Skip to main content

Documentation Index

Fetch the complete documentation index at: https://kindling.birklid.com/llms.txt

Use this file to discover all available pages before exploring further.

Open SourceApplications Layer

​
Dexter

“Claude Code, but for financial research” — an autonomous agent that breaks down complex investment questions, gathers real data, and validates its own work.
Dexter GitHub

Type

Open Source

Stack Layer

Applications

Language

TypeScript

Stars

24.9k+

​
What it is

Dexter is an autonomous financial research agent built in TypeScript. Given a complex financial question — “What are the key risks in Nvidia’s current valuation?” — it decomposes the inquiry into a structured research plan, selects and calls appropriate financial data tools (income statements, balance sheets, cash flow data, real-time price feeds), iteratively executes the research, self-validates via reflection loops, and returns comprehensive findings. Safety guardrails including loop detection and execution limits prevent runaway behavior. The project is described as “Claude Code, but built specifically for financial research” by its author virattt, a prominent AI × finance developer and content creator. Unlike generic research agents, Dexter is purpose-built for financial domains with relevant data tools and domain-specific validation patterns.
Use this when you need to automate deep equity or financial research — multi-source analysis that synthesizes fundamental data, market context, and financial statements into a coherent answer — without manually orchestrating each data-gathering step.

​
Get started

GitHub ↗

Source, API setup, and usage examples.

TradingAgents

Multi-agent framework that mirrors a trading firm’s analyst structure.

Alpaca

Trading API for connecting research conclusions to live market execution.