Data Tooling ✕

Data Tooling

underdogs · picking up speed
01
KKKKhazix/AIHOT
+31% /wk +474 ★/day↗accelerating

Because one person can't be the expert in every industry, AIHOT open-sources its entire automated newsroom — every prompt and threshold — for anyone to retarget at their own field.

★ 10.8k TypeScript LLMOps · Eval · explained
02
only-cli/oc
+22% /wk +23 ★/day↗accelerating

oc turns any website into a compact, numbered CLI so AI agents can browse without drowning in HTML tokens.

★ 704 JavaScript Coding Assistants · explained
03
ScrapeCreators/social-media-research-skills
+18% /wk +171 ★/day↗accelerating

It gives AI agents complete social media research workflows—outlier detection, comment mining, competitor teardowns—that produce actionable business artifacts instead of raw API responses.

★ 6.6k Python Coding Assistants · explained
04
fastcrw/crw
+13% /wk +23 ★/day↗accelerating

Built to give AI agents a faster, more accurate way to turn the web into markdown, offering drop-in Firecrawl compatibility and a self-hostable single binary.

★ 1.3k Rust Data Tooling · explained
05
SSShooter/ebook-to-mindmap
+11% /wk +23 ★/day↗accelerating

It turns ebooks into mind maps and summaries you can export, dodging lock-in.

★ 1.4k TypeScript Domain Apps · explained
07
pymupdf/pymupdf4llm
+6.6% /wk +22 ★/day↗accelerating

A thin Python wrapper around PyMuPDF that turns documents into structured Markdown, JSON, or plain text—layout-aware, with selective OCR that skips clean pages.

★ 2.3k Python Data Tooling · explained
08
any4ai/AnyCrawl
+5.0% /wk +25 ★/day↗accelerating

Node.js crawler that turns raw web pages into structured JSON via an LLM layer, with SERP support and a self-hosted API.

★ 3.6k TypeScript Data Tooling · explained
09
spiceai/spiceai
+4.8% /wk +22 ★/day↗accelerating

Spice gives data-heavy AI applications a local, low-latency data plane that federates existing sources and serves SQL, search, and LLM inference from a single Rust runtime.

★ 3.2k Rust Inference · Serving · explained
10
argilla-io/distilabel
+4.4% /wk +22 ★/day↗accelerating

Distilabel is a framework for engineers who need to synthesize training data and collect AI feedback from any LLM provider using research-backed, scalable pipelines.

★ 3.5k Python Data Tooling · explained
11
torchgeo/torchgeo
+3.7% /wk +22 ★/day↗accelerating

TorchGeo makes PyTorch work with satellite imagery by handling coordinate systems, spectral bands, and massive rasters for you.

★ 4.2k Python Computer Vision · explained
12
lance-format/lance
+2.8% /wk +30 ★/day↗accelerating

Lance treats vectors, images, and embeddings as first-class citizens instead of awkward guests at Parquet's SQL-only party.

★ 7.3k Rust RAG · Search · explained
13
ScrapingBee/chatgpt-scraper-api
+5.7% /wk +12 ★/day↗accelerating

Documentation and SDK examples for a paid API that replaces brittle CSS selectors with natural-language prompts and optional live search.

★ 1.4k RAG · Search · explained
14
OpenHUTB/hutb
+3.6% /wk +3.9 ★/day↗accelerating

A research platform that fuses CARLA, AirSim, and OpenSim into one Unreal-based sandbox for training autonomous cars, drones, and embodied humans.

★ 752 C++ Domain Apps · explained
15
oomol-lab/pdf-craft
+3.0% /wk +29 ★/day↗accelerating

A Python tool that uses DeepSeek OCR to convert scanned academic books into structured Markdown or EPUB without calling LLM APIs.

★ 6.8k Python Computer Vision · explained
16
buxuku/SmartSub
+1.6% /wk +14 ★/day↗accelerating

A cross-platform Electron app that runs speech recognition locally, then hands the results off to anything from Baidu to DeepSeek for translation.

★ 6.1k TypeScript Data Tooling · explained
17
Javis603/token-monitor
+2.9% /wk +16 ★/day↗accelerating

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.

★ 3.7k JavaScript LLMOps · Eval · explained
18
Ontos-AI/knowhere
+2.3% /wk +13 ★/day↗accelerating

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

★ 4k Python RAG · Search · explained
19
openags/paper-search-mcp
+2.4% /wk +11 ★/day↗accelerating

An MCP server that searches 20+ academic sources and actually tells you when it can't download something instead of hallucinating a PDF.

★ 3.1k Python Coding Assistants · explained
20
aakarim/OpenLore
−0.1% /wk −0.3 ★/day→steady

When several agents each carry their own copy of the docs, you get several versions of the truth — OpenLore is one governed Markdown source they all read from instead.

★ 1.7k Go Agents · explained Feature
loading more…

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.