ast-grep Reviews

CodeAnt AI Reviews

1. Amartya

   · Working at CodeAnt AI · 8 months ago

ast-grep mentions (24)

• The Self-Driving Codebase: Full Agent Automation with Otter

  The previous post covered how we structured the codebase: Effect conventions, ast-grep enforcement, Drift, and CLAUDE.md to collaborate with Claude Code. You describe what you want, review the output, iterate. That works well. This post is about what happens when you step away entirely: giving the agent a list of issues and letting it work through them while you do something else. In autonomous mode, there's no... - Source: dev.to / 3 months ago

• How we use Effect and ast-grep to make our codebase work better with agents

  We use ast-grep as a structural syntax scanner that operates on the syntax tree of code (using tree-sitter under the hood). You define patterns in a YAML file, and it matches those patterns against the codebase. Critically, it’s run as part of the CI pipeline and configured to exit with an error when a banned pattern is found. And they have to be errors, not warnings. We learned this the hard way. Warnings get... - Source: dev.to / 4 months ago

• Less human AI agents, please

  I linked this elsewhere but, the agent could have a skill to use https://ast-grep.github.io/ to perform such mechanical code changes. - Source: Hacker News / 4 months ago

• Less human AI agents, please

  The proper tool for this is ast-grep (sg) https://ast-grep.github.io/ And an agent can learn to use sg with a skill too. (Or they can use sed) The issue is, at every point you do a replace, you need to verify if it was the right thing to do or if it was a false positive. If you are doing this manually, there's the time to craft the sed or sg query, then for each replacement you need to check it. If there are... - Source: Hacker News / 4 months ago

• Be intentional about how AI changes your codebase

  We use https://ast-grep.github.io (on a pre-commit hook). Bridges the linter gaps nicely. - Source: Hacker News / 5 months ago

CodeAnt AI mentions (9)

• How to Use Snyk in CI/CD: Jenkins, GitHub Actions, More

  CodeAnt AI takes a different approach by bundling SAST security scanning with AI-powered code review in a single platform. Starting at $24 per user per month for the Growth plan and $40 per user per month for the Enterprise plan, CodeAnt AI provides static analysis, security vulnerability detection, and automated code quality review in one CI pipeline step. This can be more cost-effective than running separate... - Source: dev.to / 5 months ago

• How to Write Custom Semgrep Rules: Complete Tutorial

  CodeAnt AI provides a managed code review and security platform priced at $24 to $40 per user per month that includes built-in security rules covering OWASP Top 10 vulnerabilities, code quality checks, and automated PR reviews. CodeAnt AI is a strong option for teams that want comprehensive coverage out of the box without writing or maintaining custom rules. - Source: dev.to / 5 months ago

• DeepSource for JavaScript/TypeScript Projects

  CodeAnt AI is a modern code quality platform priced at $24-40/user/month that offers AI-powered analysis for JavaScript and TypeScript projects. Unlike DeepSource's primarily rule-based approach, CodeAnt AI uses AI models to detect code quality issues, security vulnerabilities, and anti-patterns - including context-dependent problems that deterministic rules miss. - Source: dev.to / 5 months ago

• Codacy Security Scanning: Find Vulnerabilities in Your Code

  If you are evaluating Codacy's security scanning, CodeAnt AI is worth putting in the comparison set. It is a Y Combinator-backed platform priced at $24-40/user/month that bundles several capabilities that Codacy either lacks or offers only on higher-tier plans. - Source: dev.to / 5 months ago

• How LLMs Are Transforming Code Review in 2026

  CodeAnt AI brings together LLM-powered analysis, deep code graph understanding, and automatic sequence diagram generation for every pull request. See why leading teams are making CodeAnt their standard for AI-assisted code review. - Source: dev.to / 5 months ago