Language Model for Mainframe Modernization

Transformer-based approaches for an efficient docstrings generation on a piece of Python's code.

Official implementation of our work, 'GypSum: Learning Hybrid Representations for Code Summarization'.

Summarize and collect into a DB a collection of LeetCode problems (Description, Solutions, Code, Analysis)

Code and data for "Impact of Evaluation Methodologies on Code Summarization" in ACL 2022.

[ICLR 2024] Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain

A tool for obtaining natural language summaries of Python functions.

CLAMS API Summarizer

A CLI tool to transform a codebase into a single, LLM-optimized markdown file. Intelligently samples content, removes duplicates, and controls token budgets to create perfect context for AI assistants

📝 Counts how many lines of code (LOC/SLOC) are in a code base, by programming language.

Snapshot an entire repo or directory as plaintext on the clipboard and paste to your favorite AI tool!

A new package that analyzes technical arguments and extracts structured summaries from text discussions about infrastructure-as-code practices. It takes user-provided text (such as forum posts, articl

Automatically summarizes Python code and emails daily progress reports to your manager. Perfect for remote teams, daily standups, and solo developers.

MoLE (Mix-of-Language-Experts) model architecture for multilingual programming

A toolkit to naturalize the source code corpus

CLI tool in Python to recursively scan a directory, read every file (with error handling), and generate a single Markdown-formatted summary file. Supports path normalization, progress logging, and customizable output filenames—ideal for quick code overviews or project documentation.

Fine-tuning Qwen2.5-Coder-0.5B LLM using QLoRA (4-bit quantization + LoRA) to generate clear, concise commit messages from Git diffs by learning to summarize code changes into human-like descriptions.

Local AI workbench for embeddings, summarization, and OpenAI Agent SDK–compatible workflows. Supports Gemma models, GPT-OSS tool-calling, hardware acceleration, caching, and rate limiting, plus cloud-offloaded, persona-driven summarization through Gemini.

A novel approach to get concise comments for a code snippet