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

D
Docker
B
Blog RSS Feed
Microsoft Security Blog
Microsoft Security Blog
Y
Y Combinator Blog
N
Netflix TechBlog - Medium
M
MIT News - Artificial intelligence
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
B
Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
C
Check Point Blog
The GitHub Blog
The GitHub Blog
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
P
Proofpoint News Feed
Martin Fowler
Martin Fowler
大猫的无限游戏
大猫的无限游戏
GbyAI
GbyAI
博客园_首页
A
About on SuperTechFans
Blog — PlanetScale
Blog — PlanetScale
人人都是产品经理
人人都是产品经理
T
Tailwind CSS Blog
aimingoo的专栏
aimingoo的专栏
T
The Blog of Author Tim Ferriss
The Cloudflare Blog

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
GitHub - basilevincenzo/ai-code-reviewer
basilevincen · 2026-04-28 · via Hacker News - Newest: "AI"

Automatic AI code review on every pull request. No API keys. No cost. Powered by GitHub Models.

How it works

When you open a PR, the bot reviews every changed file and posts inline comments for bugs, security issues, and bad practices. PRs with critical issues fail the check.

Setup

Option A — Fork (easiest)

Click Fork at the top of this page. Done. The bot is ready on your fork immediately — no configuration needed.

Option B — Add to an existing repository

  1. Copy the src/ folder and package.json from this repo into your project root
  2. Copy .github/workflows/review.yml into your project
  3. Run npm install once to install dependencies
  4. Push to GitHub — the bot activates on the next PR

No secrets, no tokens, no billing.

How authentication works

The bot uses the GITHUB_TOKEN — a temporary token that GitHub automatically generates for every workflow run. You don't create it, store it, or pay for it.

  • It's scoped to your repo only — no access to other repos or accounts
  • It expires after each run — can't be leaked or reused
  • Each user gets their own — forking the repo gives every user their independent token
  • No setup required — GitHub injects it automatically via ${{ secrets.GITHUB_TOKEN }}

If you ever need to inspect it: Settings → Actions → General → Workflow permissions.

For local testing only — if you want to run the bot on your machine instead of via GitHub Actions, you need a Personal Access Token (PAT):

  1. Go to https://github.com/settings/tokens/new
  2. Give it a name (e.g. ai-code-reviewer-local)
  3. Select scopes: repo + workflow + models (if available)
  4. Click Generate token and copy it
  5. Paste it in your .env file as GITHUB_TOKEN=ghp_your_token_here

The PAT is only needed locally. In GitHub Actions, everything is automatic.

Example

Inline comment on SQL injection

AI Code Review Summary

What it detects

Severity Examples
🔴 Critical SQL injection, XSS, eval(), hardcoded credentials, null dereference, division by zero
🟡 Warning Memory leaks, race conditions, missing error handling, performance issues
💡 Suggestion Code style, naming, best practices

Languages supported

JavaScript, TypeScript, Python, Java, Go, PHP, Ruby, C, C++, and more. Skips lock files, minified files, images, and docs.

Blocking merges on critical issues

To prevent merging PRs with critical bugs:

  1. Go to Settings → Branches → Add branch protection rule
  2. Set branch name pattern to main
  3. Enable Require status checks to pass before merging
  4. Add AI Code Review / review

Requires GitHub Pro for private repositories. Works for free on public repositories.

Requirements

  • GitHub repository (public or private)
  • GitHub Actions enabled
  • Node.js 18+