关键词 "thinking partner" 的搜索结果, 共 19 条, 只显示前 480 条
An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
A powerful server providing advanced thinking tools via the Model Context Protocol (MCP) to enhance the reasoning, planning, and iterative refinement capabilities of AI agents like Cline.
Fully AI generated Flutter app in Claude Desktop with 3.7 Sonnet by MCP servers desktop-commander and sequential-thinking
An MCP server that enables dynamic, reflective problem-solving by structuring thought processes and automatically logging each session to Recall.
A TypeScript Model Context Protocol (MCP) server to allow LLMs to programmatically construct mind maps to explore an idea space, with enforced "metacognitive" self-reflection
A unified MCP server for structured thinking tools including template thinking, and verification thinking
An MCP server providing intelligent transcript processing capabilities, featuring natural formatting, contextual repair, and smart summarization powered by Deep Thinking LLMs.
MCP server for retrieval augmented thinking and problem solving
🧠 MCP server implementing RAT (Retrieval Augmented Thinking) - combines DeepSeek's reasoning with GPT-4/Claude/Mistral responses, maintaining conversation context between interactions.
Enhanced MCP memory system with dynamic compression, context management and thinking process integration. Based on the original MCP memory server.
MCP server for applying a Claude Shannon-inspired problem-solving pattern
A Model Context Protocol (MCP) server that empowers LLMs to use some of Open Srategy Partners' core writing and product marketing techniques.
🧠 An adaptation of the MCP Sequential Thinking Server to guide tool usage. This server provides recommendations for which MCP tools would be most effective at each stage.
专长:罕见病药物再利用。Healx 利用人工智能识别可用于治疗罕见病的现有药物。其平台将生物医学数据与机器学习相结合,以加速治疗方案的开发。其显著成就包括推进脆性 X 综合征和其他罕见疾病的治疗。Healx 以患者为中心的理念以及与患者权益组织的合作使其在罕见病领域脱颖而出。 Healx是一家专注于罕见疾病的AI临床阶段生物技术公司,该公司宣布已在C轮融资中筹集了4700万美元。C轮融资由硅谷的
QwenLong-L1-32B 是阿里巴巴集团 Qwen-Doc 团队推出的,基于强化学习训练的首个长文本推理大模型。模型基于渐进式上下文扩展、课程引导的强化学习和难度感知的回顾性采样策略,显著提升在长文本场景下的推理能力。模型在多个长文本文档问答(DocQA)基准测试中表现优异,平均准确率达到了70.7%,超越OpenAI-o3-mini和Qwen3-235B-A22B等现有旗舰模型,且与Cla
MiniMax-M1是MiniMax团队最新推出的开源推理模型,基于混合专家架构(MoE)与闪电注意力机制(lightning attention)相结合,总参数量达 4560 亿,每个token激活 459 亿参数。模型超过国内的闭源模型,接近海外的最领先模型,具有业内最高的性价比。MiniMax-M1原生支持 100 万token的上下文长度,提供40 和80K两种推理预算版本,适合处理长输入
业界首个开源高完成度轻量化通用多智能体产品(JoyAgent-JDGenie) 解决快速构建多智能体产品的最后一公里问题 简介 当前相关开源agent主要是SDK或者框架,用户还需基于此做进一步的开发,无法直接做到开箱即用。我们开源的JoyAgent-JDGenie是端到端的多Agent产品,对于输入的query或者任务,可以直接回答或者解决。例如用户query"给我做一个最
只显示前20页数据,更多请搜索
Showing 145 to 163 of 163 results