666ghj/MiroFish

This page introduces an external open-source repository. It is not an HDATF product.

What it does

MiroFish builds a simulated world from uploaded seed material such as news, policy drafts or financial signals, where thousands of agents with their own memory interact. Users describe a prediction request in plain language and receive a prediction report.

How it helps ATF

Its focus on prediction by simulation is far from our products. The path from uploaded material and a plain-language question to a written report could be a loose reference for LabChin's flow from research question to final report.

License

AGPL-3.0 Network copyleft. Offering a modified version as a service also requires releasing the source. Review before any product use.

More in this category

• HKUDS/CLI-Anything
  CLI-Anything builds command line interfaces that let AI agents operate existing software. CLI-Hub is a registry for browsing, installing and managing community-built CLIs, and the project demos show agents producing CAD builds, 3D scenes, diagrams and subtitles.
• alibaba/page-agent
  A JavaScript library that adds a GUI agent inside a web page so users can control the interface with natural language. It works on the DOM as text without screenshots, and offers an optional Chrome extension and MCP server.
• TauricResearch/TradingAgents
  TradingAgents is a multi-agent LLM framework for financial trading. Agents in roles such as research manager, trader and portfolio manager use macro data, sentiment and price data to reach trading decisions.
• NousResearch/hermes-agent
  Hermes Agent is a self-improving AI agent from Nous Research. It creates skills from experience and improves them in use, keeps agent-curated memory, searches past sessions, and can be reached from Telegram, Discord, Slack or a terminal.
• langchain-ai/deepagents
  An open source agent harness on LangGraph that works with any tool-calling model. It includes sub-agents with isolated context, a pluggable filesystem, context summarization, persistent memory, skills, MCP tools and human approval of tool calls.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.