Awesome AI for Economists

A curated list of AI tools, libraries, and resources transforming how economists conduct research, teach, and analyze policy — from natural language data access to causal machine learning.

Scope: Tools with specific value for economists. General-purpose AI assistants are in the Appendix.

Highlights

This list is maintained by the OpenEcon team — building open-source infrastructure connecting AI to economics.

• AI-research-setup — New to this? Start here to set up Claude Code and Codex for economics research on macOS and Windows.
• OpenEcon Data — Query 330,000+ economic indicators from FRED, World Bank, IMF, and 10+ sources in plain English. Available as web app, Python API, and MCP server.
• Stata-MCP — Run Stata from VS Code, Cursor, Claude Code, and GitHub Copilot with real-time output, data viewer, and graph display.
• Econ Writing Skill — AI agent skill for writing economics papers, synthesizing 50+ guides by Cochrane, McCloskey, Shapiro, Head, and other leading economists.
• Econ Paper Review Skill — AI referee reports for economics papers: verified comments, editing notes, and a step-by-step revision plan before a real referee sees it.
• Econ Slides Skill — Turn your paper into a professional Beamer talk with a timed speaker script: conference, seminar, job-market, and discussant decks with verified layouts and honest numbers.
• Econ Auto Research — The vision: an economist-directed AI pipeline from research question to working paper, with adversarial self-refereeing. Star to shape the roadmap.
• overleaf-sync-now — Keeps local LaTeX in sync with Overleaf so AI coding agents never edit a stale paper.

Contents

• MCP Servers for Economic Data
• Coding Tools for Economists
• Causal Inference and Econometrics
• Simulation, Forecasting and Macro Modeling
• Literature Review and Research Discovery
• Economic Data and Analysis
• Academic Writing and LaTeX
• Document Processing and OCR
• NLP and Sentiment for Economics
• Policy, Labor and Alternative Data
• Finance-Specific AI
• Data Collection Tools
• Papers and Books
• Courses, Conferences and Community
• Appendix: General-Purpose AI

MCP Servers for Economic Data

Model Context Protocol (MCP) servers let AI assistants query economic databases directly. Connect Claude, Cursor, or other MCP-compatible tools to live data from FRED, World Bank, IMF, and more.

• Alpha Vantage MCP - Official server for stocks, forex, commodities, and economic indicators.
• BEA MCP Server - Exposes U.S. Bureau of Economic Analysis data including GDP, personal income, and regional accounts.
• BLS MCP Server - Bureau of Labor Statistics data: CPI, unemployment, employment, and wages via BLS API.
• Census MCP Server - Natural language queries for U.S. Census demographic data.
• Data Commons MCP Server - Query Data Commons public statistics from Census, World Bank, WHO, and BLS to ground AI answers.
• ECB MCP Server - Query European Central Bank exchange rates, policy rates, yield curves, and euro-area monetary statistics.
• Eurostat MCP Server - Query Eurostat APIs for EU statistics with dataset search, filtering, and CSV export.
• Financial Datasets MCP - Stock market data including prices, financials, and SEC filings via MCP.
• FRED MCP Server - Access all 800,000+ FRED time series with date filtering and frequency adjustment.
• IMF Data MCP Server - WEO forecasts, balance of payments, and more from the IMF.
• Nasdaq Data Link MCP - Access Nasdaq/Quandl financial and economic datasets.
• OECD MCP Server - Access 5,000+ OECD statistical datasets via SDMX API with prompt templates.
• OpenEcon - Natural language interface to 330,000+ economic indicators across FRED, World Bank, IMF, and more, with CSV, JSON, and DTA export.
• SEC EDGAR MCP - Connects AI assistants to U.S. SEC EDGAR filings, financial statements, and insider-trading data.
• TAM MCP Server - One server, eight sources: Alpha Vantage, BLS, Census, FRED, IMF, Nasdaq, OECD, and World Bank.
• U.S. Census Bureau Data API MCP - Official Census Bureau server connecting AI assistants to demographic, economic, and population statistics.
• UN Comtrade MCP Server - Access UN Comtrade international trade statistics with country and HS commodity code lookup.
• World Bank Data360 MCP - Official World Bank server giving AI agents structured access to Data360 development indicators.
• World Bank MCP Server - Community server for the legacy World Bank Open Data API (the official one is World Bank Data360 MCP above).

Browse the MCP Registry to discover more servers.

Coding Tools for Economists

• AI-research-setup - Step-by-step guide to setting up Claude Code and Codex for economics research on macOS and Windows.
• Aider - AI pair programming in your terminal with git integration and 260+ LLM support.
• awesome-econ-ai-stuff - Reusable AI skills for economists (SKILL.md standard) covering Stata, Python, and LaTeX workflows.
• Cline - Autonomous coding agent for VS Code with Plan/Act modes and MCP integration.
• Jupyter AI - Official JupyterLab extension with %%ai magic commands for code generation and explanation.
• Jupyter AI Agents - AI agents for JupyterLab with MCP integration for connecting notebooks to FRED, World Bank, and more.
• Marimo - Reactive Python notebook stored as pure .py files with built-in AI assistant.
• opencode - Open-source, provider-agnostic AI coding agent built for the terminal with a TUI.
• Positron IDE - IDE from Posit (makers of RStudio) with native R and Python support and an AI data assistant.
• Stata-MCP - Execute .do/.ado/.mata files from VS Code, Cursor, Claude Code, or GitHub Copilot with real-time output panels, built-in data viewer, and graph display.

AI Agent Frameworks

Build automated research pipelines — from data collection to analysis to report generation.

• Agno - Open-source Python framework with memory, knowledge, and 100+ toolkits including MCP support.
• AutoGen - Microsoft's multi-agent conversation framework for complex research workflows.
• chatlas - Posit's Python interface for LLMs with streaming, tool calling, and structured output.
• CrewAI - Role-based multi-agent systems for collaborative research workflows.
• DeerFlow - ByteDance's research SuperAgent for long-horizon tasks with sandboxed code execution.
• DSPy - Stanford framework for programmatic LLM optimization — "programming, not prompting."
• Econ Auto Research - Vision stage: an economist-directed research pipeline — identification judgment, pre-specified analysis, and referee-grade self-checking — built on the OpenEcon toolchain.
• ellmer - Tidyverse R package for calling LLM APIs with tool calling and structured data extraction.
• Google ADK - Google's modular multi-agent framework with MCP and A2A protocol support.
• GPT Researcher - Autonomous deep research agent producing cited reports from web sources.
• LangGraph - Stateful agent workflows built on cyclic graphs.
• MetaGPT - Multi-agent framework simulating roles (PM, analyst, engineer) with structured SOPs.
• OpenAI Agents SDK - Lightweight production-ready multi-agent framework with handoffs and guardrails.
• Pydantic AI - Type-safe agent framework with structured input/output, ideal for working with economic data.
• smolagents - Hugging Face's minimalist agent library where agents write actions as Python code.
• The AI Scientist - Sakana AI framework for fully automated research with LaTeX paper generation and automated reviewing.

Causal Inference and Econometrics

Core Libraries

• awesome-causal-inference - Curated list of causal inference resources, courses, and tools.
• causal-learn - Causal discovery algorithms (PC, FCI, GES) from the PyWhy ecosystem.
• CausalML - Uber's uplift modeling and causal inference with machine learning.
• CausalPy - Bayesian causal inference for quasi-experiments (DiD, synthetic control, RDD) powered by PyMC.
• DoubleML - Chernozhukov et al. (2018) Double/Debiased ML in Python and R.
• DoWhy - End-to-end causal inference: model, identify, estimate, refute.
• EconML - Microsoft/PyWhy library for heterogeneous treatment effects via Double ML and causal forests.
• grf - Generalized Random Forests for heterogeneous treatment effects (Athey, Tibshirani, Wager).
• pyfixest - Fast high-dimensional fixed-effects regression in Python with IV, Poisson, and modern difference-in-differences estimators.

Frontier Tools

• Causal-Copilot - LLM agent automating end-to-end causal discovery, inference, and reporting from natural-language queries.
• CausalAgent - Multi-agent AI for end-to-end causal inference through conversation.
• CausalFM - Foundation models for causal inference; pre-trained models replace per-problem estimation (ICLR 2026).
• CausalMatch - ByteDance's causal matching engine at industrial scale.
• CausalPFN - Prior-fitted transformer for amortized, in-context ATE and CATE estimation without per-dataset retraining.
• CImpact - Causal impact for time series with frequentist and Bayesian methods.
• contdid - DiD with continuous treatment, by Brantly Callaway.
• diff-diff - Scikit-learn-style difference-in-differences library for Python.
• differences - Python implementation of Callaway and Sant'Anna staggered difference-in-differences with multiple periods and triple differences.
• DoubleLingo - Double ML with LLM-based nuisance models for causal inference on unstructured data.
• moderndid - GPU-accelerated modern DiD with staggered adoption and event studies.
• pysyncon - Python synthetic control suite with classic, augmented, penalized, and robust estimators plus placebo inference.
• Salesforce CausalAI - Causal analysis for time series and tabular data.
• scpi - Synthetic control with prediction intervals for single, multiple, and staggered-adoption units, in R, Python, and Stata.
• TexIV - Extract instrumental variables from text data using ML.
• xtdml - Stata module for double machine learning in static panel models with fixed effects.

Simulation, Forecasting and Macro Modeling

Agent-Based Models and LLM Simulation

• AgentSociety - Large-scale LLM-driven social simulator modeling urban, social, and economic spaces with taxation and banking.
• BeforeIT.jl - Bank of Italy's agent-based macroeconomic model in Julia.
• Concordia - Google DeepMind library for generative agent-based modeling of social, economic, and market interactions.
• EconAgent - LLM agents with personality traits simulating macroeconomic activities (ACL 2024).
• LLM-ABM Survey - Tsinghua's toolkit and survey for LLM agent-based modeling.
• LLM-Economist - Mechanism design with 3–1,000+ LLM agents for optimal taxation research.
• MarS - Microsoft engine simulating financial markets via a generative Large Market Model of order flow.

Forecasting and Nowcasting

• Chronos - Amazon's pretrained time series models with Bolt variant for 250x speedup.
• Durbyn.jl - Julia port of R's forecast package.
• emerging-trajectories - LLM-based forecasting of political and economic events.
• Lag-Llama - First open-source foundation model for probabilistic time series forecasting.
• neuralforecast - Neural forecasting models (N-BEATS, NHITS, Transformers) for economic time series.
• Now-Casting.com - Real-time GDP nowcasts for major economies, updated as data releases occur.
• Project Spectrum - BIS/ECB/Bundesbank GenAI for inflation nowcasting, categorizing 34M+ products for CPI.
• statsforecast - Fast statistical forecasting for econometric time series.
• Sundial - Generative time-series foundation models giving probabilistic forecasts via flow matching without discrete tokenization.
• tabpfn-time-series - Zero-shot time-series forecasting that repurposes the TabPFN-v2 tabular foundation model, no training needed.
• TimeGPT - Nixtla's foundation model for time series trained on 100B+ data points.
• TimesFM - Google's decoder-only time series foundation model pre-trained on 400B+ time points.
• TiRex - NX-AI's xLSTM-based zero-shot time-series foundation model topping the GIFT-Eval forecasting leaderboard.
• Toto - Datadog's open-weight time-series foundation model, paired with the 350M-observation BOOM benchmark.
• uni2ts - Unified time series transformer models.

Game Theory and Mechanism Design

• Axelrod - Iterated Prisoner's Dilemma research with 200+ strategies and tournament simulations.
• Nashpy - Two-player game solver with support enumeration, vertex enumeration, and Lemke-Howson.
• pygambit - Game theory computation for extensive and strategic form games with a Python API.

DSGE and Structural Models

• Deep Learning for Dynamic Econ - Neural networks to solve DSGE models (course materials).
• econpizza - JAX-based solver for fully nonlinear heterogeneous-agent (HANK) macroeconomic models via automatic differentiation.
• gEconpy - DSGE toolkit in Python.
• MacroModelling.jl - Julia DSGE toolkit.
• OpenSourceEconomics - JAX-compatible DC-EGM, Kalman filters, and econ-project-templates.
• optimagic - Numerical optimization for economists (formerly estimagic).

Literature Review and Research Discovery

• alphaXiv - Line-by-line discussion on arXiv papers with AI-powered analysis.
• ASReview - Active learning for systematic reviews, reducing screening time by up to 95% (Nature Machine Intelligence).
• Asta - Ai2's open agentic-science assistant for paper finding, cited literature synthesis, and data analysis.
• Connected Papers - Visual graphs of related papers from a seed paper.
• Consensus - Evidence meter categorizing findings as yes/no/mixed across 200M+ papers.
• Elicit - Research agents synthesizing up to 80 papers into structured briefs from a large literature corpus.
• Inciteful - Free citation network analysis using graph algorithms to find key papers and connections.
• Kosmos - Autonomous AI scientist reading 1,500+ papers per run to synthesize fully cited research reports.
• LangChain Open Deep Research - Open-source configurable deep-research agent producing cited reports across any LLM and search tools.
• Litmaps - Dynamic multi-seed citation mapping with monitored searches and daily alerts for new papers.
• Meta-Mar - Free meta-analysis platform where AI reads PDFs and extracts quantitative outcomes.
• MindMap AI - Turns research papers, PDFs, and notes into structured visual mind maps for literature synthesis.
• OpenAlex - Fully open catalog of scholarly works with a free REST API and semantic search.
• OpenScholar - Retrieval-augmented LM for scientific literature synthesis across 45M+ papers (Nature 2026).
• PaperQA2 - RAG system for question answering and summarization over scientific literature.
• Rayyan - AI screening for systematic reviews with 90% time reduction and PRISMA flowcharts.
• ResearchRabbit - Citation network and semantic similarity discovery rebuilt with Litmaps.
• SciSpace - Deep review with iterative search and Zotero integration across 280M papers.
• Scite - Classifies 1.5B+ citations as supporting or contrasting with AI-driven research rankings.
• Semantic Scholar - AI-powered academic search with citation analysis, TLDR summaries, and free API across 220M+ papers.
• STORM - Stanford's LLM-powered system that researches topics and generates full reports with citations.
• Suppr - AI literature search, document translation, and deep-research reports over PubMed and OpenAlex, with a Zotero plugin.
• Undermind - Autonomously reads hundreds of papers and produces structured reports with timelines and categories.
• Zotero PapersGPT - Zotero AI plugin supporting ChatGPT, Claude, Gemini, and more for PDF chat and summaries.

Economic Data and Analysis

AI Data Analysis Platforms

• Julius AI - Upload datasets and ask questions in natural language; returns charts, regressions, and reports.
• Microsoft Data Formulator - Describe charts in English and get publication-quality output with Python code.

Economic Data Sources

• OpenEcon Data - Query 330,000+ economic indicators from FRED, World Bank, IMF, Comtrade, StatsCan, Eurostat, BIS, and more in plain English. Export to CSV, JSON, DTA, or Python. Try it | GitHub
• fedfred - Modern Python client for the FRED API at scale.
• FRED API v2 - Bulk retrieval of all series in any release across 800,000+ time series.
• FXMacroData - API and MCP server for macroeconomic releases, calendars, FX, commodities, and bond yields, queryable in plain English.
• Global Macro Database - Open-source macro dataset covering 241 countries, 1086–2024, from contemporary and historical sources.
• Trading Economics API - 300,000+ indicators from 196 countries with Python and R packages.

Academic Writing and LaTeX

• AI Research Feedback - Claude Code skills giving multi-agent referee-style feedback on economics papers before submission.
• Econ Paper Review Skill - Agent skill producing tough, fair referee reports on economics papers — verified comments, editing notes, and a revision plan. Works with Claude Code and OpenAI Codex.
• Econ Slides Skill - Agent skill turning a paper into a professional Beamer talk plus a timed speaker script — conference, seminar, job-market, and discussant decks with compile-and-render verification. Works with Claude Code and OpenAI Codex.
• Econ Writing Skill - Agent skill for writing economics papers, synthesizing 50+ guides by Cochrane, McCloskey, Shapiro, Head, and others. Works with Claude Code and OpenAI Codex.
• OpenAI Prism - Free LaTeX workspace with citation management, Zotero sync, sketch-to-equation, and real-time collaboration.
• Overleaf AI Assist - LaTeX error fixing, table generation, and equation generation from prompts or images.
• overleaf-sync-now - Keeps local LaTeX in sync with Overleaf so AI coding agents never edit a stale paper.
• Paperpal - Academic writing assistant on Overleaf, Google Docs, and Chrome.
• Refine.ink - AI referee generating peer-review-quality feedback on academic papers, piloting with top economics journals.
• Rigorous - Open-source AI pre-submission peer review generating referee-style manuscript feedback using your own LLM keys.
• Thesify - AI reviewer evaluating argumentation, methodology, and rigor.
• Typst - Modern LaTeX alternative with dramatically simpler syntax and sub-second compilation.
• Underleaf - Chrome extension for image-to-LaTeX and smart citation generation.

Document Processing and OCR

• DeepSeek-OCR - Open-weight vision model converting document images to Markdown with formula and table recognition.
• Docling - IBM open-source document parser with 0.97 table recognition accuracy.
• eScriptorium - Open-source platform for segmenting, transcribing, and OCR-ing historical and handwritten manuscripts.
• Marker - PDF to Markdown/JSON at 122 pages/sec with multi-page table merging.
• Mathpix - Screenshot-to-LaTeX OCR for equations, tables, and diagrams with PDF-to-Overleaf conversion.
• MinerU - PDF, web, and e-book content extraction with OCR for 84 languages.
• Mistral OCR 3 - Costs $1–2 per 1,000 pages with support for cursive, complex tables, and low DPI.
• OlmOCR - Allen AI's fully open-source OCR with SOTA accuracy on tables, equations, and handwriting.
• PaddleOCR-VL - Vision-language OCR extracting layout, formulas, and structured tables from documents across many languages.
• Pix2Text - Open-source tool recognizing layouts, tables, and math formulas in images, exporting LaTeX and Markdown.
• Surya - Open-source OCR toolkit for 90+ languages with layout, reading-order, and table recognition.
• Transkribus - Handwritten historical document transcription with 140+ AI models in 100+ languages.

NLP and Sentiment for Economics

• CentralBankRoBERTa - Fine-tuned RoBERTa for sentiment classification in central bank communications.
• EconBERTa - World Bank DeBERTa trained on 9.4B tokens from 1.5M economics papers with NER.
• FinBERT - Fine-tuned BERT for financial sentiment, widely cited in economics and finance research.
• FinSentGPT - Fine-tuned ChatGPT for multilingual financi