1
Jackrong LLM Fine-Tuning Guide
LLM微调实战指南，从入门到进阶的完整开源教程，适合AI开发者快速上手
Article URL: https://github.com/R6410418/Jackrong-llm-finetuning-guide Comments URL: https://news.ycombinator.com/item?id=48812171 Points: 2 # Comment…
2
Signal: A draft UX framework for LLM-based systems
专为LLM系统设计的UX框架草案，从交互体验角度优化AI应用设计
Article URL: https://github.com/hi-mundo/SIGNAL Comments URL: https://news.ycombinator.com/item?id=48746626 Points: 1 # Comments: 0
3
Code slicing: What lies inside OrcaSlicer
揭秘OrcaSlicer内部代码切片，分析最有趣的编译器警告
How can you avoid overlooking dangerous code parts during reviews? You can use static analysis tools. Let's take as an example OrcaSlicer, a popular s…
4
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
5
I made a Claude Code skill to check if AI crawlers can read your site
一个Claude Code技能帮你快速检测网站是否被AI爬虫抓取，保护内容不被滥用。
Article URL: https://github.com/MerqryLabs/ai-crawler-visibility Comments URL: https://news.ycombinator.com/item?id=48683149 Points: 2 # Comments: 0
6
Show HN: Open-source Notion-style personal site / blog
一键搭建Notion风格的极简个人主页/博客，完全开源可自部署
Article URL: https://github.com/terryds/notion-style-personal-site Comments URL: https://news.ycombinator.com/item?id=48625158 Points: 1 # Comments: 1
7
Show HN: Behavioral gauge for Claude Code sessions
为Claude Code会话打造的行为监控利器，开源免费，轻松追踪AI编程助手的行为指标。
Article URL: https://github.com/softcane/ccverdict Comments URL: https://news.ycombinator.com/item?id=48545671 Points: 2 # Comments: 0
8
Show HN: World Cup TUI with Live Updates
终端看世界杯直播，轻量级TUI工具实时更新赛况，命令行球迷必备。
Article URL: https://github.com/perryraskin/world-cup-tui Comments URL: https://news.ycombinator.com/item?id=48544847 Points: 2 # Comments: 2
9
Relent less AI self-evolution
AI自我进化新突破：将搜索代码从1260行压减至75行，准确率提升7.7%，token消耗减少4倍。
Article URL: https://github.com/001TMF/harness-forge Comments URL: https://news.ycombinator.com/item?id=48526233 Points: 1 # Comments: 0
10
SafeAgentDB – Isolated databases for every AI agent branch
为AI agent的每个分支提供独立隔离数据库，解决多分支数据冲突与污染问题。
Article URL: https://github.com/Aidan945/SafeAgentDB Comments URL: https://news.ycombinator.com/item?id=48470846 Points: 2 # Comments: 0
11
Show HN: CodexL – All-in-one launcher for Codex
开源一键启动器，告别Codex繁琐配置，轻松切换模型供应商
Article URL: https://github.com/musistudio/CodexL Comments URL: https://news.ycombinator.com/item?id=48455931 Points: 2 # Comments: 0
12
Show HN: Switch skills between agents, locally manage multiple configs
一键切换代理技能，本地管理多配置的开源CLI工具，让AI代理配置更灵活高效。
Hey HN, One issue that a lot of teams run into is that they want to switch their configs between different agents e.g. Claude Code --> Codex or they w…
13
AiLang: An AI-First Language Focused on Deterministic Execution
全新AI优先语言AiLang，专注确定性执行，GitHub挑战赛提交项目
AiLang — GitHub Finish-Up-A-Thon Challenge Submission This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built AiLang — A Determini…
14
LLM: Documentation driven exploration for big codebase
用LLM辅助，以文档为线索高效探索大型代码库的开源工具
Article URL: https://github.com/Anhydrite/doc-torn Comments URL: https://news.ycombinator.com/item?id=48219106 Points: 2 # Comments: 1
15
Aperion Shield: local guardrail that blocks destructive AI coding agent ops
开源本地安全护栏，阻挡AI编码代理的破坏性操作，v0.7新增45+自适应规则与更多测试用例。
Article URL: https://github.com/AperionAI/shield Comments URL: https://news.ycombinator.com/item?id=48207471 Points: 2 # Comments: 0