6 using Socratic conversation — one layer at a time.

Activate after every completed decomposition to offer saving. Activate when user says "save this", "add to library", "show my library", "what have I researched", "past decompositions", "have I done this before", or starts a decomposition on a topic that may already exist in the library. Always check library/ folder silently at the start of any new decomposition.

Manages the user's personal domain knowledge registry — company intelligence seeded per sector that the India Proxy Agent uses before searching. Activates when user runs /curiosity-stack:knowledge, says "manage my domain knowledge", "add company to my knowledge", or clicks the "missed company" add form after an India Proxy Agent run. Also activates after any India Proxy Agent output to surface the inline add prompt.

Activate when a user selects their output format after completing a decomposition. Generates exactly one of: Value Chain diagram, interactive Mindmap, Research Note, or Research Brief PDF. Never generate all — only what was selected. Always include SEBI disclaimer, attribution badge, and invisible source comment.

1 hook across 1 event

Access research notes, watchlists, and documents in Google Drive

Access newsletters, research threads, and deal flow emails

Schedule research milestones and follow-up reminders

Access Notion workspace for notes, research databases, and watchlists

Search Slack for shared research, articles, and team discussions