CocoIndex

CocoIndex is a Python framework that keeps data for AI agents and LLM apps continuously fresh by reprocessing only what changed.

What it is good for

  • Keeping documents and codebases indexed for AI search without full re-runs
  • Updating embeddings only for files that changed
  • Feeding live Slack, PDF, and meeting note data to an AI agent
  • Building retrieval pipelines that stay current with source data

At a glance

Who it is for
Setup
Requires programming

Level 5 of 5. You need to write code to use it.

Cost
Free and open source
Type
Framework or SDK
Tasks
Works with
Postgres

Momentum

Rank this week
Not ranked yet
Best rank
None yet
GitHub stars
11,811

GitHub numbers as of Nov 2, 2026. Updated weekly.

11.5k 11.7k 11.8k Sep 24, 2026 Nov 2, 2026
GitHub stars for CocoIndex: 11,559 on Sep 24, 2026, 11,811 on Nov 2, 2026. Source: GitHub.

Official links

Setup steps are on the official pages. We do not repeat them here, since they change.

Questions

Is CocoIndex free?
Yes. It is free and open source (Apache-2.0 license).
Do I need to know how to code to use CocoIndex?
Yes. You need to write code to use it.
What does CocoIndex work with?
According to its own documentation, it works with Postgres.
What is CocoIndex good for?
Keeping documents and codebases indexed for AI search without full re-runs, updating embeddings only for files that changed, feeding live Slack, PDF, and meeting note data to an AI agent, and building retrieval pipelines that stay current with source data.

Similar agents

  • Firecrawl

    Firecrawl is an API that searches the web and pulls clean page content for AI agents and apps.

  • Scrapling

    Scrapling is a Python web scraping framework that collects data from websites, including JavaScript-heavy and bot-protected ones, for developers.

  • pagesift

    pagesift is a self-hosted tool that turns web pages, PDFs and Office files into clean Markdown for AI agents and LLMs.

  • webclaw

    webclaw is a web extraction tool that turns websites into clean markdown or JSON for AI agents and apps, usable from a terminal, MCP, or API.

  • crawl4ai

    Crawl4AI is an open-source web crawler that turns any website into clean Markdown for AI agents and data pipelines.

  • OpenBB

    OpenBB is an open data platform that connects financial data sources to Python, dashboards, and AI agents for analysts.

Last updated Nov 2, 2026. Tracked since Oct 28, 2026. The summary was written by an AI model from the project's own description and checked against our copy rules. Spotted an error? Tell us.