All Posts
Filter by keyword, tag, and category.
Datawhale Open-Sources "Building Agents from Scratch": A Systematic Agent Development Tutorial
With the arrival of the "Year of the Agent," the technological focus is shifting from training large models to building agent applications. Datawhale's open-source project, "Building Agents from Scratch," is a systematic, practice-oriented tutorial. It deeply analyzes process-driven and AI-native agent architectures. Having garnered over 48,000 stars on GitHub for its high-quality content, it serves as an essential introductory guide for AI developers.
HKUDS/AI-Trader: A 100% Fully Automated Agent-Native Trading Platform
AI-Trader is a native trading platform designed specifically for AI agents, aiming to provide them with an exclusive trading environment just like humans. It supports rapid integration of mainstream agents like OpenClaw and Claude Code, and enhances production stability by separating the FastAPI Web service from background worker processes. With over 15,000 stars on GitHub, it is a popular open-source practice combining automated trading and large language models.
TradingAgents: Analysis of a Financial Trading Framework Based on Multi-Agent Large Language Models
TradingAgents is an open-source financial trading framework based on multi-agent Large Language Models (LLMs). By introducing structured output agents such as research managers, traders, and portfolio managers, and fully supporting cutting-edge models like GPT-5.4 and Claude 4.6, this project provides quantitative researchers and developers with a comprehensive toolchain for automated trading decision-making and backtesting.
🕵️♂️ Maigret: An Open-Source OSINT Automation Tool for Username-Based Information Gathering
Maigret is a powerful open-source Open-Source Intelligence (OSINT) command-line tool. By simply providing a username, it automates the search and collection of target-related information across over 3,000 websites. It does not rely on any third-party APIs, generating detailed personal profiles by directly parsing web pages. It is an invaluable assistant for security researchers, penetration testers, and automated information gathering enthusiasts.
Microsoft's Open-Source Cutting-Edge Voice AI Framework: An In-Depth Analysis of VibeVoice
Microsoft's open-source VibeVoice is a cutting-edge voice AI framework featuring multilingual Automatic Speech Recognition (ASR) and real-time Text-to-Speech (TTS) models. Natively supporting over 50 languages, it provides fine-tuning code and is compatible with vLLM for inference acceleration. With its long-text, multi-speaker synthesis, and streaming real-time generation capabilities, it has rapidly accumulated over 45,000 stars in the open-source community, becoming a vital tool in the voice domain.
TrendRadar: An Automated Public Opinion Monitoring and Hot Topic Aggregation Tool Based on AI and MCP Architecture
TrendRadar is a Python-based, AI-driven tool for public opinion monitoring and hot topic filtering. It aggregates multi-platform trends and RSS feeds, utilizing large language models for intelligent filtering, translation, and analytical briefing generation. Supporting multi-channel push notifications like WeChat and Feishu, it features rapid Docker deployment and MCP architecture integration. This tool helps users overcome information overload and build customized, automated information processing workflows.
In-Depth Analysis of OpenAI's Official Multi-Agent Framework: openai-agents-python
OpenAI's official lightweight multi-agent workflow framework, openai-agents-python, has recently gained significant traction in the developer community. Offering provider-agnostic API support, it features built-in sandbox agents, tool calling, guardrails, and human-in-the-loop mechanisms. Designed to simplify complex multi-agent collaboration workflows, this framework serves as a crucial infrastructure for building next-generation AI applications.
Onyx: An Open-Source LLM Application Platform Integrating Agentic RAG and Deep Research
Onyx is an open-source AI platform positioned at the application layer for Large Language Models (LLMs), providing a feature-rich interactive interface for various models. Its core features include Agentic RAG, multi-step deep research, and custom agents. With over 50 built-in data connectors and support for the Model Context Protocol (MCP), Onyx empowers enterprises to rapidly build advanced AI assistants equipped with web search and code execution capabilities.