HackerNews中文版

我正在开发一个专为自主 AI 智能体设计的专用内存平台。目前，智能体的内存受困于两个平庸的选择：RAG（丢失关系拓扑结构）和图数据库（需要大量的指针追踪，并在繁重的递归推理下性能下降）。我正在使用向量符号架构（超维计算）构建一个替代方案。通过将事实、序列和树以数学方式绑定到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成 O(1) 常数时间 SIMD 操作……并以低成本完成一些类似大脑的功能，也就是说，无需 GPU 和 LLM。该设计正在稳步成熟，并严格分为两部分以尊重机械亲和性： * **数据平面 (Zig)**：纯粹的裸机数学运算。通过 io\_uring 进行 2GB 内存映射 NVMe 瓦片。事实被叠加到无锁的 8 位累加器中，严格对齐到 64 字节的缓存行。查询通过 AVX-512 popcount 指令执行，以线速计算汉明距离。零垃圾回收。 * **控制平面 (Gleam)**：处理并发、路由和用于外部通信的 Linda 风格的元组空间。它管理智能体的“清理”循环和自动分块，且从不阻塞数据平面。 * **桥接器**：一个严格的 C-ABI / NIF 边界，将指针从 BEAM 调度器直接传递到 Zig 引擎。这里没有花哨的炒作，我也不会对通用人工智能 (AGI) 做出夸张的声明。我拥有大部分规范、内存布局不变性和架构设计。正在开始编码，并取得了良好的进展。我正在寻找一位热爱底层系统（Zig/Rust/C）或高并发运行时（Erlang）的人来帮助我构建这个平台。这是我的第二个 AI 平台；第一个平台运行良好且正在增长。如果您有兴趣通过裸机系统工程来解决 LLM 上下文瓶颈问题，我很乐意与您交流：请通过 acowed@pm.me 给我发邮件。谢谢，肯德尔

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，共建 Agent 记忆库 (Zig/Erlang)