coding agent adding null checks at every layer? tell it: validate once where data comes in, then trust the types inside. also: no single-use helpers, inline the logic until something gets reused. put both lines in your AGENTS.md.

if you run a few claude code sessions at once, this one's built for it • sessions grouped by project in a sidebar • allow / deny a tool permission right from the sidebar • diff panel where you leave notes and send them back to claude • each session gets its own git worktree mac only, just 32 stars so far github.com/onurozcan/omux

An offline AI assistant for when the internet goes down ask it how to keep food safe in a blackout or treat a burn it answers from FEMA/CDC guides + a local Wikipedia, and shows the exact article it used free and open source, set up once online and after that it needs no internet brangus.io/survival-llm

opus 5.5 + blender + unreal, and the thing is actually playable. that's the bar now: not a render, a game you can pick up and play.

bookmark this if you build UIs 7 free animated component libraries: skiper-ui.com kokonutui.com cult-ui.com smoothui.dev animata.design eldoraui.site hover.dev all copy-paste, all animated. saves hours of fiddling with motion

this 4B model has a neuron that seems to read sarcasm neuron explorer pushes every MLP neuron in Qwen3.5-4B up and down, keeps every output, and maps them in 3D. click one and chat with it steered -/0/+ side by side there's a claude tab that digs through neurons for you. runs locally github.com/lyramakesmusic/ne…

one night of meteors, sorted by a model while the owner slept openskycam records the sky 24/7 onto your own disk. every morning detection models go through the footage and split meteors from planes and fixed lights you review, fix labels, and it builds a training set. there's an MCP server so claude code can set it up and run it github.com/Deibler/openskyca…

ok google's image + video models are free inside memelord till oct 31 nano banana, nano banana edit and gemini omni video, unlimited, no memelord credits used only the google models though, their other tools still use credits free until oct 31, 11:59pm CT memelord.com/google

An F1 explainer you can actually flip upside down. the glass power unit view looks great. Claude + Three.js and it holds up.

open-source take on Claude in Chrome. side-panel agent that reads, clicks and fills forms across your tabs bring your own model: Anthropic, OpenAI, Gemini or local Ollama no account, no backend, keys stay in Chrome storage it's beta, so keep it off anything irreversible github.com/DumDuky/myna-brow…

hidden claude code flag: --advisor claude --model sonnet --advisor opus sonnet handles the routine work, opus gets pulled in for planning, ambiguous failures and completion checks experimental, and it's not listed in claude --help code.claude.com/docs/en/advi…

a rhythm runner where the song builds the level 4 tiny neural nets (~22 MB total) listen to your mp3 in the tab: beats, notes, vocals, pitch. the game gets built from that same song, same world every time, and nothing gets uploaded play: struna.ai code: github.com/Felliks/Struna

my claude code sessions all look the same until one silently waits on a permission prompt agentvalley parks them in the mac notch: one row per agent and sub-agent, which model it's on, and a red badge when one needs you each agent gets its own pixel programmer. free + open source, mac with a notch only agentvalley.app

a 4B model that writes whole Three.js scenes from one prompt the Q4 file is 2.7 GB, small enough to run locally these scenes are from the model card, one self-contained HTML file each still an early preview, dev says full weights + dataset come later ollama run hf.co/ccore/Qwen3.5-4B-3D-Co… huggingface.co/ccore/Qwen3.5…

too many subagents in your agent? anthropic says try folding them back into one loop skills for the how-to, tools for hard limits. one customer saw roughly 2x faster runtime subagents still win for parallel work and context bloat claude.com/resources/article…

how much compute does it take to beat warcraft 3's hardest built-in AI? one desktop. a 3090 and 16 cpu cores ~50 copies of the real game at 15x speed, three weeks of self-play, 840k games. it now wins 89% against insane alphastar used 32 TPUs per agent for 44 days robin kahlow's write-up + code: warlock.ai/blog/warcraftsim-…

for redesigning an existing site, opus has been closer to what i want than codex. way less back and forth but i don't buy that one model wins everything what's the one task where you'd still pick the other one?

tiny mac menu bar app that shows how much of your claude code, codex, gemini and grok limits you've burned 5-hour and weekly bars, plus when each one resets. it asks the official CLIs, never touches your tokens github.com/dancik/limitbar

Scrolling the terminal to work out what your coding agent just did gets old agentplay replays each session as a map and a timeline: what it read, what it edited, what failed, what shipped works with Claude Code, Codex, Cursor, Copilot, Gemini CLI. local, one command: uvx agentplay github.com/Entelligence-AI/a…

the maker kept screenshotting handwritten calculus into claude and reading long answers back. wanted a teacher looking over the shoulder instead now you write by hand, press one key, and it circles the line where you slipped and gives a hint, not the answer. box an integral and you get a 3blue1brown-style animation works with claude code, codex or gemini. linux only for now github.com/AbdullahAlhariri/…