DojoAgents passes 1,000 stars as an open-source financial research agent framework

机器之心 · wechat · 2026-07-23

Machine Heart introduces DojoAgents, an open-source financial autonomous-agent framework that has already passed 1,000+ GitHub stars.

The system breaks financial research into tool-driven agent steps such as:

The article argues that once large models become baseline tools for summarizing news and explaining earnings, the real bottleneck is no longer “answering questions” but building a persistent research loop that can keep updating its understanding, call tools, and surface verifiable evidence.

It also shows use cases like cross-market event analysis, simulated portfolios, and anonymized holdings-screening, and explains that the framework supports OpenAI, Anthropic, Gemini, DeepSeek, GLM, local models, and local deployment via Docker-like setup instructions.

The piece frames AlphaDojo as an open foundation for autonomous finance intelligence, with future plans to add more datasets, evaluation tools, and multi-agent collaboration.

Original post →

More from coding & agent

coding & agent channel →