@PrajwalTomar_: ok this one is actually so fun lol There's now a public competition where you build an AI agent and it goes head to hea…
Summary
OpenStocks 推出一个公开竞赛平台,让开发者构建的 AI 代理与华尔街分析师在企业财报预测上正面较量,上季代理在 80 多份财报中 68% 击败华尔街,最近 20 份中赢下 17 份。
View Cached Full Text
Cached at: 10/12/26, 09:31 PM
ok this one is actually so fun lol
There’s now a public competition where you build an AI agent and it goes head to head with Wall Street analysts.
Your agent predicts a company’s earnings before the results come out. The forecast gets locked, so there’s no changing it later.
Then the company reports and your agent gets scored against what Wall Street guessed.
And honestly the agents are already winning. Last season they beat Wall Street on 68% of 80+ earnings reports, and 17 of the last 20.
That’s against people whose full-time job is doing exactly this.
My agents already work while I sleep, so this weekend I’m building one to take them on.
If you’ve been building agents, this is probably the most fun way to find out if yours is actually any good.
OpenStocks (@_openstocks): AI agents are already beating Wall Street at forecasting earnings.
67% of the time last season. 85% across the latest 20 reports.
Introducing OpenStocks, the home of AI consensus.
Company earnings forecasts produced by agents, tested publicly head to head against Wall Street.
Similar Articles
@rohanpaul_ai: The usual case against Wall Street Investment bank’s forecasts is incentives. Banks often cover companies their other d…
OpenStocks 用无利益冲突的 AI 智能体预测公司财报数据,与华尔街分析师共识对比,自 8 月 4 日开始评分以来 AI 共识在 90 份财报中赢下 60 份,典型误差 2.5% 低于华尔街的 2.9%。
@sunmer575399: Found a fantastic open-source project TradingAgents, 96.1k stars, significantly lowering the AI barrier. Uses multiple AI agents for stock trading: some monitoring financial reports, others watching news, and managing sentiment, then voting on decisions, much more reliable than single-model guesses. Can easily connect to NVIDIA, Kimi, Groq, Mis…
TradingAgents is an open-source multi-agent framework for AI-driven financial trading, supporting multiple AI models and data sources, with checkpointing functionality.
@Jason23818126: After earning +1.46 million in two years, someone open-sourced their research system. The project is called AI Berkshire, and the real trading results are directly released: 2024: +69.29% 2025: +66.38% The core is not "AI stock picking", but breaking down the investment frameworks of Buffett, Munger, Duan Yongping, Li Lu into...
This project open-sources an AI research system based on the frameworks of value investing masters like Buffett, Munger, Duan Yongping, and Li Lu. It uses Claude Code/Codex to enable multi-agent parallel analysis of financial statements, valuations, etc., and shows real trading returns of over 1.46 million yuan in two years, significantly outperforming major indices.
@axichuhai: Found a 50k-star project on GitHub that turns AI models into automated stock analysts. Just configure your watchlist, and it automatically pulls candlestick charts, technical indicators, news announcements, and fundamental data to generate a decision dashboard. Core conclusions, trend scores, buy/sell points, risk alerts, catalysts, and operations...
This is a 50k-star open-source project on GitHub that uses AI models to automatically analyze stock quotes, technical indicators, and fundamental data, generating a decision dashboard with trend scores, buy/sell points, and risk alerts. It supports daily automated runs and multi-platform push notifications.
@_zheergen: Wow! Someone built a Claude Code for financial markets! It can not only analyze stocks and dig into earnings reports, but also let multiple AI analysts work at the same time — automated market monitoring, research report generation, and even connecting to brokerages for trading. LangAlpha, 2.2K Stars, Apache-2.0 open source, a platform built specifically for…
The open-source project LangAlpha has been released, dubbed the Claude Code for financial markets: it brings together multi-AI analyst collaboration, financial data, long-term memory, automated report generation, market alerts, and brokerage trading interfaces, with support for custom models and local self-hosting.