Starred repositories
📑 PageIndex: Document Index for Reasoning-based RAG
not another coding agent, kode is agent cli for everything
Lightweight static analysis for many languages. Find bug variants with patterns that look like source code.
⚡A CLI tool for code structural search, lint and rewriting. Written in Rust
An analysis tool for Python that blurs the line between testing and type systems.
A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.
Firmrec is a recurring vulnerability detector for embedded firmware.
Sys: A Static/Symbolic Tool for Finding Good Bugs in Good (Browser) Code
[USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection
A framework to test the correctness of the Linux kernel patch.
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to…
An overview of LLMs for cybersecurity.
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…
NaturalCC: An Open-Source Toolkit for Code Intelligence
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
A framework for the evaluation of autoregressive code generation language models.
The definitive Web UI for local AI, with powerful features and easy setup.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights i…
Auto-generated CodeQL rules for matching CVE vulnerabilities and variants.
Set of tools to assess and improve LLM security.
This repository is the replication package of the ICSE23 paper "Revisiting Learning-based Commit Message Generation"
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM
Universal and Transferable Attacks on Aligned Language Models