Open Code Review is an open-source, AI-powered CLI tool by Alibaba that combines deterministic engineering with dynamic Agent decision-making. It reads Git diffs, smartly bundles relevant files, and applies fine-grained rules before querying the LLM. It generates structured, line-level reviews and resolves common issues in generic agents such as incomplete coverage, position drift, and unstable feedback quality.
A layered memory system for AI Agents that combines symbolic short-term memory with hierarchical long-term storage. It optimizes performance by offloading verbose tool logs into compact Mermaid symbols, reducing token usage by up to 61% while improving accuracy. The system organizes experiences into a semantic pyramid (L0-L3), enabling structured persona management instead of flat vector retrieval. Integrated with OpenClaw and Hermes, it provides a traceable and lossless memory architecture.
DeerFlow (Deep Exploration and Efficient Research Flow) is an open-source super agent harness developed by ByteDance, designed to orchestrate sub-agents, memory, and sandboxes to perform a wide range of complex tasks. It is powered by an extensible skills system, allowing for custom functionality integration. DeerFlow 2.0 is a ground-up rewrite, offering enhanced agent capabilities and flexible deployment, recommended for use with large language models such as Doubao-Seed-2.0-Code, DeepSeek v3.2, and Kimi 2.5. It also integrates BytePlus's InfoQuest intelligent search and crawling toolset.
Claude Context is an MCP (Model Context Protocol) plugin developed by Zilliztech, designed to provide deep code context to Claude Code and other AI coding assistants. It leverages semantic search to efficiently retrieve relevant code snippets from entire codebases, injecting them directly into the AI's context. This approach addresses the limitations of context windows and high costs associated with large codebases by storing the codebase in a vector database for efficient management and cost-effectiveness.
TuriX-CUA by TurixAI is an AI-driven desktop automation agent that enables powerful AI models to perform real, hands-on actions directly on your desktop. It features a state-of-the-art computer-use agent (CUA), achieving an 80% success rate on OSWorld-style Mac benchmarks. TuriX is 100% open-source and free for personal and research use, allowing users to swap in their own models. The latest TuriX SuperPower combines CUA and CLI workflows for everyday office and coding automation, facilitating a continuous flow between GUI actions and CLI precision.
LangGraph, from LangChain, Inc., is a powerful low-level orchestration framework engineered for building, managing, and deploying sophisticated, long-running, and stateful multi-agent applications. It represents application logic as cyclic Directed Acyclic Graphs (DAGs), giving developers precise control over LLM execution, including when to pause, loop, or transfer control. LangGraph ensures durable execution, seamless human-in-the-loop capabilities, and comprehensive short-term and long-term memory management. Deep integration with LangSmith provides robust debugging and production-ready deployment, making it the ideal choice for developing complex and reliable AI agents.
LobeHub is a collaborative workspace designed for the co-evolution of humans and AI agents. It treats agents as the fundamental unit of work, allowing users to find, build, and coordinate agent teammates. Key highlights include the integration of the Model Context Protocol (MCP) for seamless tool connectivity, a library of over 10,000 skills, and structured, editable 'white-box' memory. LobeHub supports multi-model services, visual recognition, and complex workflows like projects and workspaces, providing a highly customizable and open-source environment for AI productivity.
daily_stock_analysis, developed by ZhuLinsen, is an intelligent stock analysis system powered by large AI models. It automatically analyzes selected A-share, Hong Kong, and US stocks daily, generating a 'Decision Dashboard' with core conclusions, ratings, buy/sell points, risk alerts, and action checklists. The system supports automated delivery of analysis reports via multiple channels including WeChat Work, Feishu, Telegram, Discord, Slack, and email. It integrates multi-dimensional analysis (technical, real-time quotes, chip distribution, news sentiment), supports global markets, and incorporates various built-in market strategies (e.g., moving averages, 'Chan Lun', Elliott Wave). Users can also utilize a web-based workbench for manual analysis, configuration management, historical report viewing, backtesting, and AI Agent-powered strategy inquiries.
AgentScope is a production-ready multi-agent framework designed to simplify the development of LLM-powered applications. It provides high-level abstractions for agent communication, memory management, and tool usage. Rather than using restrictive prompts, AgentScope leverages the inherent reasoning and tool-use capabilities of LLMs. Key features include Real-time Voice, Human-in-the-loop steering, Agentic RL for model tuning, and support for MCP and A2A protocols. It is engineered for scalability, supporting local, serverless, and K8s deployments with integrated OTel monitoring for enterprise-grade observability.
JeecgBoot is an enterprise-grade AI low-code platform built on SpringBoot 3 and Vue 3. It features a unique 'Low-code + No-code' dual-mode architecture. With its 'AI Skills' natural language programming capability, users can generate full-stack code, BPMN flows, and dashboards via simple prompts. The platform integrates an AI application management system similar to Dify, supporting RAG, knowledge bases, and multi-LLM integration (DeepSeek, ChatGPT, etc.). It provides robust security, multi-tenancy, and high-performance visualization tools.
Desktop Commander MCP is a versatile Model Context Protocol (MCP) server that integrates professional development tools into AI interfaces. It empowers AI to manage files, execute long-running terminal commands, and handle background processes. Key features include deep support for Excel/PDF/DOCX, in-memory code execution (Python, Node.js, R), and visual file previews. Built with security in mind, it offers Docker isolation and remote control capabilities, transforming standard AI interactions into a comprehensive, automated local development environment.
UI-TARS-desktop is an open-source native desktop application developed by Bytedance, providing a powerful GUI Agent based on the UI-TARS multimodal model. It enables AI to perceive and interact with graphical user interfaces just like a human, supporting both local and remote computer/browser operations. Built on the Model Context Protocol (MCP), it integrates seamlessly with real-world tools. The app features a redesigned UI and leverages the UI-TARS-1.5 model for high-precision vision-based control and task automation.
Dify is an open-source, production-ready LLM application development platform engineered to significantly accelerate the entire development cycle from prototype to production. It offers an intuitive visual workflow canvas, integrating a powerful Retrieval Augmented Generation (RAG) pipeline for efficient document ingestion and retrieval. Dify also features advanced agent capabilities based on LLM Function Calling or ReAct, configurable with pre-built or custom tools. It provides comprehensive support for hundreds of mainstream proprietary and open-source LLMs, a robust Prompt IDE for prompt engineering and model performance comparison, and built-in observability features (e.g., Opik, Langfuse, Arize Phoenix). This empowers developers to rapidly build, deploy, and monitor complex AI applications and agents.
An educational project by shareAI-lab focused on 'Harness Engineering' for AI agents. It provides a masterclass by reverse-engineering the architecture of Anthropic's Claude Code. The repo teaches how to build the 'vehicle' (harness) for the 'driver' (model), covering essential mechanisms like tool implementation, context compression, subagent spawning, and task dependency graphs. It shifts the development focus from prompt plumbing to building robust environments for autonomous models.
DeepSeek-Reasonix by esengine is an open-source, DeepSeek-native AI coding agent built for the terminal and desktop. Its core innovation is a cache-first architecture engineered around prefix-cache stability. By maintaining an append-only loop, it achieves near 99.8% cache hit rates during extensive coding sessions, slashing API token costs by up to 5x. Alongside its robust CLI, Reasonix features a native Tauri desktop GUI and remote QQ channel integration. It fully supports the Model Context Protocol (MCP) for tool expansion, local semantic indexing, web search, and custom Markdown-based skills, making it a highly optimized companion for developers.
A platform providing a specification and showcase for AI agent skills, helping developers integrate and discover new capabilities for AI agents.
A collection of agent skills for Google products and technologies, including Google Cloud, enabling AI agent developers to easily integrate and build intelligent applications.