1
EP223: Ollama vs vLLM vs SGLang
对比三大 LLM 推理框架 Ollama、vLLM 与 SGLang，理清性能与适用场景，帮你选对部署方案。
To use open-weight models on your machine, you have three main options: Ollama, vLLM, and SGLang. But each engine handles requests differently.
2
The best free AI models 2026 for an automation-first business
2026年免费AI模型选型指南，五大开源/免费模型组合拳，让自动化业务零成本跑起生产级验证！
The best free AI models 2026 are the ones that give you production-grade quality without a bill at the end of the month. In practice that means using …
3
Show HN: Ollama served my 40k-context model at 4k, silently
别被Ollama悄悄缩短上下文坑了，这个小工具帮你检测真实窗口大小。
Article URL: https://github.com/Bigbonus/ollama-context-window-check Comments URL: https://news.ycombinator.com/item?id=49372235 Points: 1 # Comments:…
4
Show HN: ChatOSS – A Codex alternative for Open Source AI built on Ollama
开源AI编程工作台，本地跑模型，AI代理写代码、管看板，一站式交付
ChatOSS is built on Ollama. If you use Ollama, ChatOSS local works out of the box. ChatOSS is a GUI desktop app that has multiple agentic coding apps …
5
New OllamaMQ v0.3.0
一键管理多引擎模型加载卸载，支持安全令牌，本地AI工作流必备实用工具。
- loading / unloading models - ollama, lm-studio, vllm - optional security tokens and visibility and many more on - https://github.com/Chleba/ollamaMQ…
6
Privibe - LLM Cli Local first+privacy focus+llama.cpp cache branch + Qwen3.x
本地优先的LLM CLI编码代理，支持llama.cpp缓存与Qwen3.x，无API密钥门槛，兼顾隐私与效率。
Article URL: https://github.com/alainnothere/privibe/tree/main Comments URL: https://news.ycombinator.com/item?id=49315777 Points: 2 # Comments: 1
7
Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp
苹果芯片上跑macOS虚拟机，GPU直通让llama.cpp大模型推理性能暴涨11-16倍，实测细节满满。
Article URL: https://github.com/trycua/cua/blob/main/blog/gpu-passthrough-macos-vms.md Comments URL: https://news.ycombinator.com/item?id=49259339 Poi…
8
Show HN: Visual knowledge graphs using Ollama and Embeddings
用Ollama和Embeddings本地构建可视化知识图谱，开源玩法值得一试。
Article URL: https://github.com/punnerud/Local_Knowledge_Graph Comments URL: https://news.ycombinator.com/item?id=49270102 Points: 1 # Comments: 0
9
Show HN: Memcode AI goes open source with Claude Code inspired coding agent
Memcode AI开源发布：受Claude Code启发的编码代理，内置本地LSP、沙箱Shell与视觉输入，能灵活接入Ollama或OpenAI端点，值得一试。
Article URL: https://github.com/memcode-ai/memcode Comments URL: https://news.ycombinator.com/item?id=49239401 Points: 2 # Comments: 0
10
Open-Source AI Platform Orbit
自托管AI平台，Docker一键部署，本地离线运行大模型，兼顾隐私与便捷
Article URL: https://github.com/schmitech/orbit Comments URL: https://news.ycombinator.com/item?id=49134457 Points: 2 # Comments: 0
11
Voice Commander: Control Your Mac with Hey Jarvis
试试用Ollama本地跑Llama 3.2，让Mac听懂“Hey Jarvis”，免费私有还能打造45个工具。
The Problem With Cloud AI Every token costs money. Every API call adds up. And your data goes to their servers. The Local Alternative brew install oll…
12
Show HN: Hermes Notes PKB
自托管块级知识库，融合Obsidian与Capacities精髓，还支持接入本地AI，开源党狂喜。
20+ years of PKMS obsession plus big enough chops to be dangerous at vibe-coding have led to this: a full-featured, block-first personal knowledge bas…
13
Show HN: MandoCode Desktop – Native Windows AI Coding Assistant on Ollama .NET
本地AI编码助手，基于开源模型运行，可同时开启多个代理，保护代码隐私且不依赖厂商。
Quick backstory on how this version came to be: the original MandoCode is a CLI, and its UI is built with RazorConsole — Blazor components rendered in…
14
Agent and RAG for Obsidian, Need Feedback
Obsidian老用户自研Agent+RAG项目，本地Ollama驱动，求反馈及同好测试。
I just built this as a Personal/Portfolio project. I genuinely needed it, so I built it and I regularly use it. I wanted to know if anyone else who us…
15
Show HN: An interactive way to exploit an LLM without going to jail
交互式测试LLM安全防护，用多种模型模拟越狱攻击，开源可自部署
Article URL: https://github.com/joshfischer1108/jailbreak-lab Comments URL: https://news.ycombinator.com/item?id=49060776 Points: 2 # Comments: 0
16
Geometric Configurations of Perturbed Jailbreak Prompts
揭秘大模型安全软肋：扰动型越狱提示的几何结构，小模型内部表征泄露攻击机制。
arXiv:2607.20581v1 Announce Type: cross Abstract: Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuous…
17
Frontier-class LLM inference on a laptop CPU
笔记本CPU也能跑前沿LLM？这个开源项目性能直逼甚至超越llama.cpp，技术细节曝光效率提升关键。
Article URL: https://github.com/arizqi/cpubrrr Comments URL: https://news.ycombinator.com/item?id=49026595 Points: 1 # Comments: 0
18
Show HN: CLI Coding Agent that runs on llamafile and/or GGUF
基于llamafile/GGUF的终端编码智能体，本地运行高效又灵活
Article URL: https://github.com/kdeps/kdeps Comments URL: https://news.ycombinator.com/item?id=49029939 Points: 2 # Comments: 0
19
A Shared Subcircuit Lets LLMs Count Down Across Tasks
大模型内部发现通用倒数机制，助你在多种任务中精准控制输出长度
arXiv:2607.12279v1 Announce Type: cross Abstract: Writing a sentence of exactly twelve words; ending a DNA sequence at the right codon; formatting an …
20
Build a Local LLM Chatbot with Ollama and Python
手把手教你用Ollama和Python搭建本地大模型聊天机器人，零门槛运行AI
Build a Local LLM Chatbot with Ollama and Python Build a Local LLM Chatbot with Ollama and Python Imagine typing a question into your chatbot and gett…