Best used with an AI agent

40+ live apps, open data APIs, MCP servers, and 200+ guides - more than anyone wants to click through. Point your AI here and it reads the whole map and does the work: finds the tool, pulls the data, runs the analysis, and hands you the links.

Here for the open-source code? Your agent finds the right repo for you - and can even clone and deploy it.

Prefer to explore on your own? Go right ahead.

Paste this to Claude Code, Codex, or any AI agent:
Go to tigzig.com and read tigzig.com/llms.txt. It is a practitioner toolkit - 40+ analytics apps, open no-auth data APIs, MCP servers, open-source repos (github.com/amararun), and 200+ build guides. Help me [your task]. Surface the exact links; where there is an API or MCP, call it directly; and if I want to self-host, find the repo and help me deploy it.

Published Full Validation Reports for Every Dataset on VIGIL

Published: March 10, 2026

Published full validation reports for every dataset on VIGIL - India Corporate Signals Tracker. 315,000+ records across 9 categories. Every finding documented publicly.

Ran a detailed AI-assisted audit and validation across all data sources. Specifically targeted at areas where I know from experience things tend to break. Covering - Takeovers, pledge, encumbrance, related party transactions, insider transactions, credit ratings and surveillance.

Cross-referenced against independent NSE downloads with detailed data quality and error assessment. Pretty much a full rebuild just for validations.

e.g. one major issue found and fixed - pledge symbol mapping was completely empty. 1,388 of 1,509 companies now mapped. Remaining 120 are delisted or suspended.

Then the source data quality stuff. A company puts year as 1925 instead of 2025, another puts it as 2924. Few records contain "plz check carefully" - looks like some internal test data that escaped to production. Twelve takeover records show shareholding above 100%. Same company appearing 27 different ways because company name is free text. And bucket loads more..

Just part of the game when you work with data. You need to validate during build....then again in your daily updates...again after major changes..and again on an adhoc basis....and again..and again..till every exception and error has been beaten out of it...then you take a breath...and you start again..

Full reports on every data source: vigil.tigzig.com - Validations

VIGIL Validation Reports