Local-first document archive assistant for semantic search and RAG using local LLMs and embeddings.
-
Updated
Jan 7, 2026 - Python
Local-first document archive assistant for semantic search and RAG using local LLMs and embeddings.
Local-first Windows invoice and receipt email archiver with IMAP, Gmail API, OCR, PDF conversion, and DATEV-style CSV export
A local-first, browser-based document archive — no server, no account, no upload.
本地文档档案库 CLI:OCR 提取 + qwen3.7-max 字段抽取 + SQLite 索引(合同/证明/发票等)
Local-first IMAP & Gmail document downloader with OCR, PDF conversion, dedupe and PWA review
Local-first PySide6 file manager with OCR, PDF tools, duplicate detection, SQLite indexing, and privacy review
授权范围内的开源情报资料归档系统:每条结论都可回溯到原件与行号,身份关联必须人工复核,绝不自动合并同名。本地单机运行,只监听 127.0.0.1。
FlyArchive — self-hosted personal document archive and knowledge base with hybrid semantic + full-text search. Local-first RAG: an MCP server gives Claude, Codex and any LLM agent search and document tools over your files, mail and scans. Strict intake, access tokens, nothing leaves your machine.
Which OCR engine reads your documents best? Vision LLMs vs classic OCR on your own pages, headers and footers first. Runs locally.
已授权可查看腾讯在线文档的本地归档与备份 Codex/Claude Code skill
To associate your repository with the document-archive topic, visit your repo's landing page and select "manage topics."