evidently
github.comEvidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen
- GitHub stars
- 7,980
- Language
- Jupyter Notebook
- Code license
- Apache-2.0
DUCKQUANT / THE QUANT & AI DIRECTORY
14,444 resources, ranked by in-directory PageRank
Showing 433–468 of 14,444 resources
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen
AutoGluon is an open-source AutoML toolkit covering tabular, time-series, image and text data.
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking
A simple, easy, customizable Gymnasium environment for trading.
The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Open-Source Evaluation & Testing library for LLM Agents
[ACM ICAIF'25] Federated Financial Reasoning Distillation
FinLBench: A Benchmark for Evaluating Large Language Models on Long-Text Financial Documents
An executable, bilingual benchmark for evaluating LLMs and AI agents on quantitative-investment work
FinFusion: S&P 500 return forecasting with Temporal Fusion Transformers - compares TFT, ARIMAX, LSTM, and regime-aware variants.
Real-time trading decisions for Jane Street Kaggle competition. LightGBM + feature engineering on 47M market records. Weighted R2: 0.014, directional accuracy
Source code for paper Residual Learning in Empirical Asset Pricing
Master's thesis code implementing deep hedging of derivative portfolios with neural networks.
FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets
Codes and data for KDD 2026 paper "Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?"
A Business-Driven Real-World Financial Benchmark for Evaluating LLMs
[NeurIPS 2025 & ICLR 2025 Financial AI Best Paper Award] A multi-agent framework that leverages LLMs to simulate socio-economic systems
Public repository by HiRenyi. Primary language: Python.
ABIDES: Agent-Based Interactive Discrete Event Simulation
AI-powered stock analyst using multi-agent architecture. Features 6 specialized agents (Valuation, Sentiment, Fundamentals, Technical, Risk, Portfolio) for trading signal generation. Includes ML pipeline, backtesting…
Contribute to alimert05/zero-shot-stock-xai development by creating an account on GitHub.
Vise is an AI-driven portfolio management platform that builds and rebalances personalized portfolios for financial advisors
ConvFinQA is a conversational finance QA dataset requiring multi-step numerical reasoning over financial reports
Agentic research on Japanese equities. Competing analysts produce investment theses from regulatory filings
Reproducible benchmarks for LLM output drift and agent replay in financial operations: DFAH-Bench, the installable dfah package, and a hands-on workshop
CLI that diffs a company's 10-K/10-Q year-over-year (Risk Factors, MD&A, Loughran-McDonald tone shift) and fact-checks every number in its own report against
Finance-grade tool-calling agent over SEC filings for any US public company: exact XBRL numbers (never LLM arithmetic), every claim cited, abstains instead of
Rogo provides AI agents that automate financial analysis and diligence workflows for investment banks and investors
Numerai is a crowdsourced AI hedge fund: data scientists submit encrypted ML models whose predictions drive a live fund
Bridgewise uses generative AI to produce research and buy/hold/sell ratings on global equities for brokers and exchanges
Magnifi is an AI investing assistant that answers natural-language questions about stocks, funds and portfolios
Holly is Trade Ideas' AI-powered stock-scanning engine that ranks intraday trade candidates from live market data
R - Constructs a yield curve by the Smith-Wilson method from a table of LIBOR and SWAP rates.
MetaTrader 5 trading platform is a free Forex and stock trading tool
Astt — Open-source, self-hosted net worth & portfolio tracker
Open solution code for the Jane Street 2024 Kaggle competition on real-time market data forecasting