惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

aimingoo的专栏
aimingoo的专栏
Y
Y Combinator Blog
云风的 BLOG
云风的 BLOG
Microsoft Azure Blog
Microsoft Azure Blog
腾讯CDC
T
The Blog of Author Tim Ferriss
P
Proofpoint News Feed
Hugging Face - Blog
Hugging Face - Blog
博客园_首页
小众软件
小众软件
美团技术团队
Martin Fowler
Martin Fowler
爱范儿
爱范儿
有赞技术团队
有赞技术团队
博客园 - 【当耐特】
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Microsoft Security Blog
Microsoft Security Blog
宝玉的分享
宝玉的分享
J
Java Code Geeks
B
Blog
V
V2EX
Stack Overflow Blog
Stack Overflow Blog
B
Blog RSS Feed
博客园 - Franky

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
Zorv | Autonomous AI CVE Patcher for Node.js & Python Dep...
youelfedr · 2026-06-04 · via Hacker News - Newest: "AI"
by OpenYF AI

ZORV

_

Get Lifetime Access

Run it locally or inside your CI/CD. 100% self-hosted. Zero subscription fees.

Why bots fall short

Traditional Dependency Bots Break Your Builds.
You Clean Up the Mess.

Standard tools like Dependabot and Renovate are great at finding outdated packages, but they only do half the job. When they bump a major package version:

1. Breaks Tests

The package API changes, throwing errors and breaking your suite.

2. Blocks Backlog

The PR sits gathering dust, requiring developers to fix manually.

3. Triggers Alerts

Security teams continuously flag unresolved CVE security alerts.

Zorv fixes this by acting as an autonomous developer in your CI pipeline. When a package bump breaks your tests, Zorv analyzes the test failure, rewrites the obsolete API usage, verifies the tests pass, and opens a clean, merge-ready Pull Request.

See it in action

The loop that secures your codebase

1

Audit & Scan

Zorv scans your repository using npm audit to extract patchable CVEs and target package versions.

2

Surgical Version Bump

It creates a new isolated Git branch and surgically upgrades the package in package.json.

3

Sandboxed Execution & Isolation

Zorv installs dependencies and runs your test suite inside an isolated Bubblewrap Linux sandbox. This blocks network access for tests, prevents directory traversal, and ensures untrusted code cannot touch your host OS.

4

AI Auto-Fix Loop

If tests fail, Zorv feeds the test logs and errors into your configured LLM (Azure OpenAI, Anthropic, Gemini, etc.) to rewrite the obsolete or broken API usage. It automatically repeats this loop until tests pass.

5

Commit & Open Pull Request

Once the tests are 100% green, Zorv stages only the modified source files, commits them, and opens a clean, merge-ready Pull Request with a clear explanation and diff summary.

Why Zorv is different

100% Self-Hosted CLI & Docker

Zorv runs entirely on your infrastructure. Your proprietary source code never leaves your network, keeping you fully compliant with SOC2, GDPR, and HIPAA.

Bubblewrap Isolation

The LLM-generated code runs in a hardened sandbox. Zorv blocks internet access for the tests, prevents directory traversal attacks, and isolates the host system.

11+ LLM Providers Supported

Plug in your own API keys. Zorv natively supports Azure OpenAI, OpenAI, Anthropic, Gemini, Grok, Groq, Cohere, TogetherAI, OpenRouter, and local models.

SOC2 Auditable Logs

Zorv generates append-only, ISO 8601-compliant JSONL logs documenting every single file read, write, and command execution for clear compliance verification.

Drop into GitHub Actions in 60 Seconds

Frequently Asked Questions

Works with

Gemini

OpenAI

Anthropic

DeepSeek

Ollama

Grok

Kimi

Perplexity

Qwen

xAI

Mistral