gokhanercan/gen-atomic
An LLM-based code generation framework aims to support a wide range of atomic language units, from compiled code to semi-structured markups.
This tool helps software developers quickly generate and evaluate various code snippets, from C# and Python to SQL and Regex, using large language models. Developers provide a description of the code needed along with examples of correct and incorrect outputs, and the system generates the code, optionally evaluating its performance across different LLM configurations. It's designed for software developers who need to generate accurate code for diverse programming languages and formats.
No commits in the last 6 months.
Use this if you are a software developer who needs to rapidly generate and validate code or semi-structured markups like YAML using large language models, especially if you want to compare different model performances.
Not ideal if you are a non-technical user looking for a no-code solution, or if you are an academic interested in the theoretical underpinnings of LLM concepts rather than practical code generation.
Stars
7
Forks
—
Language
Python
License
—
Category
Last pushed
Oct 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/gokhanercan/gen-atomic"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
k4black/codebleu
Pip compatible CodeBLEU metric implementation available for linux/macos/win
LiveCodeBench/LiveCodeBench
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of...
EdinburghNLP/code-docstring-corpus
Preprocessed Python functions and docstrings for automated code documentation (code2doc) and...
hendrycks/apps
APPS: Automated Programming Progress Standard (NeurIPS 2021)
solis-team/Hydra
[FSE 2026] Do Not Treat Code as Natural Language: Implications for Repository-Level Code...