Crespo – Tree-sitter AST blueprints instead of raw code for LLMs
Tree-sitter AST blueprints compress codebase context when JinaAI and Firecrawl already exist.
Your codebase was probably AI-generated. Get a better handle on it. Noodles creates interactive diagrams that visualize how your code actually works, so you can understand what the AI built without reading every line.
Tree-sitter + agentic flow ~50x faster than raw LLM calls, but codebase visualization is crowded category.
Developers onboarding to AI-generated codebases, code reviewers analyzing PRs, teams auditing unfamiliar repositories
code2flow · Sourcetrail · GitHub Copilot Code Review
Just shipped a big update:
- Switched from D2 to Mermaid for rendering - Tree-sitter AST parsing + agentic flow instead of raw LLM calls. ~50x faster. - Works on any GitHub repo or PR, not just local - Dropped the web frontend, it's just a CLI now - Published as a pip package
Still a ton to improve and I'm building fast. Feedback, issues, PRs all welcome.
Tree-sitter AST blueprints compress codebase context when JinaAI and Firecrawl already exist.
Yet another codebase visualizer competing with Sourcegraph and Cursor.
AST + embeddings for codebase search—but Sourcegraph Cody, Cursor, and Continue already solve this.
Tree-sitter AST compression cuts LLM context tokens 50-70% while preserving API structure.
Tree-sitter AST parsing beats regex for architecture drift detection.
MCP server lets Claude Code query blast radius before editing code.