开发即插即用的个人人工智能记忆，可跨人工智能代理工作
2 分•作者: heysrb•5 天前
我一直在做一个名为 Make0 AI 的项目，我希望为 Codex 和 Claude Code 提供通用的上下文。问题很简单——在使用 Claude 时，在用完每日/每周限制后，我不得不在 Codex 中从头开始。当然，我可以提示 Claude 总结一个我可以交给 Codex 的交接内容，但这效率低下。
所以我想到了使用简单的指令列表，比如一个共享的 md 文件，为它们在本地创建一个通用上下文。但问题是文件不断增长，到某个点通用上下文超过了 20k tokens，只是不必要地增加了 token 预算。
然后我实现了基于 RAG 的检索方法来处理列表，只加载提示所需的内容，然后，经过几次迭代，它就演变成了一个图谱记忆——Brain。
所以这个产品 Make0 AI 让你能够创建 Brain，你可以通过 MCP 将它们连接到任何 AI 代理，然后它们会立即了解你的喜好、厌恶、偏好等。AI 代理可以读取、写入这个记忆。
这可以作为你的长期记忆，而 AI 代理则成为 token 提供者和任务执行者。你可以从一个地方完全控制你的数据/记忆。把它想象成一个你可以插入任何代理的“USB 闪存驱动器大脑”。
我知道我可能不是第一个实现这个的人，但我试图让用户体验简单，并且完全不以开发者为中心。你可以直接将你的记忆/数据拖放到 Brain 中，甚至可以玩转一个可视化的 Brain。
还有一件事，我对记忆进行了基准测试。LoCoMo 在标准模式（现已推出）下整体得分 83.3%，单跳得分 92.5%，在另一种配置（实验性最大模式）下，整体得分 92%，单跳得分 94.4%。可在基准测试页面查看。
目前我将其设置为仅限邀请。如果你想尝试，请告诉我！
查看原文
So I've been working on a project (Make0 AI) for a long time where I wanted to give common context to both Codex and Claude Code. The problem is simple - while working on Claude and after exhausting the daily/weekly limits I've start again from scratch in Codex. Of course I can prompt Claude to summarise a handoff that I can give to Codex but that is inefficient.<p>So I thought of a creating a common context for both of them locally using a simple list of instructions like a shared md file. But the problem was the file kept on growing and after some point the common context went beyond 20k tokens and was just inflating the token budget unnecessarily.<p>Then I implemented a RAG based retrieval approach on the list to only load what is required for that prompt and voila, after a few more iterations it resulted into a graph memory - Brain.<p>So this product Make0 AI gives you the ability to create Brains that you can connect to any Ai agent via MCP and then they immediately know your likes, dislikes, preferences etc. AI agents can read, write to this memory.<p>This can be your long term memory and the agents just become the token providers and task executors. You have full control over your data/memories from a single place. Think of this as a "USB thumb drive brain" that you plug to any agent.<p>I know I may not be the first one to implement this but I tried to make the UX simple and is not at all developer focused. You can just drag and drop your memories/data to the brain and even play around with a visual brain.<p>One more thing, i've done benchmarks on the memory. LoCoMo scores 83.3% overall, with Single hop 92.5% in standard mode (available now) and in another configuration (experimental max mode) it scores 92% overall and 94.4% in single hop. Available in the benchmark page.<p>I'm currently keeping this invite only. Do let me know if you folks wanna try it!