Highlights
Stars
Amazon EC2 instance comparison site
TDD-Bench-Verified is a new benchmark for generating test cases for test-driven development (TDD)
Automated Projects Installation and Testing with LLM Agents
Local Message Generator (OMEGA): An LLM-based commit message generator that can use a quantized open-source LLM to produce high-quality commit messages.
A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award)
Replication package of the ICSE2025 paper titled "Leveraging Large Language Models for Enhancing the Understandability of Generated Unit Tests"
Let your Claude able to think
RAG that intelligently adapts to your use case, data, and queries
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
Create, customize, and manage SWE-Bench containers
LSP server leveraging LLMs for code completion (and more?)
Autonomous Agents (LLMs) research papers. Updated Daily.
Codebase of the MSc thesis by Vera Kowalczuk "Large Language Model-based Code Translation between Programming Languages"
[NeurIPS 2024] Evaluation harness for SWT-Bench, a benchmark for evaluating LLM repository-level test-generation
Generate automated tests for your Node.js app via LLMs without developers having to write a single line of code.
RepairAgent is an autonomous LLM-based agent for software repair.
[Archived] We are seeking to support the most ambitious and innovative ideas to systemically improve the sustainability of the OSS ecosystem. Submit your idea or view other ideas here.
A continuously updated collection of CodeLLM papers
Graph-based method for end-to-end code completion with context awareness on repository
A Database of Real Faults and an Experimental Infrastructure to Enable Controlled Experiments in Software Engineering Research
Helping Ethical Hackers use LLMs in 50 Lines of Code or less..