XERJ

XERJ is a local search engine and MCP server that lets AI agents search code, docs and logs without reading files one by one, for developers and coding-agent users.

What it is good for

  • Searching a codebase without an agent reading every file
  • Giving an AI coding agent memory of private project docs
  • Searching logs, PDFs and CSV files with full-text and vector search
  • Connecting a local search index to Claude Code or Cursor

At a glance

Who it is for
Setup
Guided command-line setup

Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.

Cost
Free and open source
Type
Agent app
Tasks
Works with
Claude Code, Cursor, Claude Desktop

Momentum

Rank this week
#57
Best rank
#5 week 42, 2026
Stars gained last week
+3,195
GitHub stars
18,738

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

940 10.5k 20.1k Sep 24, 2026 Nov 2, 2026
GitHub stars for XERJ: 2,258 on Sep 24, 2026, 18,738 on Nov 2, 2026. Source: GitHub.

Ranking history

Official links

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

Questions

Is XERJ free?
Yes. It is free and open source (Apache-2.0 license).
Do I need to know how to code to use XERJ?
You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
What does XERJ work with?
According to its own documentation, it works with Claude Code, Cursor, and Claude Desktop.
What is XERJ good for?
Searching a codebase without an agent reading every file, giving an AI coding agent memory of private project docs, searching logs, PDFs and CSV files with full-text and vector search, and connecting a local search index to Claude Code or Cursor.

Similar agents

  • Skill Seekers

    Skill Seekers is a tool that turns documentation sites, GitHub repos, and PDFs into Claude skills for developers and AI builders.

  • graphify

    Graphify is a skill that turns a project's code, docs, and PDFs into a queryable map for AI coding assistants, so they can answer questions without rereading every file.

  • Kun

    Kun is a desktop agent app that runs coding, writing, design, and research tasks on your own computer for developers and writers who want local control.

  • skills

    skills is a collection of reusable skill files that teach AI coding agents repeatable workflows for research, content, and codebase work.

  • Understand-Anything

    Understand-Anything is a plugin that turns a codebase, knowledge base, or docs into an interactive graph you can explore and ask questions about, for people new to a project.

  • Waza

    Waza is a set of eight skills that teach Claude Code, Codex, and Cursor engineering habits like planning, debugging, and reviewing code.

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.