Bullet
30-60% faster than Claude Code and Codex
What it does
Bullet is a coding agent built for speed. We got tired of burning hours waiting on agent runs. The models were fine, but the loops around them were slow. Bullet auto-picks the right model/reasoning level per prompt, parallelizes searches/reads/commands, and uses targeted code search instead of embedding your whole repo. Works with your Claude Code or Codex subscription, API keys, or an on-device model. 95.8% on SWE-bench Verified (top 3), 119s/task. Built by Yale CS grads, ex-AppLovin/Citadel.
Bullet is a really fast coding agent with a leaner orchestration layer.
Bullet routes, searches, and executes with one purpose: keeping up with you. Same model → tools → results pattern. A tighter loop around it. Route straightforward work to fast models. Escalate only when the mission demands it. Targeted search and file reads find relevant code without embedding the whole repo. Independent tool calls execute in parallel. Duplicate calls and stuck loops are intercepted before they waste another second. Same router, tools, and agent loop. Now it lives in your shell. At our company, we were burning hours waiting on agent runs. We were building with Claude Code every day, watching capable models move through needlessly slow machinery. So Bullet began as a passion…from codewithbullet.com
Does the same job
all alternatives →
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
Lettertrace▲375Track your AI visibility for free (using your own API keys!)
Dev tools · 25d ago · lettertrace.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 9d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com