DeepSeek Harness更新，支持插件式架构，实现代理自我进化的新版本，值得一试。
DeepSeek Harness采用“一切皆插件”架构，支持模型、工具、存储、代理循环、调度和UI的替换或重新组合。MemSearch提供记忆和学习信号，DeepSeek Harness提供可组合的运行时环境。MemSearch和DeepSeek Harness结合，实现代理自我进化的新版本。
𝗪𝗲 𝗯𝗿𝗼𝘂𝗴𝗵𝘁 𝗠𝗲𝗺𝗦𝗲𝗮𝗿𝗰𝗵 𝘁𝗼 𝗗𝗲𝗲𝗽𝗦𝗲𝗲𝗸 𝗛𝗮𝗿𝗻𝗲𝘀𝘀, 𝗴𝗶𝘃𝗶𝗻𝗴 𝗶𝘁 ...
𝗪𝗲 𝗯𝗿𝗼𝘂𝗴𝗵𝘁 𝗠𝗲𝗺𝗦𝗲𝗮𝗿𝗰𝗵 𝘁𝗼 𝗗𝗲𝗲𝗽𝗦𝗲𝗲𝗸 𝗛𝗮𝗿𝗻𝗲𝘀𝘀, 𝗴𝗶𝘃𝗶𝗻𝗴 𝗶𝘁 𝗽𝗲𝗿𝘀𝗶𝘀𝘁𝗲𝗻𝘁 𝗺𝗲𝗺𝗼𝗿𝘆 𝗮𝗻𝗱 𝗮 𝗽𝗮𝘁𝗵 𝘁𝗼 𝘁𝘂𝗿𝗻 𝗿𝗲𝗽𝗲𝗮𝘁𝗲𝗱 𝗲𝘅𝗽𝗲𝗿𝗶𝗲𝗻𝗰𝗲 𝗶𝗻𝘁𝗼 𝗿𝗲𝘂𝘀𝗮𝗯𝗹𝗲 𝗦𝗸𝗶𝗹𝗹𝘀. DeepSeek Harness is getting attention for its “everything is a plugin” architecture. Models, tools, storage, the agent loop, scheduling, and even the UI can be replaced or recomposed. But that raises a harder question: If an agent can change almost any part of itself, how does it know what to improve? It needs evidence from past work. 𝗧𝗵𝗮𝘁 𝗶𝘀 𝘄𝗵𝗮𝘁 𝗠𝗲𝗺𝗦𝗲𝗮𝗿𝗰𝗵 𝗯𝗿𝗶𝗻𝗴𝘀 𝘁𝗼 𝗗𝗲𝗲𝗽𝗦𝗲𝗲𝗸 𝗛𝗮𝗿𝗻𝗲𝘀𝘀. 𝗠𝗲𝗺𝗦𝗲𝗮𝗿𝗰𝗵 𝗽𝗿𝗲𝘀𝗲𝗿𝘃𝗲𝘀 𝘁𝗵𝗿𝗲𝗲 𝗸𝗶𝗻𝗱𝘀 𝗼𝗳 𝗺𝗲𝗺𝗼𝗿𝘆: • What happened across previous sessions. • What remains true about the project and the user. • Which workflows repeat often enough to become reusable Skills. DSH turns that third layer into an actionable experience. Its Memory Dock surfaces Skill candidates, shows where they came from, and lets users review them before installation. The loop is simple: Experience → memory → repeated pattern → Skill candidate → human review → new capability MemSearch provides the memory and learning signal. DeepSeek Harness provides the composable runtime github.com/zilliztech/mem… omes action. Nothin github.com/deepseek-ai/de… ca #DeepSeek m #AIAgents o #AgentMemory uman decides. That is the version of agent self-evolution we find credible. MemSearch: https://t.co/OoqhEFvI4I DeepSeek Harness: https://t.co/vQual8kFFD #DeepSeek #AIAgents #AgentMemory 💬 0 🔄 1 ❤️ 0 👀 65 ⚡