repowiseelastic/elasticsearch

elastic / elasticsearch

Free and Open Source, Distributed, RESTful Search Engine

Java★ 78,197
Use in your agentAsk this codebase

github.com/elastic/elasticsearchIndexed at 4d3bb5aBehind upstream

What is elasticsearch?

elasticsearch is a distributed search and analytics engine, scalable data store, and vector database for searching and analyzing data. It stores and indexes structured or unstructured data so REST APIs can add documents and retrieve search results. Elasticsearch is primarily written in Java.

Written by a model from the README and the source

Code health

Health scores land with the first index: complexity, duplication, coverage, churn and ownership across every file.

Use elastic/elasticsearch in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/elastic/elasticsearch
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is elasticsearch put together?")
  • get_why("why is elasticsearch structured this way?")

Explore elasticsearch

Key features of elasticsearch

  • Elasticsearch supports full-text search over indexed documents.
  • Elasticsearch supports vector searches and generative AI applications.
  • Elasticsearch stores logs, metrics, application performance monitoring data, and security logs.
  • Elasticsearch supports augmented generation and search use cases.
  • Elasticsearch provides REST APIs for indexing, retrieving, and searching documents.

How elastic/elasticsearch works

Data enters Elasticsearch through REST APIs or clients that send HTTP requests. Elasticsearch stores and indexes documents in indices, while timestamped data can use data streams with multiple backing indices. A cluster makes newly indexed documents available from any node, and search requests query the indexed data. The start-local script sets up Elasticsearch and Kibana with Docker for local development and testing. Kibana provides Discover and a Dev Tools Console for searching data, testing requests, and creating data views. The Python elasticsearch client can connect to a local cluster with basic authentication.

elastic/elasticsearch FAQ

What is elasticsearch?

elasticsearch is a distributed search and analytics engine, scalable data store, and vector database for searching and analyzing data.

How does elasticsearch work?

elasticsearch accepts documents and requests through REST APIs, stores and indexes the documents, and returns search results from the indexed data. Elasticsearch clusters make indexed documents available from any node.

What language is elasticsearch written in?

elasticsearch is written primarily in Java.

How is the elasticsearch code organized?

elasticsearch is organized as a Java codebase that provides the Elasticsearch engine, REST APIs, cluster services, indexing, and search functionality.

When should I use elasticsearch?

Use elasticsearch for full-text search, logs, metrics, application performance monitoring, security logs, vector search, and augmented generation.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of elastic/elasticsearch from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.