AI Developer Tool · Rust

llmastsearch

AST-based code search with tree-sitter for LLM consumption

Luiz Cesar Spies@oldnordic · Atlas 77.7 · #1 builder

View on GitHub Open Luiz Cesar Spies's Atlas

What it is

The llmastsearch project is a Rust-based command-line tool and library for performing syntax-aware code queries using tree-sitter parsers, providing structured JSON output optimized for LLM consumption. It supports seven programming languages and includes features such as language detection, glob pattern matching, and directory filtering.

Scored from the code at its last scan, 11 Oct 2026. How merit is scored

Where it counts

NLP & LLMs80%
Machine Learning30%
AI Agents20%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the NLP & LLMs board

Whole board

RankProjectBuilderFieldMerit

10TheLuxApp-Ai-ChatBotML Application · TypeScriptTheLuxApp-Ai-ChatBot is a TypeScript-based enterprise AI chatbot platform that integrates multiple LLMs (GPT-4, Claude, Azure OpenAI) with communication platforms like Discord, Slack, and Telegram, featuring multi-tenancy, RAG, and tool execution. It provides deployment guides…65.7/100AdvancedMaster MindNLP & LLMs
11EuchreGameDataset / Data Pipeline · PythonThe EuchreGame repository provides a deterministic Python Euchre engine, a browser-based sandbox for gameplay and AI interaction via Pyodide, and a data factory pipeline for generating synthetic trajectories to distill a language model into a Euchre-playing agent.63.4/100AdvancedJarad PeckenpaughNLP & LLMs
12llmastsearchAI Developer Tool · Rust62.0/100AdvancedLuiz Cesar SpiesNLP & LLMs
13sub-zeroAI Developer Tool · PythonSub-Zero is an end-to-end interpretability and steering system for LLMs that identifies and attenuates corporate/refusal directions in model weights through SVD-based probing and gradient-masked fine-tuning, accompanied by a pipeline for building a detailed Brain Atlas.61.7/100AdvancedRickNLP & LLMs
14deep-chaos-schedulerArchitecture Modification / Research · PythonThe repository introduces a sticky-topology chaos scheduler (DeepChaos) for transformer fine-tuning that removes dead and identity layers during training to improve speed and reduce VRAM usage, paired with a diagnostic suite (BoL scans) for model analysis.61.0/100AdvancedRickNLP & LLMs

What it is

Where it counts

Around it on the NLP & LLMs board

More from Luiz Cesar Spies