Data Tooling

A Dart SDK that lets Flutter apps upload video and search inside it by meaning, speech, or imagery—without imposing any UI.

Token Monitor reads local logs from two dozen AI coding tools to surface live token burn, costs, and limits in one place, synced across all your machines.

Turns URLs into clean markdown and JSON so AI agents don't have to parse HTML soup.

OpenLake wants storage to bypass the host entirely and land straight in GPU memory.

It turns technical PDFs and EPUBs into on-demand Claude Code skills, so you can query a book's actual frameworks instead of hoping the model remembers them.

Because your coding assistant shouldn't need a securities API cheat sheet to analyze A-shares.

A single Markdown skill file turns AI coding assistants into zero-auth terminals for US and HK equities — with every source audited for legal compliance.

Most AI image prompts are one-off text blobs; this repo distills 96 visual styles into structured JSON templates so you can swap variables without losing style direction.

It removes the visible Gemini sparkle, invisible SynthID fingerprints, and C2PA metadata that AI image generators embed in every output.

It exists to automate the tedious pipeline of turning noisy PDFs and plain text into structured training data for domain-specific LLMs.

LaTeXSnipper bundles screenshot OCR, handwriting recognition, symbolic computation, and Office plugins into a single offline desktop app so you can actually use the math you capture.

Uses multimodal LLMs to transcribe PDFs into Markdown, preserving complex layouts that traditional extractors mangle.

It scrapes WeChat public articles and serves them as RSS, Markdown, and JSON because Tencent won’t.

This unofficial rebuild of a Google Research project chains specialized agents to turn rough text and data into publication-ready academic figures.

Scans running WeChat process memory to extract SQLCipher keys, then exposes your chat database as a JSON-first CLI designed for AI agent consumption.

A pipeline that turns messy PDFs and slides into structured, navigable memory for AI agents instead of flat text shards.

Unstract turns document extraction into a prompt-and-deploy workflow instead of a regex archaeology dig.

It scrapes and normalizes search results from six engines so you don't have to pay per-query for structured SERP data.

TickDB open-sources its MCP server, Skill definitions, and CLI so AI agents can query unified real-time market data across stocks, forex, and crypto without writing REST clients.

ktx is a local context layer that ingests your data stack and business knowledge so Claude, Codex, and other agents query warehouses with approved metrics instead of inventing SQL.