TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Jolt – AI coding tool for production, 100K+ line codebases

15 点作者 yevyevyev4 个月前

2 条评论

yevyevyev4 个月前
Hey HN,<p>We built Jolt to solve a fundamental problem with AI coding tools - they struggle with larger, real-world codebases and cannot accurately determine the context files for your prompt.<p>Jolt&#x27;s public beta is live today, and we&#x27;d love your feedback. You can use Jolt on the web or in any VSCode-based IDE. Our free tier will let you work on codebases up to ~100K lines.<p>We developed a novel way for Jolt to understand large codebases and automatically determine context files. Our approach scales to multi-million line codebases - the largest codebase using us in production is over 8M lines.<p>Jolt is optimized for codebase understanding rather than response speed. That said, using Jolt is significantly faster than other tools when you include the time spent selecting context files.<p>Manually selecting context files is a non-starter when you&#x27;re working on larger codebases or unfamiliar code. It&#x27;s a broken product experience. Most AI coding tools rely on some flavor of vector-embedding RAG to determine the files related to your prompt. The reality is that vector-embedding search is not effective on code, and there is a sharp drop in efficacy as codebase size increases.<p>Here&#x27;s what folks are using Jolt for: - Writing code, tests, and refactoring - Onboarding developers - Brainstorming a feature&#x27;s implementation - Asking questions about OSS repos - Writing documentation, including mermaid charts - Contributing across the stack<p>Thanks for reading, and let us know what you think.
HrubyOnRails4 个月前
&gt; automatically determine context files this is the killer feature