AI search engine and MCP server for bots and 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.
Rust agent-memoryai-agentsbm25claude-codeclicode-searchcursordatabaseelasticsearchfull-text-searchhybrid-searchjsonllocal-firstmcpmcp-servermodel-context-protocolragrustsearch-enginevector-search
version: "3.9"
services:
xerj:
build: .
container_name: xerj
restart: unless-stopped
ports:
- "8080:8080" # Native REST API
- "9200:9200" # Elasticsearch-compatible REST API
- "8081:8081" # gRPC API
volumes:
- xerj-data:/data
environment:
XERJ_LOG: info
# The image already sets both (see Dockerfile): xerj defaults to a
# loopback bind, which inside a container means nothing published on
# `ports:` above would ever answer. Repeated here so the exposure is
# visible in the file you actually edit — the published ports are
# cleartext HTTP, so put TLS in front of them before this leaves a
# trusted network.
XERJ_BIND_ADDRESS: "0.0.0.0"
XERJ_ALLOW_INSECURE_NETWORK_BIND: "true"
command: ["--data-dir", "/data"]
volumes:
xerj-data:
driver: local