#6666th of 118 in Agent frameworks and SDKsFor finance and business, trading, stocks and crypto, finance and accounting
dexter
Terminal agent that plans and runs financial research using live market data
- Stars
- 27.8k
- License
- no license
- Last commit
- Sep 2026
- Last release
- Sep 2026
- Language
- TypeScript
21,000 on 21 Apr 202627,815 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Dexter is a TypeScript agent that runs on Bun. It breaks a financial question into research steps, calls tools for income statements, balance sheets and cash flow data from Financial Datasets, and checks its own results before answering. It supports OpenAI, Anthropic, Google, xAI, OpenRouter and Ollama models, and can also be reached through a WhatsApp gateway.
Who it is for: Developers who want a self-run agent for financial research
Strengths
- Logs every tool call and agent step to JSONL scratchpad files for inspection
- Includes loop detection and step limits against runaway execution
- Eval suite with LangSmith tracking and LLM-as-judge scoring
- Multiple model providers, including local Ollama
Weaknesses
- Needs a Financial Datasets API key, a third-party data service
- Setup lists an OpenAI key as a prerequisite; fully local use is not documented
- Focused on financial research, not a general-purpose agent library
- README says it is not intended for real trading or investment
What it needs
- no GPU
- Needs Bun, Financial Datasets API, Exa or Tavily (optional, web search), LangSmith (evals)
- Models: OpenAI, Anthropic, Google, xAI, OpenRouter
Quick answers
Is dexter open source?
Its code is public on GitHub, but the repository has no license, so by default nobody may reuse it.
Does dexter need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 118| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |