Repositories list

• ResearchKit

  Public

  FSoft-AI4Code/ResearchKit’s past year of commit activity
  ResearchKit is an AI-assisted research writing environment built on top of Overleaf Community Edition. It treats Overleaf as the IDE and the LaTeX paper project…

  JavaScript

  •

  GNU Affero General Public License v3.0

  •00 forks•11 star•00 issues•00 pull requests•Updated Apr 8, 2026Apr 8, 2026

• CodeWiki

  Public

  FSoft-AI4Code/CodeWiki’s past year of commit activity
  [ACL 2026] Open-source framework for holistic, structured repository-level documentation across multilingual codebases

  documentation-generatorcode-documentationautomated-documentation+ 3

  documentation-generatorcode-documentationautomated-documentationcode-understandingrepository-documentationopen-source-deepwiki

  Python

  •136136 forks•884884 stars•33 issues•11 pull request•Updated Apr 4, 2026Apr 4, 2026

• SafetyCode

  Public

  FSoft-AI4Code/SafetyCode’s past year of commit activity
  Python

  •

  Apache License 2.0

  •00 forks•00 stars•00 issues•00 pull requests•Updated Feb 9, 2026Feb 9, 2026

• TestWeaver

  Public

  FSoft-AI4Code/TestWeaver’s past year of commit activity
  [ICSE 2026] TestWeaver: Execution-aware, Feedback-driven Regression Testing Generation with Large Language Models

  automated-test-generationai4selarge-language-models

  automated-test-generationai4selarge-language-models

  Python

  •

  Apache License 2.0

  •11 fork•22 stars•00 issues•00 pull requests•Updated Jan 11, 2026Jan 11, 2026

• RepoExec

  Public
  [NAACL 2025] Benchmark for Repository-Level Code Generation, focus on Executability, Correctness from Test Cases and Usage of Contexts from Cross-file Dependenc…

  Python

  •

  MIT License

  •44 forks•4444 stars•22 issues•00 pull requests•Updated Jan 8, 2026Jan 8, 2026

• Mainframe-Studio

  Public

  FSoft-AI4Code/Mainframe-Studio’s past year of commit activity
  Python

  •11 fork•55 stars•00 issues•00 pull requests•Updated Dec 6, 2025Dec 6, 2025

• CodeWikiBench

  Public

  FSoft-AI4Code/CodeWikiBench’s past year of commit activity
  Comprehensive Benchmarking System for CodeWiki

  Python

  •66 forks•1212 stars•00 issues•00 pull requests•Updated Nov 23, 2025Nov 23, 2025

• codewiki-demo

  Public

  FSoft-AI4Code/codewiki-demo’s past year of commit activity
  HTML

  •00 forks•33 stars•00 issues•00 pull requests•Updated Nov 10, 2025Nov 10, 2025

• Visual-Reasonser

  Public

  FSoft-AI4Code/Visual-Reasonser’s past year of commit activity
  Python

  •

  Apache License 2.0

  •00 forks•11 star•00 issues•00 pull requests•Updated Aug 9, 2025Aug 9, 2025

• UniGraph

  Public
  Python

  •00 forks•44 stars•00 issues•00 pull requests•Updated Jul 25, 2025Jul 25, 2025

• SFT-Infra

  Public
  Supervised Fine-tuning Infra for Software Research

  Python

  •

  Apache License 2.0

  •00 forks•11 star•00 issues•00 pull requests•Updated May 3, 2025May 3, 2025

• SWE-Synth

  Public
  [ICSE 2026] [ACM SIGSOFT Distinguished Paper Award] SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs

  ai4codesynthetic-bug-dataset

  ai4codesynthetic-bug-dataset

  Python

  •11 fork•1818 stars•00 issues•00 pull requests•Updated Apr 22, 2025Apr 22, 2025

• fsoft-ai4code.github.io

  Public
  JavaScript

  •00 forks•00 stars•00 issues•00 pull requests•Updated Apr 21, 2025Apr 21, 2025

• CodeMMLU

  Public
  [ICLR 2025] 🚀 CodeMMLU Evaluator: A framework for evaluating LM models on CodeMMLU MCQs benchmark.

  Python

  •

  MIT License

  •33 forks•2929 stars•33 issues•00 pull requests•Updated Apr 21, 2025Apr 21, 2025

• mcphub

  Public
  MCPHub is an embeddable Model Context Protocol (MCP) solution for AI services. Seamlessly integrate MCP servers with OpenAI Agents, LangChain, and Autogen frame…

  Python

  •1111 forks•22 stars•00 issues•00 pull requests•Updated Apr 14, 2025Apr 14, 2025

• DP-parser

  Public
  Dependecy graph parser

  Python

  •

  MIT License

  •00 forks•33 stars•11 issue•00 pull requests•Updated Apr 1, 2025Apr 1, 2025

• VisualCoder

  Public
  [NAACL 2025] Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning

  cfgai4codevlms

  cfgai4codevlms

  Jupyter Notebook

  •22 forks•1212 stars•00 issues•00 pull requests•Updated Feb 9, 2025Feb 9, 2025

• HyperAgent

  Public
  Generalist Software Agents to Solve Soware Engineering Tasks

  repositorymulti-agentcode-generation+ 5

  repositorymulti-agentcode-generationcoding-assistantcode-understandingrepo-levelcodellmcodellms

  Python

  •

  Apache License 2.0

  •2323 forks•241241 stars•33 issues•88 pull requests•Updated Dec 10, 2024Dec 10, 2024

• AgileCoder

  Public
  [FORGE 2025] Incorporating Agile methodology into agents to create complex real-world softwares

  agilesoftwarecode-generation+ 8

  agilesoftwarecode-generationagile-developmentmulti-agentsagile-methodologiescode-graphmetagptchatdevcodellms+ 1

  Python

  •

  MIT License

  •5858 forks•456456 stars•1010 issues•00 pull requests•Updated Oct 15, 2024Oct 15, 2024

• codevista_readme

  Public
  00 forks•00 stars•00 issues•00 pull requests•Updated Sep 25, 2024Sep 25, 2024

• RepoHyper

  Public
  [FORGE 2025] Graph-based method for end-to-end code completion with context awareness on repository

  Jupyter Notebook

  •

  Apache License 2.0

  •1313 forks•7272 stars•33 issues•00 pull requests•Updated Sep 3, 2024Sep 3, 2024

• XMainframe

  Public
  Language Model for Mainframe Modernization

  migrationcobolmainframe+ 3

  migrationcobolmainframecode-summarizationcodellmllms-benchmarking

  Python

  •

  Apache License 2.0

  •1212 forks•7171 stars•33 issues•00 pull requests•Updated Aug 23, 2024Aug 23, 2024

• TheVault

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

  datasetmultilingual-nlpai4code

  datasetmultilingual-nlpai4code

  Jupyter Notebook

  •

  MIT License

  •1010 forks•105105 stars•00 issues•00 pull requests•Updated Aug 21, 2024Aug 21, 2024

• CodeFlow

  Public
  [FORGE 2025] Predicting Program Behavior with Dynamic Dependencies Learning

  cfggnnai4code

  cfggnnai4code

  Python

  •22 forks•2929 stars•00 issues•00 pull requests•Updated Aug 15, 2024Aug 15, 2024

• pydep

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

  Python

  •

  MIT License

  •11 fork•1313 stars•22 issues•00 pull requests•Updated Aug 7, 2024Aug 7, 2024

• CodeText-parser

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

  tree-sitterparser

  tree-sitterparser

  Python

  •

  MIT License

  •55 forks•5151 stars•00 issues•00 pull requests•Updated Jul 1, 2024Jul 1, 2024

• SRank-CodeRanker

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

  Python

  •11 fork•1616 stars•00 issues•00 pull requests•Updated Jun 9, 2024Jun 9, 2024

• code-llm-evaluator

  Public
  🏎️ Fast Code LLMs evaluator

  Python

  •

  MIT License

  •11 fork•33 stars•00 issues•00 pull requests•Updated May 14, 2024May 14, 2024

• Dopamin

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

  Python

  •

  Apache License 2.0

  •00 forks•88 stars•00 issues•00 pull requests•Updated May 13, 2024May 13, 2024

• HierarchyNet

  Public
  Python

  •00 forks•77 stars•11 issue•00 pull requests•Updated Feb 17, 2024Feb 17, 2024