ForkFree

Data and analytics

quivr

by The-Vibe-Company

Quivr V2 is an engine that takes in streams of content, stores it safely and makes it searchable by keyword and meaning within seconds. It also lets you follow topics over time and get alerts, with plugins for file formats, AI models and business rules.

Worth a lookEstablished, with a few things to check (listed below).

View on GitHubProject website

Stars
39.6k +3 a day
Licence
MIT
Runs on
A small server
Setup
Technical
Language
Go
Age
1263 days

What you can do with it

  • Ingest articles and other content into a Corpus and search it with hybrid keyword and vector search
  • Follow a topic over time and receive alerts, for example by webhook, when new matching content arrives
  • Write plugins to handle your own file formats, AI models or business rules

Make money with it

A freelance developer could build and host custom monitoring and search systems for clients, charging for setup and a monthly fee.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Build an internal search tool over documents, news or customer feedback instead of paying for a hosted search service
  • Set up topic monitoring and alerts on competitors or industry news for a client or your own team

Can you use it commercially?

Free to use, change and sell, including in paid products. Keep the copyright notice.

Not legal advice. Read the project's licence file before building a product on it.

Getting it running

You run it with Docker Compose through make commands, and it needs Go, Docker, Python and Node.js installed. The first run downloads about 1 GB of images and models.

Follow the official instructions in the project README.

Things to check

  • The README says it is at evaluation stage and should not be run in production yet
  • The API is v0 and may change without notice
  • Heavy stack to run: PostgreSQL, Temporal, Weaviate and S3-compatible storage
  • Full verification only runs on Linux x86_64
  • The name and description may differ from the earlier Quivr project, so check you have the right version

Checked 27 Oct 2026. Summary drafted by AI from the project's README.

More in Data and analytics

Scrapling D4Vinci
Worth a look

Scrapling is a Python library for collecting data from websites, covering single page requests, JavaScript-heavy sites and large crawls. It is used to pull out text, prices, listings and other information and save it as JSON, CSV or Markdown.

89.9k stars +73 a day BSD-3-Clause
daily_stock_analysis ZhuLinsen
Worth a look

A Python system that uses large language models to analyse a personal watchlist of shares across several markets, including China, Hong Kong, the US, Japan, Korea and Taiwan. It gathers market data and news, then sends a daily "decision dashboard" report to chat apps or email.

67.1k stars +34 a day MIT
duckdb duckdb
Ready to use

DuckDB is a fast database that runs inside your own application or from a command line, with no separate server to manage. It is built for analysing data held in files such as CSV, Parquet and JSON using SQL.

42.6k stars +26 a day MIT