Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

A faster coding agent than Codex and Claude Code

Details

External ID
49173799
Source
HN
Company
—
Product
A faster coding agent than Codex and Claude Code
Website domain
codewithbullet.com
Launched
Aug. 4, 2026
Cohort
—
Upvotes
9
Upvotes percentile
0.5309139784946236
Tags
—
Fetched at
Sept. 10, 2026, 5:32 a.m.
Updated at
Sept. 10, 2026, 5:32 a.m.

Description

Hi HN, excited to be sharing this with you guys today.TL;DR: Bullet is a fast coding agent.At our company, we were burning hours waiting on agent runs. The models weren’t the problem. The agent loops around them were slow (unnecessary planning, oversized context, repeated searches, and serial tool calls).So we built Bullet as a passion project, the goal being to help you iterate faster, without giving up quality: - It automatically selects the model and reasoning level for each prompt. - It runs independent searches, reads, and commands in parallel. - It uses targeted code search instead of embedding the entire repository. - It works with your Claude Code or Codex subscription, OpenAI/Anthropic/xAI API keys, or an on-device model with no key.Claude Code and Codex each center on their own model ecosystem. OpenCode gives you many models, but largely leaves model selection and configuration to you. Bullet sits above the models. Connect what you already pay for, then let Bullet choose the fastest path for every task.On SWE-bench Verified, Bullet resolved 479/500 issues (95.8%, top 3 on the leaderboard) in one attempt, averaging 119 seconds per task (35–67% faster than mini-SWE-agent + Fable/Sol). Full results and methodology here: https://www.codewithbullet.com/blog/benchmark-results.htmlWe would love honest feedback on the product! It takes less than a minute to download and set up. We’d love to hear what you like about Bullet, and what sucks. The Mac app DMG release is on our website: https://www.codewithbullet.com/P.S: we hid a code on the website, see if you can unlock the secret page at the footer (all built with Bullet) :) https://youtu.be/34wfiSoSw4Q

Enrichment

Theme
Claude integrations and coding agents
Vertical
—
Function
Agent / copilot
Audience
Developer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
coding agent for developers
Manually corrected
False

Could you build this?

Partial Building a basic CLI coding agent with tool calling and routing is straightforward, but achieving top-tier SWE-bench performance (claimed 95.8%) and sub-second parallel execution requires deep agent loop tuning and benchmark optimization.

What it would actually take: The stack involves Node.js/TypeScript or Rust for the CLI, tree-sitter or ripgrep for AST/regex code search, and async tool orchestration interfacing with LLM APIs. The hard part is building an execution engine that parallelizes independent tool calls without causing state drift, managing tight context pruning without hallucination, and routing dynamically across models to hit high SWE-bench benchmarks.

Discussion

6 comments analyzed.

Competitors mentioned: Claude Code, Github Copilot

Concerns raised: Speed/latency significantly slower than Claude Code (13 min vs 12 min on comparable task), File autocomplete missing for @<filename> references, Doesn't automatically load CLAUDE.md context file, Plan progress marks completion prematurely before code generation, Excessive model calls and unnecessary tasks during execution

Feature requests: Add file autocomplete for @<filename> references, Auto-load CLAUDE.md equivalent for repository context, Show exact task duration/timing when completed, Improve plan progress tracking accuracy

Competitors

Other products that read as similar to this one — 357 launches clear the similarity bar, closest 8 shown.

Attention rank: #185 of 358 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 273 days after the earliest competitor.

Other launches for this product