
A developer released Trading Dojo, an open-source MCP system that hands AI agents like Claude Desktop and Antigravity CLI live stock and crypto data plus simulated buy/sell tools. In a demo, the AI researched tokens, flagged HYPE, ran chart analysis, and proposed buying 2 HYPE (about 28,000円分) at a 0.1% fee.
Summaries like this, in your inbox every morning.
The project emerged from a simple frustration with existing investment apps that push one-way signals rather than letting users discuss strategy with their own AI. By adopting MCP, the developer gives the AI full access to trading tools, so the agent can carry out a multi-step flow from research to chart analysis to portfolio sizing to order execution within a single conversation. Two design turns shaped the build. First, a long holiday showed that stock prices would not move while markets were closed, so crypto support running 24/7 was added to allow testing anytime. Second, after reviewing the API terms of exchanges and brokerages, the developer dropped a central-server plan and moved everything to run locally, which keeps the project free of licensing issues and open source. The development itself used Google's Antigravity IDE with Gemini 3.8 Flash (Medium), and the resulting system runs a Next.js dashboard on localhost that reflects trades in real time.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Vannor launched its agentic marketing model, in which autonomous AI agents research, create, review, publish a…

Microsoft, Alphabet, Meta and Amazon are expected to spend more than $700 billion on AI infrastructure this ye…

Auten, which builds an MCP server that gives clients a real screen to operate, published a checklist saying si…

The developer of HACH, an AI agent resident in Slack / Teams / Chatwork, laid out three things that break duri…

TypeSafe AI released Jev, a System One Model that returns defined decisions instead of free text, with publish…

OpenAI published 722 math research manuscripts made by an unreleased AI model on October 6, 2026; a sign error…
