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.
Open CoDesign is an open-source, local-first desktop application that serves as an alternative to Claude Design and v0. Built with Electron, it enables users to transform prompts into polished prototypes, slide decks, and web artifacts using their own AI models (Claude, GPT, Gemini, Ollama, etc.). It features an agentic workflow that plans, codes, and self-checks designs locally, offering high privacy, multi-model compatibility, and editable exports like HTML and PPTX without platform lock-in.
deepclaude is a backend adapter for the Claude Code CLI that redirects its autonomous agent loop to cost-effective models like DeepSeek V4 Pro. It preserves core features such as file editing, terminal execution, and subagent spawning while reducing costs by 17x through DeepSeek's automatic context caching. The tool supports mid-session backend switching via slash commands, remote control via web browsers, and real-time cost tracking, offering a high-performance yet affordable extension to the autonomous coding ecosystem.
Open Multi-Agent is a lightweight, TypeScript-native multi-agent orchestration framework. By simply providing a goal, its built-in coordinator automatically decomposes the goal into a task DAG, parallelizes independent steps, and synthesizes the final output. With only 3 runtime dependencies, it seamlessly drops into any Node.js backend. Key features include mixing over 12 LLM providers within a single team, a sandboxed filesystem workspace, pluggable shared memory, and native integration with the Model Context Protocol (MCP) for tool extensibility.
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.
New API is a next-generation LLM gateway and AI asset management system developed by QuantumNous. As a feature-rich fork of One API, it aggregates various AI model providers (including OpenAI, Claude, Gemini, etc.) and provides a unified OpenAI-compatible interface. It features intelligent routing with weighted load balancing, automatic failover, and a comprehensive billing system supporting Stripe and EPay. With a modern dashboard and support for advanced features like Reasoning Effort, Realtime API, and OIDC authentication, it serves as a robust infrastructure for enterprise and personal AI resource management.
