Model-agnostic agent harness for local LLMs — configure agents in YAML and run them on your own hardware (vLLM, Ollama, LM Studio, llama.cpp). - ahwurm/localharness Read more ›
Bitrise engineer Olivér Falvai on how Xcode 27's Device Hub and devicectl unify simulators and physical devices, and what that unlocks for iOS CI/CD. Read more ›
# Tirith > Tirith is a free, open-source terminal security tool that intercepts shell commands and pastes in real-time, detecting homograph attacks, pipe-to-shell patterns, ANSI injection, credential leaks, data exfiltration, AI-config drift, and 200+ other threats across 29 categories — in under 2ms with zero network calls. Written in Rust. Used by developers and AI coding agents. ## What Problem Does Tirith Solve? Browsers have URL safety checks, phishing filters, and certificate warning... Read more ›
Organize your job hunt with Jobflo. Track applications, utilize on-device AI for resume matching, and beat ghost jobs. The ultimate local-first job search tracker for professionals. Read more ›
I noticed how slow my ZSH had. gotten and decided to fix it. Timed, profiled, and fixed it. Read more ›
1 point by kanakkholwal 7 minutes ago \| hide \| past \| favorite \| discuss Guidelines \| FAQ \| Lists \| API \| Security \| Legal \| Apply to YC \| Contact Read more ›
Otty is a blazing-fast, GPU-accelerated terminal emulator. Read more ›
There's a lot of talk about the shortcomings of LLMs. They don't actually reason. They're expensive, especially when running in a loop. They're quite slow at doing things. There's a narrow category of use cases that LLMs excel at, one of which is "sifting through the noise". The noise is everything we have to process Read more ›
Thanks to the support of the community, the project now has a future again. Those who gave through donations, operating nodes, and spreading awareness are the reason the ecosystem lives on. Development of the project will resume, and critical infrastructure will continue to be supported. Session will remain available. Read more ›
From pretraining to RLHF/GRPO — every algorithm hand-written in pure PyTorch. Read more ›
ax watches every session your coding agent runs, spots the mistakes it repeats, and turns them into small, repo-specific fixes you review and apply - one at a time. Local-first, typed, AGPL-3.0. Read more ›
TL;DR: Newly published tests show a Chromium/Blink prototype running on iOS is 28.6% faster than Safari in Speedometer 3.1 page responsiveness tests. The tests also highlight a significant number of web features already available in the prototype but which rival browser vendors are blocked from bringing to iOS. This is a clear example of how much Apple's browser engine ban is costing consumers, businesses and the Web. Read more ›
Learn how Ray Serve LLM + vLLM stack achieves up to 24x higher throughput with direct streaming, HAProxy integration, and a new vLLM Ray executor backend. Read more ›
AI-powered zsh command generator that inserts safe, reviewable shell commands. - longyijdos/hi-shell Read more ›
Minimal local-first notes for projects, tasks, boards, calendars, and markdown - skorotkiewicz/gimji Read more ›
A terminal text editor. A real alternative to VS Code, Zed, and Sublime that runs in your terminal. Read more ›
Learn how modern AI evolved from simple language models to Transformers, reasoning models, and ChatGPT through practical examples and diagrams. Read more ›