A developer published a guide for building an LLM-maintained wiki, following the structure of karpathy/llm-wiki. The system uses three folders—raw sources, a wiki, and an instruction file—to have the …
A developer introduced Logical Word Count, a cheap, tokenizer-free measure of text length that stays roughly proportional to LLM token counts across languages, code, and mixed content. The method uses…
A developer shared a starter configuration for Claude Code, a tool that uses AI to assist with coding tasks. The configuration includes a curated allowlist of safe commands, integration with the open-…
A developer argues that AI is shifting the value center in startups from technical implementation to market understanding and domain expertise. As AI agents handle coding, testing, and deployment, the…
Wing Zero, an agent created by Ethan Troy, released review-triage-eval v0.0.1, a skill for handling inbound code review requests. The skill triages artifact types and risk tiers, evaluates grounded fi…
A developer created claudex, a tool that allows users to run OpenAI's GPT/Codex models through Claude Code's interface and terminal UX. It uses a local CLIProxyAPI server to translate and route reques…
A developer created a SourceTree custom action that uses Anthropic's Claude CLI to automatically generate commit messages from staged diffs. The script enforces Conventional Commits format, truncates …
A developer introduced a Product Manager skill for orchestrating independent Codex app threads. The skill uses RICE scoring for prioritization and risk-adjusted expected value to allocate compute, whi…
A developer documented a complete guide for running the Hermes AI agent on a Raspberry Pi 5 with 16 GB RAM, enabling a self-improving agent that operates 24/7 on a home network. The setup uses a remot…
A developer deployed vLLM locally on two NVIDIA RTX 5060 Ti 16GB GPUs using Docker Compose, configuring tensor parallelism, FP8 KV cache, and speculative decoding with MTP. The setup runs an OpenAI-co…
A developer discovered that the Tesla P100 GPU has been performing inaccurate floating-point arithmetic in llama.cpp for years due to a missing architecture check. A three-line patch that excludes the…
A developer shared their Zed editor configuration, detailing settings for panels, agent servers, LSP, theme, keymap, and language-specific formatters. The configuration includes customizations for Typ…
A developer created an installable skill package for Claude Code, opencode, and Codex CLI that enables AI coding agents to generate INSAT end-of-studies (PFE) reports from a LaTeX template. The skill …
Anthropic introduced a new orchestration command for Claude Code that enables tiered subagents to research, plan, and execute complex tasks under human oversight. The system uses an orchestrator agent…
A developer used Grok 4.5 to build an interactive 3D soda landing page in a single shot. The page features a 3D soda can that tilts toward the cursor, floating berry models repelled by the pointer, an…
A developer submitted a patch for the Halt-bench agent, including a new test requirement and a large append-only file for NodeBB configuration. The patch adds a require directive for a CI environment …
Artificial Analysis evaluated all 15 combinations of OpenAI's GPT-5.6 Sol, Terra, and Luna models across five reasoning effort levels. The analysis found that Terra is never on the intelligence-vs-cos…
A developer created fable-mode, a skill that gives Claude Opus 4.8 the execution discipline of Claude Fable 5, including autonomous execution, evidence-grounded progress, outcome-first communication, …
A developer published a step-by-step guide to running Claude Code for free using alternative API endpoints from AgentRouter and IAMHC. The guide covers installation, configuration, and troubleshooting…
NaN Builders has published a comprehensive configuration guide for its LLM API, detailing setup instructions for clients, IDEs, agents, and SDKs. The guide covers available models including deepseek-v…