In simple English
This tool collects information about venture capital firms and the people who work at them. It uses artificial intelligence to read websites and pull out names, roles, and contact details. You can query the data using standard database commands. The project is free to run on your own computer. It is meant for founders who want to build their own investor lists without paying for expensive commercial databases.
What it is
A TypeScript application that crawls venture capital websites, extracts unstructured details using language models, and stores them in a version-controlled database called Dolt. It acts as an open source alternative to paid directories like Pitchbook or Crunchbase.
What it is good for
Founders who want to build a custom contact list of investors and venture capital partners without paying for commercial market intelligence tools.
- Uses language models to extract structured data from messy web pages automatically.
- Stores data in Dolt (a version-controlled database that works like Git for data), making history easy to track.
- Provides ready-made commands to scrape specific firms or run random discovery batches.
- Requires an external API key for language models, which adds ongoing usage costs.
- Setting up Node.js, pnpm, and Dolt requires comfort with the command line.
- Web scraping is fragile and will break when venture capital websites change their layouts.
Paid investor databases like Pitchbook and Crunchbase
TablePlus
- browserbase/stagehand26k stars
An AI-powered web scraping framework that automates browser interaction using natural language instructions.
- firecrawl/firecrawl195k stars
An open source tool that turns entire websites into clean markdown for language models and data pipelines.
- dbeaver/dbeaver52k stars
A free desktop program that connects to more than a hundred kinds of database and lets you browse and edit them.
- dimitri/pgloader6.5k stars
Loads data into PostgreSQL from other databases and from files, keeping going when individual rows fail.
dolt clone iloveitaly/venture_capital_firms . dolt sql-server & pnpm install cp .env.example .env # Add your OpenAI API key to the .env file before running commands tsx commands.ts --help