Code AI platform with Code Search & Cody

Home of CodeT5: Open Code LLMs for Code Understanding and Generation

The open source Sourcegraph alternative. Sourcebot gives you a powerful interface to search though all your repos and branches across multiple code hosts.

CodeTF: One-stop Transformer Library for State-of-the-art Code LLM

PySonar2: a semantic indexer for Python with interprocedual type inference

Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].

This repository provide the studies on the security of language models for code (CodeLMs).

goto.dev - Pull request superpowers

Collections of research, benchmarks and tools towards more robust and reliable language models for code; LM4Code; LM4SE; reliable LLM; LLM4Code

The semantic layer for software engineering: Connect code to meaning, build on understanding

Source code for EMSE 2023 paper "Zero-Shot Code Representation Learning via Prompt Tuning"

Official repository for "RoCode: A Dataset for Measuring Code Intelligence from Problem Definitions in 🇷🇴 Romanian 🇷🇴"

CodeT5 LLM fine-tuned with C++ code from KDE

AI-powered search capabilities for AI assistants using the Tavily API and Model Context Protocol (MCP)

A code analysis tool that generates dependency graphs from multi-language codebases, enabling AI agents to explore and understand code structure through MCP integration. Features real-time file watching, dynamic instrumentation, and security scanning.

🌈 Paper-implementations in Code Search (Baseline).

AI-powered code search MCP server using Exa API for intelligent code search and retrieval in AI assistants

Advanced Detection of Source Code Clones via an Ensemble of Unsupervised Similarity Measures

Cursor AI SSOT & Rule Engine Template: A comprehensive framework for integrating Cursor AI's advanced features into any project. Includes Single Source of Truth (SSOT) tracking, custom project rules, and Model Context Protocol (MCP) with Knowledge Graph for intelligent context management.