GitHub Trending 日报

📅 日期：2026/03/17

🎯 系列说明：每日精选GitHub热门开源项目，带你发现最新技术趋势和优质项目。每日推送，持续更新中…

📊 今日热门项目速览

1. MiroFish

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

🐍 Python | ⭐ +3260 今日 | 🏆 29,996 总计

仓库地址：666ghj/MiroFish

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude’s agent-sdk), and injects relevant context back into future sessions.

🔷 TypeScript | ⭐ +1045 今日 | 🏆 36,811 总计

仓库地址：thedotmack/claude-mem

3. project-nomad

Project N.O.M.A.D, is a self-contained, offline survival computer packed with critical tools, knowledge, and AI to keep you informed and empowered—anytime, anywhere.

🔷 TypeScript | ⭐ +775 今日 | 🏆 1,831 总计

仓库地址：Crosstalk-Solutions/project-nomad

4. superpowers

An agentic skills framework & software development methodology that works.

🐚 Shell | ⭐ +3152 今日 | 🏆 88,626 总计

仓库地址：obra/superpowers

5. GitNexus

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive knowledge graph wit a built in Graph RAG Agent. Perfect for code exploration

🔷 TypeScript | ⭐ +1860 今日 | 🏆 15,603 总计

仓库地址：abhigyanpatwari/GitNexus

6. browser

Lightpanda: the headless browser designed for AI and automation

📦 Zig | ⭐ +2086 今日 | 🏆 20,224 总计

仓库地址：lightpanda-io/browser

7. OpenViking

OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.

🐍 Python | ⭐ +2012 今日 | 🏆 14,161 总计

仓库地址：volcengine/OpenViking

8. learn-claude-code

Bash is all you need - A nano Claude Code–like agent, built from 0 to 1

🔷 TypeScript | ⭐ +1535 今日 | 🏆 29,299 总计

仓库地址：shareAI-lab/learn-claude-code

9. heretic

Fully automatic censorship removal for language models

🐍 Python | ⭐ +788 今日 | 🏆 15,291 总计

仓库地址：p-e-w/heretic

10. deepagents

Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.

🐍 Python | ⭐ +1026 今日 | 🏆 12,918 总计

仓库地址：langchain-ai/deepagents

11. claudian

An Obsidian plugin that embeds Claude Code as an AI collaborator in your vault

🔷 TypeScript | ⭐ +111 今日 | 🏆 4,160 总计

仓库地址：YishenTu/claudian

12. vite-plus

Vite+ is the unified toolchain and entry point for web development. It manages your runtime, package manager, and frontend toolchain in one place.

🦀 Rust | ⭐ +621 今日 | 🏆 2,242 总计

仓库地址：voidzero-dev/vite-plus

🔍 今日精选项目详解

MiroFish

项目地址：https://github.com/666ghj/MiroFish

作者：666ghj

📖 项目简介

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

📊 项目数据

指标	数值
⭐ Stars	29,996
🍴 Forks	3,667
👀 Watchers	29,996
📝 Language	Python
📅 Created	2025-11-26
🔄 Updated	2026-03-17
📜 License	AGPL-3.0

💡 核心特点

标签：agent-memory, financial-forecasting, future-prediction, knowledge-graph, llms, multi-agent-simulation, public-opinion-analysis, python3, social-prediction, swarm-intelligence

📄 项目概览

简洁通用的群体智能引擎，预测万物
A Simple and Universal Swarm Intelligence Engine, Predicting Anything
English | 中文文档

⚡ 项目概述

MiroFish 是一款基于多智能体技术的新一代 AI 预测引擎。通过提取现实世界的种子信息（如突发新闻、政策草案、金融信号），自动构建出高保真的平行数字世界。在此空间内，成千上万个具备独立人格、长期记忆与行为逻辑的智能体进行自由交互与社会演化。你可透过「上帝视角」动态注入变量，精准推演未来走向——让未来在数字沙盘中预演，助决策在百战模拟后胜出。

你只需：上传种子材料（数据分析报告或者有趣的小说故事），并用自然语言描述预测需求
MiroFish 将返回：一份详尽的预测报告，以及一个可深度交互的高保真数字世界

🚀 快速开始

# 克隆项目
git clone https://github.com/666ghj/MiroFish.git

# 进入目录
cd MiroFish

# 查看文档
cat README.md

💭 推荐理由

这个项目在今日GitHub Trending榜单中排名第一，值得关注的原因：

🤖 AI/ML领域：紧跟当前AI技术浪潮，具有前瞻性
🔥 快速增长：累计29,996 Stars，社区认可度高
🚀 持续迭代：近一周内有更新，项目活跃度高
🎯 易于上手：提供示例代码，快速入门

📝 系列说明

GitHub Trending 日报是一个持续更新的系列，每日为你带来：

🔥 热门项目速览：快速了解当日最火的开源项目
🔍 精选项目详解：深入分析排名第一的项目
💡 技术趋势洞察：把握开源社区最新动态

往期日报

订阅方式

📧 RSS订阅：/atom.xml
💬 微信公众号：DeepThinking深思
📺 B站：@八里桥好

🤝 参与贡献

如果你发现有趣的开源项目，欢迎推荐！

💬 评论留言推荐
📧 邮件：leiqi@fudan.edu.cn
🔗 GitHub：@leiqichn

📡 数据更新：2026-03-17 09:05:51
🔗 数据来源：GitHub Trending