1
Show HN: Self hosting a modern LLM stack
一键自托管LLM栈，整合模型、向量数据库、缓存和可观测性工具
Article URL: https://github.com/raiyanyahya/llmaker Comments URL: https://news.ycombinator.com/item?id=48714397 Points: 5 # Comments: 1
2
I removed the vector database from my AI agent stack
作者用实际项目展示移除向量数据库后AI agent架构更轻量高效，值得关注。
Article URL: https://github.com/usemoss/moss Comments URL: https://news.ycombinator.com/item?id=48693631 Points: 2 # Comments: 0
3
Show HN: LLM Memory Solved?
neuron-db为LLM打造持久化记忆，突破上下文窗口限制，让模型用3D可视化召回事实，开源方案或成记忆难题解法。
Article URL: https://github.com/gary23w/neuron-db Comments URL: https://news.ycombinator.com/item?id=48527346 Points: 1 # Comments: 0
4
Show HN: RAG built for Frappe using TurboVec
专为Frappe框架打造的RAG系统，基于TurboVec向量引擎，为ERP系统注入智能检索与生成能力。
Article URL: https://github.com/ssenthilnathan3/turbo_rag Comments URL: https://news.ycombinator.com/item?id=48472271 Points: 1 # Comments: 0
5
The AI Curse (Vis the Lisp Curse)
AI生态正在重蹈Lisp诅咒：看似简单的概念，却无统一高星实现，碎片化已现。
Article URL: https://blog.djhaskin.com/blog/the-ai-curse/ Comments URL: https://news.ycombinator.com/item?id=48469536 Points: 2 # Comments: 0
6
I'm building CortexDB — an agent-native context database for AI agents
专为AI代理打造的上下文数据库，区别于传统向量数据库与键值存储，解决代理上下文管理难题。
I'm building CortexDB — an agent-native context database for AI agents Most modern RAG systems follow the same pattern: Split documents into chunks Co…
7
Show HN: SynapCores – AI-native database (vector, graph, SQL, AutoML, LLM)
SynapCores将向量、图、SQL与AutoML融合成一个引擎，5个现场演示+161个即用配方让AI增强查询30秒上手。
Article URL: https://synapcores.com Comments URL: https://news.ycombinator.com/item?id=48268700 Points: 2 # Comments: 0
8
Show HN: Rust Database from Scratch
用Rust从零构建的PostgreSQL兼容数据库，支持图与向量查询，开源可学习。
Article URL: https://github.com/ayoubnabil/aiondb Comments URL: https://news.ycombinator.com/item?id=48206073 Points: 4 # Comments: 2
9
Human-Like Document AI
像人类一样理解复杂文档，无需向量数据库，精准答案可溯源验证
Article URL: https://pageindex.ai/ Comments URL: https://news.ycombinator.com/item?id=48170832 Points: 2 # Comments: 1