archival-research

AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.

TelidonP5: a JS encoder and decoder for NAPLPS vector graphics files (originally developed for Telidon hardware, later used throughout the BBS era).

Operations CLI for IntellyWeave - open-source platform for OSINT analysis, archival research, and investigative journalism

Project files, scripts, configurations, and workflow publications for the Archives-Textract Test Project

Academic archival research in ancient history and egyptology

Docuement scanner for the Episodes in the History of Australia's Asian Context Project

Archival cross-referencing and cipher-structure analysis of the public Zodiac record.

Agent-first CLI, Python API, and MCP server for the National Archives Catalog API

CLI tool for importing, processing and archival of universally saved online collections

Human-edited archival documentary workflow with Nix, FFmpeg, Whisper, provenance tracking, boundary review, and reproducible delivery QC.

Structured archival research dossiers - repeatable Internet Archive methodology applied to cipher machines, vintage electronics, archival systems theory, and more. Companion to warc-portfolio.

IAMMP *.CIS file format viewer for objective C devices.

Browser-based archival snapshot tool for capturing DOM-rendered legal text from bdlaws.minlaw.gov.bd for academic research. Not a legal database.

Can an unaffiliated researcher still discover an astronomical object? Four routes through open archives, measured rather than argued: three closed, one bounded. No discovery — the negative result, a working archival moving-object pipeline, and ten recorded errors are the output.

A Claude-powered knowledge base for managing a research corpus. Drop source documents into the ingest folder and Claude processes them into a structured, cross-referenced markdown wiki, extracting text from native PDFs and web pages, and transcribing scanned docs through an offline-first OCR pipeline. All source content is retained in markdown

Collaborative research platform for the historical, philosophical, and computational study of breast cancer before 1900.

Deterministic agentic harness for historical OCR, text-mining metrics, and per-corpus exploratory reports.

Historical research by Ho Siew Khui 何小驹 (Hé Xiǎojū), specialising in nineteenth-century Malayan historiography through evidence-led archival research.

🤖 Trascrizione automatica di documenti storici italiani con AI. Utilizza Google Gemini per digitalizzare certificati di decesso del 1800, estraendo dati strutturati ed esportandoli in Excel per ricerche genealogiche e storiche.