Asto – AST-based code editing for AI agents
AST operations beat fragile text patches for AI agent code edits.
Agent Integrated Development Environment (CLI Tool)
AST scalpel for agents, but existing code-gen tools already handle large refactors.
AI agent developers, infrastructure teams automating code refactors
Codemod · ast-grep · IDE refactoring engines
AST operations beat fragile text patches for AI agent code edits.
It turns real program analysis — ASTs, cross-file dependency graphs, taint tracking and Z3 symbolic paths — into callable MCP tools for agents, not just another prettier linter. Concrete features like simulate_refactor, generate_unit_tests from symbolic paths, and cross-file security_scan give it a distinct technical voice. The <10% false-positive claim and heavy test coverage are promising, but I'd want to see results on large, messy repos before swapping out existing scanners.
Hash-anchored AST edits beat Cline and Roo on cost with reproducible evals.
AST-based contracts beat raw code for AI, but codebase analyzers are increasingly crowded.
CLI wrapper for docx editing when python-docx already exists.
AST-verified AI code audits prevent hallucinations; LLM findings checked against parser ground truth.