HackerNews中文版

大家好，HN！我们是来自 DeepSource (YC W20) 的 Jai 和 Sanket，今天我们推出了 Autofix Bot，这是一个混合静态分析 + AI 代理，专为与 AI 编码代理协同使用而设计。AI 编码代理让代码生成变得几乎免费，并将瓶颈转移到了代码审查。仅使用固定检查器的静态分析是不够的。仅使用 LLM 进行审查也有几个局限性：运行之间不确定性、安全问题召回率低、大规模成本高昂，并且容易“分心”。我们花了过去 6 年的时间构建了一个确定性的、仅静态分析的代码审查产品。今年早些时候，我们从头开始思考这个问题，并意识到静态分析解决了仅 LLM 审查的关键盲点。在过去的六个月里，我们构建了一个新的“混合”代理循环，该循环将静态分析和前沿 AI 代理结合在一起，在发现和修复代码质量和安全问题方面，优于仅静态分析和仅 LLM 工具。今天，我们向公众开放它。混合架构的工作原理如下：<pre><code> - 静态分析：5,000 多个确定性检查器（代码质量、安全性、性能）建立高精度基线。子代理抑制特定于上下文的误报。 - AI 审查：代理使用静态分析结果作为锚点来审查代码。可以访问 AST、数据流图、控制流、导入图等工具，而不仅仅是 grep 和常用的 shell 命令。 - 修复：子代理生成修复方案。静态工具在发出干净的 git patch 之前验证所有编辑。 </code></pre> 静态分析解决了 LLM 的关键问题：运行之间的不确定性、安全问题召回率低（LLM 容易被风格问题分心）以及成本（静态分析缩小了提示大小和工具调用）。在 OpenSSF CVE 基准测试 [1]（200 多个真实的 JS/TS 漏洞）中，我们的准确率达到 81.2%，F1 分数为 80.0%；而 Cursor Bugbot（准确率 74.5%，F1 分数 77.42%）、Claude Code（准确率 71.5%，F1 分数 62.99%）、CodeRabbit（准确率 59.4%，F1 分数 36.19%）和 Semgrep CE（准确率 56.9%，F1 分数 38.26%）。在秘密信息检测方面，F1 分数为 92.8%；而 Gitleaks（75.6%）、detect-secrets（64.1%）和 TruffleHog（41.2%）。我们为此使用了我们的开源分类模型。[2]完整的评估方法和我们如何评估每个工具：<a href="https://autofix.bot/benchmarks" rel="nofollow">https://autofix.bot/benchmarks</a>您可以使用我们的 TUI 在任何存储库上交互式地使用 Autofix Bot，将其作为 Claude Code 中的插件，或与我们的 MCP 在任何兼容的 AI 客户端（如 OpenAI Codex）上使用。[3] 我们专门为 AI 编码代理优先的工作流程而构建，因此您可以要求您的代理在每个检查点自动运行 Autofix Bot。今天就试试吧：<a href="https://autofix.bot" rel="nofollow">https://autofix.bot</a>。我们很乐意听取任何反馈！---[1] <a href="https://github.com/ossf-cve-benchmark/ossf-cve-benchmark" rel="nofollow">https://github.com/ossf-cve-benchmark/ossf-cve-benchmark</a>[2] <a href="https://huggingface.co/deepsource/Narada-3.2-3B-v1" rel="nofollow">https://huggingface.co/deepsource/Narada-3.2-3B-v1</a>[3] <a href="https://autofix.bot/manual/#terminal-ui" rel="nofollow">https://autofix.bot/manual/#terminal-ui</a>

查看原文

Hi there, HN! We’re Jai and Sanket from DeepSource (YC W20), and today we’re launching Autofix Bot, a hybrid static analysis + AI agent purpose-built for in-the-loop use with AI coding agents.AI coding agents have made code generation nearly free, and they’ve shifted the bottleneck to code review. Static-only analysis with a fixed set of checkers isn’t enough. LLM-only review has several limitations: non-deterministic across runs, low recall on security issues, expensive at scale, and a tendency to get ‘distracted’.We spent the last 6 years building a deterministic, static-analysis-only code review product. Earlier this year, we started thinking about this problem from the ground up and realized that static analysis solves key blind spots of LLM-only reviews. Over the past six months, we built a new ‘hybrid’ agent loop that uses static analysis and frontier AI agents together to outperform both static-only and LLM-only tools in finding and fixing code quality and security issues. Today, we’re opening it up publicly.Here’s how the hybrid architecture works:<pre><code> - Static pass: 5,000+ deterministic checkers (code quality, security, performance) establish a high-precision baseline. A sub-agent suppresses context-specific false positives. - AI review: The agent reviews code with static findings as anchors. Has access to AST, data-flow graphs, control-flow, import graphs as tools, not just grep and usual shell commands. - Remediation: Sub-agents generate fixes. Static harness validates all edits before emitting a clean git patch. </code></pre> Static solves key LLM problems: non-determinism across runs, low recall on security issues (LLMs get distracted by style), and cost (static narrowing reduces prompt size and tool calls).On the OpenSSF CVE Benchmark [1] (200+ real JS/TS vulnerabilities), we hit 81.2% accuracy and 80.0% F1; vs Cursor Bugbot (74.5% accuracy, 77.42% F1), Claude Code (71.5% accuracy, 62.99% F1), CodeRabbit (59.4% accuracy, 36.19% F1), and Semgrep CE (56.9% accuracy, 38.26% F1). On secrets detection, 92.8% F1; vs Gitleaks (75.6%), detect-secrets (64.1%), and TruffleHog (41.2%). We use our open-source classification model for this. [2]Full methodology and how we evaluated each tool: <a href="https://autofix.bot/benchmarks" rel="nofollow">https://autofix.bot/benchmarks</a>You can use Autofix Bot interactively on any repository using our TUI, as a plugin in Claude Code, or with our MCP on any compatible AI client (like OpenAI Codex).[3] We’re specifically building for AI coding agent-first workflows, so you can ask your agent to run Autofix Bot on every checkpoint autonomously.Give us a shot today: <a href="https://autofix.bot" rel="nofollow">https://autofix.bot</a>. We’d love to hear any feedback!---[1] <a href="https://github.com/ossf-cve-benchmark/ossf-cve-benchmark" rel="nofollow">https://github.com/ossf-cve-benchmark/ossf-cve-benchmark</a>[2] <a href="https://huggingface.co/deepsource/Narada-3.2-3B-v1" rel="nofollow">https://huggingface.co/deepsource/Narada-3.2-3B-v1</a>[3] <a href="https://autofix.bot/manual/#terminal-ui" rel="nofollow">https://autofix.bot/manual/#terminal-ui</a>

Show HN: Autofix Bot – 混合静态分析与 AI 代码审查代理