Domain Apps

A research framework that assigns LLMs to trading-floor roles—analyst, researcher, trader, risk manager—to debate and execute simulated stock decisions.

Kronos recasts noisy, multi-dimensional candlestick data as hierarchical discrete tokens so an autoregressive Transformer can forecast financial markets like a language model.

Strix deploys autonomous LLM agents to attack your applications and validate findings with working proof-of-concepts, trading the false-positive noise of static scanners for actual exploits.

DeepTutor was built to turn generic LLM chats into persistent, agentic tutoring that can research, co-write, and remember across sessions.

It corrals 500+ news feeds and dozens of data streams into one dashboard so you can monitor geopolitical, financial, and infrastructure signals without sending everything to a cloud LLM.

A Linux Foundation project that collects reference implementations and best-practice notebooks for every stage of a recommendation-system pipeline.

It exists to bundle quantitative analytics, AI research, and live trading into one native desktop app for users who would rather not rent a Bloomberg terminal.

It gives LLM agents real brokerage access, then cages live trading inside strict mandates, kill switches, and audit ledgers.

To explore AI-driven trading, it orchestrates a committee of LLM agents cast as famous investors who analyze stocks and generate orders that never reach a market.

MAA automates the daily chores of Arknights by treating the game screen as a computer vision problem, using OpenCV and OCR to handle farming, recruitment, and base shifts without human tapping.

FinGPT offers lightweight, open-source financial LLMs and datasets as an alternative to million-dollar proprietary training runs like BloombergGPT.

Qlib provides a full-stack ML pipeline for quantitative finance—from alpha research to order execution—and now plugs into an LLM agent to automate R&D.

It automates video transcription, translation, and dubbing while stubbornly insisting on single-line, human-readable subtitles.

OpenBB normalizes proprietary and public financial data so engineers can feed the same sources to Python scripts, REST APIs, Excel, and AI agents without rebuilding integrations.

Python toolkit for algorithmic trading across stocks, options, futures, and crypto, with an unusual obsession with classical chart patterns.

A PyTorch toolkit that treats robot learning like Hugging Face treats NLP: standardized datasets, pretrained policies, and one interface for many arms.

A framework-free Python multi-agent system built to scrape, debate, and report on public sentiment across 30+ Chinese and international social platforms.

An open-source trading platform where AI agents onboard themselves by reading a markdown skill file, then publish signals, copy trades, and paper-trade across major markets.

This Chinese-localized fork rebuilds a multi-agent LLM trading framework in FastAPI and Vue, adds A-share data and domestic model support, and explicitly refuses to place live orders.

An AI-powered resume builder that tailors your CV to specific job descriptions instead of spraying the same PDF everywhere.