1
session-indexer
给Claude Code会话装个语义搜索引擎，历史记录随手可查
Semantic search over your own Claude Code session history Discussion | Link
2
Show HN: I built a Claude Code plugin to query 10.6M earnings-call embeddings
用Claude Code插件秒搜1060万条财报电话会议记录，精准引用原文，投资研究神器。
Hi HN, I've been using LLMs for one-off market questions against a database of earnings transcripts since ~2025. In tech years that's a long time so a…
3
Show HN: VS Code Extension – Semantic Code Search (Semble)
语义搜索代码，VS Code 智能定位，告别关键词瞎猜。
Article URL: https://github.com/SeanPedersen/vscode-semble Comments URL: https://news.ycombinator.com/item?id=49204742 Points: 1 # Comments: 0
4
AI Tool Discovery at Scale: All You Need is DNS
借鉴DNS分布式架构，实现百万级AI工具的高效语义发现，突破传统集中式管理的O(N)瓶颈，为自主智能体时代铺路。
arXiv:2607.18242v1 Announce Type: new Abstract: The coming era of autonomous AI agents demands a discovery mechanism capable of navigating millions of…
5
Fidx – local semantic search in one SQLite file, no LLM at query
用SQLite实现本地语义搜索，查询时无需大模型，轻量高效的开源方案。
Article URL: https://github.com/williamliu-ai/fidx Comments URL: https://news.ycombinator.com/item?id=48791740 Points: 1 # Comments: 0
6
Photocore – Local AI – Find and organize your photos
本地AI照片管理工具，支持语义搜索与RAW格式，免费索引200张，隐私安全。
Article URL: https://photocore.pro/en Comments URL: https://news.ycombinator.com/item?id=48766432 Points: 1 # Comments: 0
7
AI Agents Don't Need More Memory. They Need Governed Recall.
这篇文章颠覆了AI代理记忆的主流认知，指出关键不在于容量，而在于权限和语义检索的受控召回。
Most AI Agent Memory discussions start from the same assumption: If the agent forgets, give it more memory. More chat history. More retrieved document…
8
How to Build a High-Performance RAG Pipeline with Ollama, Python and TypeScript
手把手教你用Ollama+Python+TypeScript搭建高性能本地RAG管道，无需云端API。
The TL;DR If you need to spin up a local, privacy-first AI agent that can query your own internal documents without sending data to third-party APIs, …
9
Show HN: Omni – Local-first multimodal file search on macOS
macOS本地优先的多模态文件搜索，支持中英日等多语言语义匹配，无需关键词，扫描页面也能搜。
Finally made something I've always wanted, using the model we built. • SOTA omni embedding model, fully local, indexes text, PDF, image, audio, and vi…
10
Show HN: Zatron – Encrypted semantic search, 98% quality, 8x faster than FHE
加密语义搜索新突破，质量高达98%，速度比全同态加密快8倍，完全开源。
Article URL: https://github.com/zahraarmantech/ZATRON Comments URL: https://news.ycombinator.com/item?id=48356184 Points: 1 # Comments: 0
11
Experimenting with graph-based semantic memory for AI agents
开源AI代理图语义记忆项目，整合SQLite、llama.cpp、BGE-M3等，30秒可安装体验。
Article URL: https://github.com/AEndrix03/Graft Comments URL: https://news.ycombinator.com/item?id=48216282 Points: 4 # Comments: 0
12
Ask HN: Is there a good code intelligence MCP server yet?
Hacker News 热帖：社区正在寻找成熟的代码智能 MCP 服务器，讨论当前碎片化现状与候选方案。
I'm looking for a good code intelligence MCP server (semantic search, symbol lookup, call graphs, etc.) to pair with an AI coding agent. The idea is t…
13
Introducing text and code embeddings
OpenAI 推出文本与代码嵌入新端点，轻松实现语义搜索、聚类等高级 NLP 任务。
We are introducing embeddings, a new endpoint in the OpenAI API that makes it easy to perform natural language and code tasks like semantic search, cl…
14
XSearch: Explainable Code Search via Concept-to-Code Alignment
XSearch通过概念到代码对齐实现可解释代码搜索，新方法提升语义检索的可解释性与泛化能力
arXiv:2605.16046v1 Announce Type: cross Abstract: Semantic code search has been widely adopted in both academia and industry. These approaches embed n…