HackerNews中文版

我正在开发一个专门为自主AI代理设计的内存平台。目前，代理内存面临两个乏味的选择：RAG（关系拓扑丢失）和图数据库（需要大量指针追踪，并在重度递归推理时性能下降）。我正在使用向量符号架构（超维计算）构建一种替代方案。通过将事实、序列和树以数学方式绑定成固定大小的高维向量（D=16,384），我们可以将复杂的图遍历压缩为O(1)常数时间的SIMD操作……并且以低成本实现一些类脑的功能，也就是说，不依赖于GPU和大型语言模型（LLM）。设计正在顺利成熟，并严格分为两个部分，以尊重机械同情： • 数据平面（Zig）：纯粹的裸金属数学。通过io_uring实现2GB内存映射的NVMe块。事实被叠加到严格对齐到64字节缓存行的无锁8位累加器中。查询通过AVX-512 popcount指令执行，以线速计算汉明距离。没有垃圾回收。 • 控制平面（Gleam）：处理并发、路由以及用于外部通信的Linda风格元组空间。它管理代理的“清理”循环和自动分块，而不会阻塞数据平面。 • 桥接：一个严格的C-ABI/NIF边界，将指针从BEAM调度器直接传递到Zig的核心部分。这里没有风险投资的浮夸言辞，我也没有对AGI做出夸大的声明。我已经完成了大部分规格、内存布局不变性和架构设计。现在开始编码，并取得了良好的进展。我在寻找热爱低级系统（Zig/Rust/C）或高度并发运行时（Erlang）的人来帮助我构建这个平台。这是我第二个AI平台，第一个平台运转良好并在不断增长。如果你对裸金属系统工程感兴趣，想解决LLM上下文瓶颈，我很乐意交流：请发邮件至acowed@pm.me。祝好， Kendall

查看原文

I’m working on a purpose-built memory platform for autonomous AI agents.Right now, agent memory is stuck between two hohum options: RAG (which loses relational topology) and Graph Databases (which require massive pointer chasing and degrade under heavy recursive reasoning).I'm building an alternative using Vector Symbolic Architecture (Hyperdimensional Computing). By mathematically binding facts, sequences, and trees into fixed-size high-dimensional vectors (D=16,384), we can compress complex graph traversals into O(1) constant-time SIMD operations…and do some quasi brain-like stuff cheaply, that is, without GPUs and LLMs.The design is maturing nicely and strictly bifurcated to respect mechanical sympathy:• The Data Plane (Zig): Pure bare-metal math. 2GB memory-mapped NVMe tiles via io_uring. Facts are superposed into lock-free 8-bit accumulators strictly aligned to 64-byte cache lines. Queries are executed via AVX-512 popcount instructions to calculate Hamming distances at line-rate. Zero garbage collection.• The Control Plane (Gleam): Handles concurrency, routing, and a Linda-style Tuplespace for external comms. It manages the agent "clean-up" loops and auto-chunking without ever blocking the data plane.• The Bridge: A strict C-ABI / NIF boundary passing pointers from the BEAM schedulers directly into the Zig muscle.There is no VC fluff here, and I'm not making wild claims about AGI. I have most of spec, memory layout invariants, and the architecture designed. Starting to code and making good progress.I’m looking for someone who loves low-level systems (Zig/Rust/C) or highly concurrent runtimes (Erlang) to help me build the platform. This is my second AI platform; the first one is healthy and growing.If you are interested in bare-metal systems engineering to fix the LLM context bottleneck, I'd love to talk: email me at acowed@pm.me.Cheers, Kendall

寻找合作伙伴构建代理记忆（Zig/Erlang）