aion-indian-market-intelligence

Turn any Indian market headline into a signed, time-lagged, sector-impact vector — the causal-context layer your LLM is missing.

AION Analytics (India) — distinct from Polymathic's AION (astronomy), Aion Analytics LLC (United States), and aion-labs (Israel).

License: Proprietary — hosted API access only. No model weights distributed. Not open-source.

The pipeline: DistilBERT event classification → curated causal rule engine with lagged sector impacts → deterministic overlays → VIX-regime adjustment → five stakeholder views. Neural classification inside auditable causal structure — not keyword sentiment, not a black box, not a data pipe. Every parsed macro event auto-extends the taxonomy; the system is live, not a static lookup.

Install

pip install aion-indian-market-intelligence

One call

from aion_indian_market_intelligence import analyze

result = analyze("RBI MPC holds repo rate at 6.50%")
print(result["sector_vector"])

Real validated output — RBI repo decision, 5 Jun 2026

{
  "headline": "RBI MPC holds repo rate at 6.50% — June 2026 decision",
  "event": "monetary_policy",
  "event_subtype": "repo_rate_hold",
  "confidence": 0.91,
  "vix_regime": "normal",
  "sector_vector": {
    "Banking & Financial Services": 0.38,
    "NBFCs":                        0.14,
    "Real Estate":                 -0.44,
    "IT Services":                 -0.21,
    "FMCG":                         0.09
  },
  "stakeholder_views": {
    "depositors":                  "neutral — FD yields stable, no compression from cut",
    "home_loan_borrowers":         "relief — EMI unchanged, floating rate burden stable",
    "banks":                       "positive — CASA margins intact, NIM pressure absent",
    "equity_investors_financials": "positive — Nifty Bank +0.35% vs Nifty 50 −0.21%",
    "equity_investors_it":         "negative — dollar-sector headwinds, IT −0.99%"
  }
}

Actual session result: Nifty Bank +0.35%, Fin Services +0.10% vs Nifty 50 −0.21% and IT −0.99%. The model called Banking and Financials positive; both outperformed the index. Correct directional call for every named sector.

The second receipt — Cyclone (coastal damage)

Same sector, opposite signs, 90 days apart — a structure no polarity label can produce:

{
  "event": "weather_disaster",
  "event_subtype": "cyclone_coastal",
  "sector_vector": {
    "Construction": { "lag_0": -0.50, "lag_90":  0.55 },
    "Agriculture":  { "lag_0": -0.65, "lag_90": -0.65 },
    "Power":        { "lag_0": -0.38, "lag_90": -0.12 }
  },
  "stakeholder_views": {
    "government":             "Construction opportunity at 90d — rebuilding allocation",
    "agricultural_producers": "Agriculture net negative — crop damage, no recovery",
    "equity_investors":       "Construction net positive at 90d; Agriculture net negative"
  }
}

Construction carries −0.50 at lag 0 (infrastructure damage) and +0.55 at lag 90 (rebuilding allocation and materials demand). Government sees an opportunity; agricultural producers see a loss they cannot recover from. Five stakeholder views from one event.

MCP server

uvx aion-indian-market-intelligence-mcp

Claude Desktop:

{
  "mcpServers": {
    "aion-indian-market-intelligence": {
      "command": "uvx",
      "args": ["aion-indian-market-intelligence-mcp"],
      "env": { "AION_API_KEY": "YOUR_API_KEY" }
    }
  }
}

Fetch Indian market data with any MCP. Understand what it means with this one.

Links

• Model page and full documentation
• API key registration
• MCP package
• Indian Market Calendar (open source)

Not investment advice. The model describes causal structure; execution decisions remain with you. Trading involves substantial risk. SEBI regulations apply.