LLMQuant
quant-mindQuantMind is an AI-powered knowledge extraction and retrieval framework that transforms unstructured financial research (papers, news, reports, SEC...
96 repositories found
LLMQuant
quant-mindQuantMind is an AI-powered knowledge extraction and retrieval framework that transforms unstructured financial research (papers, news, reports, SEC...
OpenDCAI
DataFlowDataFlow is a low-code platform for generating, cleaning, and preparing data for LLM training using LLM-based operators and visual pipelines. It...
lotus-data
lotusLOTUS is a Python framework for bulk processing unstructured and structured data using LLMs and agents at scale, with optimization for accuracy and...
getnao
naonao is an open-source analytics agent framework that enables data teams to build conversational interfaces for querying data warehouses (BigQuery,...
speedyapply
2027-AI-College-JobsA curated job board aggregating AI/ML internship and new graduate positions updated daily, targeting college students entering the tech field. It...
Jon-Becker
prediction-market-analysisA specialized research framework for collecting, storing, and analyzing prediction market data from Polymarket and Kalshi, featuring the largest...
D4Vinci
ScraplingScrapling is an adaptive Python web scraping framework that handles everything from single HTTP requests to full browser-based crawling with stealth...
datajuicer
data-juicerData-Juicer is a modular data processing platform optimized for preparing multimodal datasets for foundation model training and inference. It...
ruc-datalab
DeepAnalyzeDeepAnalyze is an agentic LLM system for autonomous data science workflows, automating tasks from data preparation through report generation across...
rilldata
rillRill is a business intelligence platform built on OLAP engines (DuckDB, ClickHouse) designed for both human analysts and AI agents to build, query,...
Asabeneh
30-Days-Of-Python30 Days Of Python is a structured, self-paced curriculum that guides learners through Python from absolute basics (variables, operators, data types)...
PrefectHQ
prefectPrefect is a Python workflow orchestration framework for building and deploying resilient data pipelines with built-in scheduling, retries, caching,...
akfamily
akshareAKShare is a Python library that provides unified access to Chinese financial data sources including stocks, bonds, futures, options, and economic...
meltano
meltanoMeltano is a declarative, code-first data integration engine designed to simplify building and maintaining ELT (extract-load-transform) pipelines. It...
dbt-labs
metricflowMetricFlow is a semantic layer for defining, building, and maintaining metrics in code that compiles metric definitions into reusable SQL. It...
TerriaJS
terriajsTerriaJS is a TypeScript library for building web-based geospatial data exploration platforms with 2D/3D visualization capabilities (Cesium globe...
hibuz
dev-conf-replayA curated directory of replay links for Korean IT conferences, seminars, and developer talks, organized by topic (AI, blockchain, cloud, DevOps,...
bitol-io
open-data-contract-standardThe Open Data Contract Standard (ODCS) is a structured specification for defining agreements between data producers and consumers, covering schema,...
tinyplex
tinybaseTinyBase is a reactive data store and synchronization engine for JavaScript/TypeScript applications, designed for real-time data management with...
spiceai
spiceaiSpice is a Rust-based SQL query, full-text search, and LLM-inference engine designed as a sidecar or distributed system to accelerate data access for...
deepnote
deepnoteDeepnote is an AI-native data notebook platform that serves as a drop-in replacement for Jupyter, designed for data professionals and teams who need...
dlt-hub
dltdlt is an open-source Python library that automates data loading from diverse sources (REST APIs, SQL databases, cloud storage) into structured...
NVIDIA-NeMo
CuratorNeMo Curator is a GPU-accelerated data preprocessing and curation toolkit built by NVIDIA for preparing large-scale text, image, video, and audio...
quiltdata
quiltQuilt is a scientific data management platform on AWS that enables teams to create, version, and discover deeply contextualized data packages with...
uwdata
mosaicMosaic is a TypeScript framework for linking interactive data visualizations, tables, and widgets to a backing database (primarily DuckDB) for...
skrub-data
skrubskrub is a Python library that streamlines machine learning workflows by providing specialized tools for data cleaning, preprocessing, and...
robustmq
robustmqRobustMQ is a unified messaging engine written in Rust that consolidates multiple messaging protocols (MQTT, Kafka, AMQP, NATS) into a single binary...
odota
webOpenDota Web is a React-based UI for browsing Dota 2 player statistics and game data via the OpenDota API. It serves competitive gaming analytics...
apache
devlakeApache DevLake is an open-source data platform that aggregates fragmented DevOps tool data into unified dashboards and metrics for engineering teams....
BIT-DataLab
Edit-BananaEdit Banana is a framework that converts static diagrams and figures into editable DrawIO (XML) formats using SAM 3 and multimodal LLMs. It...
Showing 30 of 96
Weekly newsletter
Every Monday: the repos worth your attention, anomaly signals and deep AI analysis. No fluff, unsubscribe any time.