Virat Singh's banner

Virat Singh

@virattt • 49,049 subscribers

Founder @findatasets, market infra for your agents.

Shorts

Dexter hit 10,000 stars on GitHub. It’s OpenClaw and Claude Code, for finance. What Dexter can do: • find undervalued stocks • break down financials • turn research into a thesis All our code is open source.

Dexter hit 10,000 stars on GitHub. It’s OpenClaw and Claude Code, for finance. What Dexter can do: • find undervalued stocks • break down financials • turn research into a thesis All our code is open source.

1,002,607 views

I’ve been building Dexter for 2 months now. It’s like Claude Code, but for finance. What Dexter can do: • find undervalued stocks • analyze them in detail • build investment thesis All of the code is open source. Bonus: Dexter can also run on local LLMs.

I’ve been building Dexter for 2 months now. It’s like Claude Code, but for finance. What Dexter can do: • find undervalued stocks • analyze them in detail • build investment thesis All of the code is open source. Bonus: Dexter can also run on local LLMs.

552,631 views

Dexter just hit 25,000 stars on GitHub. It's like Claude Code, but for finance. How I use it: • Screen stocks • Track earnings • Monitor my portfolio Bring your own data, search, LLM providers. It’s 100% open source.

Dexter just hit 25,000 stars on GitHub. It's like Claude Code, but for finance. How I use it: • Screen stocks • Track earnings • Monitor my portfolio Bring your own data, search, LLM providers. It’s 100% open source.

42,310 views

Introducing Dexter. An open source financial agent in ~200 lines of code. Think: Claude Code, but for finance. What Dexter does today: • plans tasks • runs on its own • validates its work • researches stocks It’s built with OSS tools like for managing LLMs, prompts, outputs, etc. No coding experience needed to run. Goal: build the best financial agent and share every line of code along the way. Next: evals, starting with

Introducing Dexter. An open source financial agent in ~200 lines of code. Think: Claude Code, but for finance. What Dexter does today: • plans tasks • runs on its own • validates its work • researches stocks It’s built with OSS tools like for managing LLMs, prompts, outputs, etc. No coding experience needed to run. Goal: build the best financial agent and share every line of code along the way. Next: evals, starting with

316,597 views

I cleaned up a lot of Dexter’s code today. Our core agent loop is now ~300 lines. What Dexter does: • finds undervalued stocks • analyzes them deeply • builds valuation models All of it is open source.

I cleaned up a lot of Dexter’s code today. Our core agent loop is now ~300 lines. What Dexter does: • finds undervalued stocks • analyzes them deeply • builds valuation models All of it is open source.

188,756 views

Introducing Dexter 2.0 Open source. Built for financial research. Like Claude Code, but for stocks. What Dexter does: • plans tasks • runs on its own • validates its work • researches stocks It uses OSS tools like , with a fresh stack of typescript, react, ink, and bun. Fast to build. Easy to use. No coding required. My favorite project of the year.

Introducing Dexter 2.0 Open source. Built for financial research. Like Claude Code, but for stocks. What Dexter does: • plans tasks • runs on its own • validates its work • researches stocks It uses OSS tools like , with a fresh stack of typescript, react, ink, and bun. Fast to build. Easy to use. No coding required. My favorite project of the year.

209,854 views

Dexter now writes investment memos. My flow: I pick a stock and ask Dexter to pull all data + learn everything about it. Then Dexter gives me variant takes and bull / bear on the stock. Total time is ~3 mins. I went from idea → long $DDOG at $109.

Dexter now writes investment memos. My flow: I pick a stock and ask Dexter to pull all data + learn everything about it. Then Dexter gives me variant takes and bull / bear on the stock. Total time is ~3 mins. I went from idea → long $DDOG at $109.

15,280 views

I’m really proud of this launch. We just shipped an Earnings Feed that updates ~2 seconds after earnings go live. It gives you every reported financial through a clean, structured API. Available to all today.

I’m really proud of this launch. We just shipped an Earnings Feed that updates ~2 seconds after earnings go live. It gives you every reported financial through a clean, structured API. Available to all today.

49,505 views

Julius is the best AI data analyst I’ve used. I asked it to pull Delta's latest earnings, check if they beat / missed, and how rising oil costs are impacting margins. It wrote code, drew charts, and analyzed everything in ~7 secs. Lovely work by the Julius AI team.

Julius is the best AI data analyst I’ve used. I asked it to pull Delta's latest earnings, check if they beat / missed, and how rising oil costs are impacting margins. It wrote code, drew charts, and analyzed everything in ~7 secs. Lovely work by the Julius AI team.

45,247 views

I just upgraded our Warren Buffett agent. Makes our AI hedge fund more realistic. Warren Buffett agent: 1 • analyzes business fundamentals 2 • evaluates competitive moat 3 • assesses management quality 4 • calculates margin of safety 5 • seeks long-term value This is one of our most disciplined agents. It only says "buy" when both fundamentals are strong AND there's a margin of safety above 30%. 1. Business Fundamentals: Examines financial stability, debt levels, and consistent earnings growth over time. 2. Competitive Moat: Evaluates stability of ROE and profit margins to identify durable competitive advantages. 3. Management Quality: Monitors share repurchases vs. dilution and dividend policies to assess capital allocation skills. 4. Margin of Safety: Requires a 30% discount to intrinsic value before considering any purchase. 5. Value Focus: Prioritizes businesses with predictable cash flows and strong fundamentals over speculative growth stories. What agent should we add next?

I just upgraded our Warren Buffett agent. Makes our AI hedge fund more realistic. Warren Buffett agent: 1 • analyzes business fundamentals 2 • evaluates competitive moat 3 • assesses management quality 4 • calculates margin of safety 5 • seeks long-term value This is one of our most disciplined agents. It only says "buy" when both fundamentals are strong AND there's a margin of safety above 30%. 1. Business Fundamentals: Examines financial stability, debt levels, and consistent earnings growth over time. 2. Competitive Moat: Evaluates stability of ROE and profit margins to identify durable competitive advantages. 3. Management Quality: Monitors share repurchases vs. dilution and dividend policies to assess capital allocation skills. 4. Margin of Safety: Requires a 30% discount to intrinsic value before considering any purchase. 5. Value Focus: Prioritizes businesses with predictable cash flows and strong fundamentals over speculative growth stories. What agent should we add next?

251,250 views

Dexter can now search insider trades. Ask: “Are PLTR execs buying or selling the stock?” Dexter pulls latest Form 4 filings, reads them, and answers using data straight from the SEC.

Dexter can now search insider trades. Ask: “Are PLTR execs buying or selling the stock?” Dexter pulls latest Form 4 filings, reads them, and answers using data straight from the SEC.

103,398 views

Dexter can now access any financial metric. The coverage here is massive, and includes over 20,000 stocks over 30 years. Metrics are from: 1 • income statements 2 • balance sheets 3 • cash flow statements 4 • key ratios Powered by a new financial metric subagent.

Dexter can now access any financial metric. The coverage here is massive, and includes over 20,000 stocks over 30 years. Metrics are from: 1 • income statements 2 • balance sheets 3 • cash flow statements 4 • key ratios Powered by a new financial metric subagent.

77,998 views

Stock market data shouldn’t cost $20,000. I built Financial Datasets to fix this. For $20 you get: • 30 years of earnings • Every S&P 500 company • In under 30 secs No contracts. No restrictions. No limits.

Stock market data shouldn’t cost $20,000. I built Financial Datasets to fix this. For $20 you get: • 30 years of earnings • Every S&P 500 company • In under 30 secs No contracts. No restrictions. No limits.

131,794 views

Our AI hedge fund has a new agent. Nassim Taleb agent, which bets on chaos. How it works: 1 • finds big upside bets 2 • avoids fragility 3 • buys what thrives in crisis It’s our 3rd macro agent, after Stan Druckenmiller and Rakesh Jhunjhunwala.

Our AI hedge fund has a new agent. Nassim Taleb agent, which bets on chaos. How it works: 1 • finds big upside bets 2 • avoids fragility 3 • buys what thrives in crisis It’s our 3rd macro agent, after Stan Druckenmiller and Rakesh Jhunjhunwala.

36,704 views

Dexter can now read SEC filings. It pulls filings, finds the important parts, and answers with citations. Supported filings: • 10-K • 10-Q • 8-K Coverage: 20,000 stocks over 30 years. All of the code is open source.

Dexter can now read SEC filings. It pulls filings, finds the important parts, and answers with citations. Supported filings: • 10-K • 10-Q • 8-K Coverage: 20,000 stocks over 30 years. All of the code is open source.

58,148 views

Gemini 2.5 Pro is live in our AI hedge fund!

Gemini 2.5 Pro is live in our AI hedge fund!

167,642 views

I’m rebuilding Dexter from scratch. Like Claude Code, we’re moving from python to typescript. Here is why: • richer UI • better async • type safety • full-stackness Claude Code uses Ink, which is React for command line apps. We will use it as well. Excited to rebuild.

I’m rebuilding Dexter from scratch. Like Claude Code, we’re moving from python to typescript. Here is why: • richer UI • better async • type safety • full-stackness Claude Code uses Ink, which is React for command line apps. We will use it as well. Excited to rebuild.

61,222 views

The future of finance isn’t closed. It’s open source. Meet Dexter, a deep research agent built in public. It’s crushing evals, improving fast, and every line of code is yours. Finance belongs to everyone.

The future of finance isn’t closed. It’s open source. Meet Dexter, a deep research agent built in public. It’s crushing evals, improving fast, and every line of code is yours. Finance belongs to everyone.

53,272 views

Dexter can now use local LLMs. We finally added ollama support today. Includes models like: • qwen 3 • gemma 3 • deepseek r1 Because Dexter is built on LangChain, switching between local and cloud models is easy. Huge thanks to Harsh Gupta for shipping this.

Dexter can now use local LLMs. We finally added ollama support today. Includes models like: • qwen 3 • gemma 3 • deepseek r1 Because Dexter is built on LangChain, switching between local and cloud models is easy. Huge thanks to Harsh Gupta for shipping this.

36,456 views

We’re launching a new Dexter tomorrow. Biggest change is the core agent loop. Some highlights: ~32% less code ~60% faster ~40% cheaper This is the 3rd rewrite of Dexter. So far its crushing our benchmarks.

We’re launching a new Dexter tomorrow. Biggest change is the core agent loop. Some highlights: ~32% less code ~60% faster ~40% cheaper This is the 3rd rewrite of Dexter. So far its crushing our benchmarks.

33,548 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

I made a real-world AI hedge fund team. It has 4 agents: 1 • market data agent 2 • quant agent 3 • risk manager agent 4 • portfolio manager agent You can run all of my code below. No prior coding experience is required. The agents work sequentially, passing messages to the next agent. 1 • Market Data Agent gathers market data and calculates technical signals. 2 • Quant Agent takes market data and generates a buy, sell, or hold signal. 3 • Risk Management Agent takes trading signal and generates a risk signal. 4 • Portfolio Management Agent considers all signals and makes a final trading decision.

I made a real-world AI hedge fund team. It has 4 agents: 1 • market data agent 2 • quant agent 3 • risk manager agent 4 • portfolio manager agent You can run all of my code below. No prior coding experience is required. The agents work sequentially, passing messages to the next agent. 1 • Market Data Agent gathers market data and calculates technical signals. 2 • Quant Agent takes market data and generates a buy, sell, or hold signal. 3 • Risk Management Agent takes trading signal and generates a risk signal. 4 • Portfolio Management Agent considers all signals and makes a final trading decision.

368,451 views • 1 year ago

It's happening. Last night, I started downloading financial data from the SEC. • income statements • balance sheets • cash flow statements 10,000+ public companies. 3 million rows in total. I’m using multiple worker nodes to pull, parse, and clean the data. The orchestration is beautiful. This week, I will: • create an API for accessing the data • write and publish developer docs • add auth so you can use it cc buildspace nights & weekends 🔊 on for the video

It's happening. Last night, I started downloading financial data from the SEC. • income statements • balance sheets • cash flow statements 10,000+ public companies. 3 million rows in total. I’m using multiple worker nodes to pull, parse, and clean the data. The orchestration is beautiful. This week, I will: • create an API for accessing the data • write and publish developer docs • add auth so you can use it cc buildspace nights & weekends 🔊 on for the video

313,830 views • 1 year ago

I built a stock market API in 42 days. All during buildspace s5. What is the API? Today, it lets you pull financials for 16,000 tickers going back 30+ years. Why did I build the API? Because the big providers have: • poor API design • poor documentation • expensive sales contracts • strict data retention policies How did I build it? I started building the API from scratch at the start of s5 in early June. I got deep into the SEC Edgar API and cracked how to scrape at scale. Sonnet 3.5 from Anthropic was a godsend for this. I hacked early mornings, late nights, and weekends, with a full-time job. Day by day. Code by code. I set weekly goals and hit each one. End result: I’m excited to see where this API goes. It may go nowhere, but I’ll always know that I can set goals and crush them.

I built a stock market API in 42 days. All during buildspace s5. What is the API? Today, it lets you pull financials for 16,000 tickers going back 30+ years. Why did I build the API? Because the big providers have: • poor API design • poor documentation • expensive sales contracts • strict data retention policies How did I build it? I started building the API from scratch at the start of s5 in early June. I got deep into the SEC Edgar API and cracked how to scrape at scale. Sonnet 3.5 from Anthropic was a godsend for this. I hacked early mornings, late nights, and weekends, with a full-time job. Day by day. Code by code. I set weekly goals and hit each one. End result: I’m excited to see where this API goes. It may go nowhere, but I’ll always know that I can set goals and crush them.

236,442 views • 1 year ago

We hit 30,000 stars on GitHub this week. Best project I’ve worked on in 2025.

We hit 30,000 stars on GitHub this week. Best project I’ve worked on in 2025.

105,904 views • 1 year ago

It's going live. My stock market API now has coverage for all S&P 500 tickers. • income statements • balance sheets • cash flow statements 30+ years of data. No API limits. You can connect your AI financial agents to this data. This open beta will run for ~1 week. Main goal is to load test the system prior to a full launch. Full launch includes coverage for 15,000+ stocks. Three things: • create an account 🙏 • send API requests 💻 • come hang in the discord ❤️ cc buildspace Farza 🇵🇰🇺🇸

It's going live. My stock market API now has coverage for all S&P 500 tickers. • income statements • balance sheets • cash flow statements 30+ years of data. No API limits. You can connect your AI financial agents to this data. This open beta will run for ~1 week. Main goal is to load test the system prior to a full launch. Full launch includes coverage for 15,000+ stocks. Three things: • create an account 🙏 • send API requests 💻 • come hang in the discord ❤️ cc buildspace Farza 🇵🇰🇺🇸

100,860 views • 1 year ago

Introducing my first MCP server. Connects your agents to the stock market. We have 3 initial tools: 1 • get financial statements 2 • get stock prices 3 • get market news Everything is real-time from Financial Datasets It works perfectly with MCP hosts like Claude Desktop, etc. Lmk if you are building an MCP host in finance and let’s team up.

Introducing my first MCP server. Connects your agents to the stock market. We have 3 initial tools: 1 • get financial statements 2 • get stock prices 3 • get market news Everything is real-time from Financial Datasets It works perfectly with MCP hosts like Claude Desktop, etc. Lmk if you are building an MCP host in finance and let’s team up.

59,167 views • 1 year ago

I am rebuilding my AI financial agent. Fully open source. Runnable locally. Today's change adds stock price charts. How it works: • ask a question • agent selects best tool • agent renders UI components • agent answers question is perfect for this project: • rich existing toolkits • new tools easy to add • backend is python • frontend is typescript This will be one of my core projects moving forward. Feature requests are welcome.

I am rebuilding my AI financial agent. Fully open source. Runnable locally. Today's change adds stock price charts. How it works: • ask a question • agent selects best tool • agent renders UI components • agent answers question is perfect for this project: • rich existing toolkits • new tools easy to add • backend is python • frontend is typescript This will be one of my core projects moving forward. Feature requests are welcome.

37,175 views • 1 year ago

I spent 7 days it’s finally working… My stock market API is a remote MCP server Toughest part was setting up OAuth 2.1 Easiest part was deploying on @cloudflare I love seeing financial datasets connect to Claude.

I spent 7 days it’s finally working… My stock market API is a remote MCP server Toughest part was setting up OAuth 2.1 Easiest part was deploying on @cloudflare I love seeing financial datasets connect to Claude.

14,255 views • 11 months ago

No more content to load