A curated collection of noteworthy tools, articles, and resources from across the web — searchable, organized, and enriched with AI analysis.
Showing 481-504 of 1253 bookmarks
All Stories
Python command-line tool for interacting with AI models through the OpenRouter API/Cloudflare AI Gateway, or local self-hosted Ollama. Optionally support Microsoft LLMLingua prompt token compressi…
LM Studio 0.4.0 introduced llmster and the lms CLI. Here is how I set up Gemma 4 26B for local inference on macOS that can be used with Claude Code.
Terminal based spreadsheet tool. Contribute to maaslalani/sheets development by creating an account on GitHub.
Gemma Gem runs Google’s Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine. - kessler/gemma-gem
A ~9M parameter LLM that talks like a small fish. Contribute to arman-bd/guppylm development by creating an account on GitHub.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A set of delightful extensions for Pi. Contribute to tmustier/pi-extensions development by creating an account on GitHub.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
The blog surveys 7 configuration changes to transform a multi-homed Linux host into a switch or router: activating IP forwarding, defining bridges, nftables policies, stateful firewalling with conntrack, NAT and masquerade policies, DHCP/DNS with dnsmasq, and WiFi with hostapd. It explains packet processing in the Linux kernel networking stack, including netfilter hooks at PREROUTING, INPUT, FORWARD, OUTPUT, and POSTROUTING stages. IP forwarding is enabled via net.ipv4.ip_forward=1 in /etc/sysctl.d/, allowing packets to reach the FORWARD hook instead of being dropped.
April 2026 TLDR setup for Ollama + Gemma 4 26B on a Mac mini (Apple Silicon) — auto-start, preload, and keep-alive - how-to-setup-ollama-on-a-macmini.md
Recordly is an open‑source screen recorder for MacOS/Windows/Linux with auto-zoom, motion blur animated cursors, webcam overlays, auto-captions and more. Used to create product demos, guided walkth…
Capy is the AI-native IDE for parallel development. Run multiple coding agents at once, ship faster, and manage work from task to PR.
Strix Halo Toolboxes provide containerized environments using Toolbx for running AI workloads on AMD's Ryzen AI MAX+ (Strix Halo) processors with up to 128GB unified memory. They include repositories for LLAMA.CPP (LLM inference with RDMA/Vulkan/ROCm), ComfyUI (image/video generation), VLLM (serving with RCCL patches), and LLM fine-tuning (QLoRA/full for Gemma 3/Qwen 3). Setup on Fedora 43 with Framework Desktop uses custom kernel parameters for dynamic memory allocation, GPU device mapping, and accelerator-performance tuning.
LLM inference in C/C++. Contribute to ubergarm/llama.cpp development by creating an account on GitHub.
Use Codex from Claude Code to review code or delegate tasks. - openai/codex-plugin-cc
📄 A cheat sheet for Kotlin programming language. Contribute to alidehkhodaei/kotlin-cheat-sheet development by creating an account on GitHub.
Contribute to chenglou/pretext development by creating an account on GitHub.
Search, browse, and resume sessions across Codex, Claude, Gemini, Copilot, Droid, OpenCode, and OpenClaw. New in 3.3.3.1: fixes Codex reset countdown exceeding 5 hours.
Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents - manaflow-ai/cmux
This guide details Go's identifier rules: unicode letters, digits, underscores only; no leading digits; no keywords. It mandates camelCase for unexported and PascalCase for exported identifiers, consistent acronym casing like userID, ASCII letters, no clashes with builtins or stdlib, and minimal type inclusion in names. Identifier length should increase with scope for descriptiveness, with exported items capitalized and main packages mostly unexported.
Spanish legislation as a Git repo — every law is a Markdown file, every reform a commit. 8,600+ laws. - EnriqueLop/legalize-es
What if you could let Claude and Codex work together as pair programmers, talking to each other directly? One of them as the main worker and the other as a reviewer.
Embed AI Search components in your website and connect AI agents via MCP.
Hetzner VPS setup guide for Ubuntu 24.04 — hardened SSH, fail2ban, UFW firewall, and optional Tailscale. Claude Code prompt. - deniurchak/claude-vps-setup-prompt
