Virat Singh’s Dexter shot past 24K stars this week, adding 600 in a single day, sitting near the top of GitHub Trending. It’s a CLI-based autonomous agent for deep financial research — think Claude Code, but pointed at SEC filings instead of source code.
What Dexter actually does
Ask “is Constellation Energy fairly valued” and Dexter plans the research, pulls 10-Ks, 10-Qs, 8-Ks, earnings transcripts and live prices, runs DCF and multiples, validates outputs through a separate agent, then writes a thesis. Four agents under the hood: Planner, Action, Validator, Answer. Built in TypeScript with Ink and LangChain.
Why this one matters
Most “AI agents” today are general-purpose chatbots in a wrapper. Dexter goes the other way: a vertical agent that completes a known workflow end-to-end. Singh is a finance guy who built ai-hedge-fund and ai-financial-agent before this — Dexter is the third pass and clearly the one that clicked.
Open and API-friendly
MIT licensed, runs locally, BYO key. Plug in OpenAI, Anthropic, or a local model — the agent loop is provider-agnostic. There’s even a WhatsApp gateway: link your phone, message yourself, and Dexter responds in the same chat. Anyone building finance copilots or pricing autoresearch into a fund’s workflow can fork it today.
You Might Also Like
- Insforge Hits 1 on Product Hunt and 3600 Github Stars is This What Agent Native Backends Look Like
- Openviking Treats ai Agent Memory Like a File System and 9k Github Stars say its Working
- Alibabas Agentscope Hits 21k Github Stars What Makes This Multi Agent Framework Different
- Agent Reach Hits 12k Github Stars by Solving ai Agents Biggest Blind Spot
- Microsoft Vibevoice Scores 24k Github Stars Doing What Elevenlabs Charges 99 Month for
Top AI Product 
Leave a comment