FSoft AI4Code

CodeCapybara

Open-source Self-Instruction Tuning Code LLM

RepoPilot

Repo-Level Coding Assistant that Can Understand Your Whole Codebase

TheVault

[EMNLP 2023] The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation

AgileCoder

Dynamic Collaborative Agents for Software Development

RepoHyper

Graph-based method for end-to-end code completion with context awareness on repository

CodeText-parser

⚒️ Tree-sitter custom toolkit for extracting function and class from raw source file

RepoExec

Benchmark for Repository-Level Code Generation, focus on Executability, Correctness from Test Cases and Usage of Contexts from Cross-file Dependencies

DocChecker

DocChecker: Bootstrapping Code-Text Pretrained Language Model to Detect Inconsistency Between Code and Comment

SRank-CodeRanker

[ACL 2024] Novel reranking method to select the best solutions for code generation

VarWizard

VarWizard: Better Code Quality Through Variable Name Refinement.

Dopamin

[NLBSE 2024] Dopamin: Transformer-based Comment Classifiers through Domain Post-training and Multi-level layer aggregation (Best Tool Award)

HierarchyNet

code-llm-evaluator

🏎️ Fast Code LLMs evaluator

pydepcall

Dependency call extraction tool for Python modules (function, class, import statement)

ChatDev

Create Customized Software using Natural Language Idea (through Multi-Agent Collaboration)

fsoft-ai4code.github.io

langchain

⚡ Building applications with LLMs through composability ⚡