OpenAI has introduced Codex Luna Worker, a specialized agent designed for fast, narrowly scoped, and repeatable coding tasks. The agent operates with a high-reasoning model and follows strict develope…
A developer created claude-awake, a pair of scripts that keep a Mac awake (even with the lid closed) while Claude Code is actively running tasks, using heartbeat hooks and a pmset watchdog. The daemon…
The cuda-oxide project introduces proof-carrying views that eliminate bounds-check overhead in CUDA kernels written in Rust, boosting GEMM performance from 2,942 to 7,159 GFLOPS (2.43x) with only ~0.1…
A new JavaScript reference document, created by AI in collaboration with a user, provides a comprehensive matrix of how property types—enumerable vs non-enumerable, string vs symbol, and own vs inheri…
Dex Horthy, founder of HumanLayer, has outlined a four-gate software development workflow—Product, Architecture, Program Design, and Vertical Slices—designed to make critical decisions before code is …
Developer Giles Hall released a userscript that removes Amazon's 'Alexa for Shopping' (formerly Rufus) AI sidebar and reclaims the reserved gutter space. The script uses multiple layers of defense, in…
PrabhdeepSingh's sonu plugin introduces a daemonless ticket-queue poller, a cron wrapper that wakes a headless agent session only when a trigger label or in-flight ticket branch exists. The script, fa…
A developer created a bash script that blocks AI agents from using Homebrew on a system, displaying a warning message and exiting with code 42. The script instructs agents to use Nix instead, aiming t…
An engineer detailed how to set up routines, background agents, and stacked skills in Claude Code, sharing a repo-health check routine that runs scheduled cloud agents to verify README instructions. T…
A developer created a tool that generates concise, technically precise summaries of GitHub pull requests by grounding them in the actual diff rather than the PR description. The tool resolves the PR f…
Deep Dey, an 18-year-old Class 12 student, released a comprehensive security white paper analyzing the NetMirror Android application, detailing its permissions, network activity, and native libraries.…
An engineer at vLLM analyzed concurrent KV block load coalescing in Mooncake and vLLM, finding that while the code path for single-flight optimization exists, real traces show almost no coalescable wo…
A developer using the handle @99hud has published a step-by-step guide for using Anthropic's Claude desktop app with the Apify Google Maps connector to generate lists of local businesses with contact …
A developer has compiled an overview of AI engineering techniques, including training from scratch, fine-tuning, quantization, prompt engineering, structured outputs, tool calling, RAG, model routing,…
A developer released a shell script that lets users test custom prompts against an already-trained ESP32-S3 model without retraining or rewriting the 15MB model partition. The script tokenizes the pro…
A developer has released a one-shot build script that automates the entire pipeline for running a 28M parameter AI model on an ESP32-S3 microcontroller, from cloning the repository to training, export…
A developer shared a configuration guide for integrating Qwen AI models into OpenCode on Ubuntu Linux, providing the JSON configuration file path and code snippet for setting up the Qwen provider with…
ForgentAI has published a GTM tender-match MCP client metadata file, specifying OAuth 2.0 device code and refresh token grants for its native application. The metadata defines client identity, authori…
An engineer has published a style guide that applies the ASD-STE100 Simplified Technical English standard to AI agent output. The guide instructs agents to use active voice, simple tenses, and short s…
Sarvam AI released version 0.38.0 of its Sarvam Code CLI, an autonomous software-engineering agent. The update includes a full agent system prompt extracted from the darwin-arm64 binary, detailing the…