xerj

xerj is a vector database - Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.

Overview

Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search and agent memory, behind an Elasticsearch-compatible API. Works with Claude Code, Cursor and any MCP client.

XERJ is a community-trusted local AI search that indexes any folder automatically, so your coding agent stops burning tokens reading files one by one and pulls the exact code it needs instead. Reference coding is its main use case and the clearest win: point an agent at a task and it downloads the open-source repos closest to it, indexes them, and reuses how they solved the problem before writing its own code. In a controlled study that cut a coding agent's output tokens by 2.7x at the same 16/16 solve rate (case study), and people report roughly 5x in everyday work (field reports). It is enough for a smaller, cheaper model to out-code a pricier one working from memory, while you spend less time in fix loops. Try it now with a one-prompt install:

Keep that data directory outside any folder you will autoindex. 'data/' is not in the built-in ignore list, so '--data-dir ./data' inside a tree you then index makes the node index its own storage.

xerj is open-source, written primarily in Rust, with 12,825 GitHub stars under the Apache 2.0 license. The latest release is v1.0.0-rc.97 (2026-10-19).

Key capabilities

From the project's documentation:

• Reference coding: index the OSS projects nearest your problem and retrieve how they solved
• Codebase Q&A and RAG: index a repo, ask for the mechanism, get the passage with file:line
• Security audits: index a target tree and query for sink patterns, secrets and dangerous
• Log and incident analysis: mixed formats become typed indices with the aggregations you
• Agent long-term memory: /_memory/{namespace} stores what an agent learns and recalls it
• "Read https://xerj.org/llms.txt, set XERJ up as your search backend, index ./docs, and

Install

A quick way to get started (always check the official docs for the latest):

curl -fsSL https://xerj.org/get | sh

How it fits a local-AI stack

xerj runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related vector databases in the directory:

• Chroma
• "cognee"
• "Langchain-Chatchat"
• "LongMemory"

Sources

• Source code & docs: xerj-org/xerj
• Official website: https://xerj.org

Stats from GitHub, 2026-10-22.