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:
- market scanning
- news retrieval
- company analysis
- industry-chain mapping
- portfolio construction
- risk analysis
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.
More from coding & agent
- Atomic Agent targets local open-model use with 1,000+ skills and MCP servers — eyishazyer · 2026-07-23
- video-use edits raw footage into final.mp4 by reading transcripts, not frames — alex_verem · 2026-07-23
- Citrolabs opens ego-lite, a browser for humans and AI agents to work in parallel — citrolabs · 2026-07-23
- Alibaba open-sources open-code-review, a hybrid LLM agent for line-level code review — alibaba · 2026-07-23
- Codex feels cleaner on a blank project than inside a messy legacy codebase — Individual-Carob5593 · 2026-07-23
- Qwen3.8-Max looks stronger on 3D web frontends than Kimi K3 — cedric_chee · 2026-07-23