Parseltongue compresses large codebases into 5%-size dependency maps for AI coding agents
paraschopra · x · 2026-10-27
Resident Amul is building Parseltongue, which turns a large codebase into a compact public-interface dependency graph (5% of the code's size) so AI coding agents can navigate faster and cheaper. A tree-sitter-based CLI already exists (105 GitHub stars), but tree-sitter isn't enough for thorough graphs. Plan: post-train an open-weight LLM under 100 MB RAM to draw these maps for Rust code, trained on the top 50 OSS Rust libraries with Codex-generated labels, aiming to beat tree-sitter on unseen codebases.
More from coding & agent
- OpenAI, Google, Anthropic Reportedly Building FINRA-Style AI Self-Regulator by 2027 — emmanuelvivier · 2026-10-27
- IBM Launches Verifiable Identity and Control for Enterprise AI Agents — emmanuelvivier · 2026-10-27
- One word in your prompt decides the language: 'easy' gets Python, 'fast' gets Rust — rseroter · 2026-10-27
- NewMax runs optimized Claude Code with BYOK keys, plus pool rotation and OAuth — yangyi · 2026-10-27
- Vibecoder builds interactive map of NYC restaurants owned by private equity firms — Polymarket · 2026-10-27
- How to Get Cited by ChatGPT: A 6-Step AEO Playbook — jamesbrooksco · 2026-10-27