Skip to content

armgit / xerj

Public Imported from GitHub
0

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.

NameLast commit date
..
agent-memory-without-postgres-qdrant.md
agentic-memory-vs-rag.md
agentic-rag-vs-rag.md
answer-questions-about-a-docs-folder-with-citations.md
ask-questions-about-a-github-repo-without-cloning.md
audit-php-codebase-with-an-index.md
autoindex-dataset-refused-by-server.md
autoindex-exit-codes.md
autoindex-says-extract-the-archive-first.md
autoindex-server-back-pressure-429.md
batch-lookup-cve-ghsa-ids-offline.md
batch-lookup-ids-from-csv-against-local-index.md
bm25-vs-vector-search.md
catalog-files-with-autoindex-map.md
cheap-low-volume-log-search.md
check-codebase-index-is-complete.md
classify-text-from-labelled-history-without-llm.md
claude-code-memory.md
code-search-mcp-for-claude-code.md
coding-agent-memory-across-sessions.md
count-keyword-mentions-over-time-jsonl.md
do-search-embeddings-help.md
does-xerj-support-s3-alerting-plugins.md
estimate-autoindex-time-before-running.md
evidence-for-agent-memory-links.md
filter-knn-exact-scan-caveat.md
find-duplicate-github-issues-before-filing.md
full-text-search-browser-history.md
full-text-search-over-jsonl-files-cli.md
full-text-search-sqlite-database.md
give-chatgpt-claude-local-file-access.md
how-xerj-autoindexes-a-folder.md
how-xerj-combines-search.md
hybrid-search-quality-measured-ndcg.md
improve-basic-faiss-rag-pipeline.md
index-csv-with-many-columns.md
index-markdown-into-elasticsearch-api.md
index-monorepo-for-agent.md
index-multiple-csv-files.md
index-reference-library-for-coding-agent.md
is-pdf-indexing-efficient.md
keep-index-current-as-files-change.md
keep-s3-bucket-index-current.md
knowledge-graphs-for-agent-memory.md
local-code-search-mcp-fewer-tokens-than-grep.md
local-embeddings-without-openai-api.md
local-search-mcp-for-codex-and-cursor.md
mcp-api-search-or-vector-search.md
notion-export-duplicate-search-results.md
private-agent-memory-namespaces.md
rag-without-vector-database.md
read-autoindex-progress.md
read-indexed-email-and-pdf-folder.md
rebuild-reference-corpus-index.md
reciprocal-rank-fusion-when-to-use.md
reduce-embedding-api-cost.md
reindex-taking-forever.md
rerank-search-results-calibrated-judge.md
resume-interrupted-autoindex-run.md
retrieval-that-says-not-found-with-file-line-citations.md
search-all-pdfs-in-a-folder.md
search-bvh-motion-capture-files.md
search-claude-code-past-sessions.md
search-confluence-html-export.md
search-engine-without-docker.md
search-file-contents-in-a-folder.md
search-files-in-an-s3-bucket.md
search-github-issues-and-prs-locally.md
search-gmail-takeout-mbox-locally.md
search-gzip-logs-without-zgrep.md
search-gzipped-csv-or-json.md
search-html-export.md
search-json-and-jsonl-logs.md
search-jupyter-notebook-cells.md
search-kubernetes-pod-logs-on-disk.md
search-obsidian-pdf-docx-attachments.md
search-openapi-spec-for-agent.md
search-slack-json-export.md
search-sql-dump-file.md
search-unity-project-assets.md
search-word-documents-in-a-folder.md
search-yaml-xml-config-repository.md
search-zendesk-ticket-json-export.md
set-mcp-memory-storage-path.md
share-folder-read-only-search-without-uploading.md
share-local-search-index-through-a-tunnel.md
store-agent-memory-without-llm-call.md
syntax-aware-code-search-refactoring.md
vector-database-vs-full-text-search.md
verify-ai-report-claims-against-sources.md
what-a-share-link-guest-can-reach.md
what-is-agentic-memory.md
what-is-an-mcp-memory-server.md
what-is-hybrid-search.md
what-is-xerj.md
why-autoindex-skipped-files.md