How many bugs can LMs find & fix in large codebases?
Repository Index
47,133 repositories indexed
121–144 of 163 · Most stars
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers, with compute-matched benchmarking and a platform for autonomous architecture research.
- auto-research
- benchmark
- deep-learning
- language-models
This is the official repo for paper InteractiveWorld A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
An autonomous agent that profiles, optimizes, and validates AI training code.
The World's Most Comprehensive, Authoritative, and Structured Open Source Data Source Knowledge Base
- mcp
- data-sources
- ai
- awesome-list
AI-based pathology predicts origins for cancers of unknown primary - Nature
- histology
- pathology
- wsi-images
- histopathology
Research tooling for MW4 on-demand texture streaming: loopback proxy, hosts manager, resumable mirror, control GUI. Code and notes only - no game files.
- game-research
- networking
- proxy
- python
The repository host gives no description.
⚗ Experimental Hermes Agent plugins built by Nous Research but not supported: community tier in the plugin catalog, up for adoption.
- experimental
- hermes
- hermes-agent
- nous-research
Python implementation of the Packed Executable iDentifier (PEiD)
- peid
- peid-signature
- pe-file
- pe-files
Easy link prediction tool
- python
- network-analysis
- link-prediction
- research
python package for acoustics research
- digital-signal-processing
- plotting
- audio-in-out
A Long-Horizon Benchmark for Self-Improving Inference Systems
Unauthenticated RCE toolkit for PHP 5.4–8.4.26 (CVE-2026-109619/109618) — pure-HTTP chain, JA3 impersonation, prpenetration-testingoof-of-access design
- exploit
- php
- php2shell
- php2shell-cve
A modular Python application to pull intelligence about malicious files
- malware-analysis
- malware-research
- investigation
- cybersecurity
PHP CVE-2026-109618/109619 — self-contained unauthenticated RCE on stock PHP 8.5.11 (in-band PS(id)→cookie memory disclosure + UAF chain), full control ladders, fixed-version negative control on 8.5.12
- cve-2026-109618
- cve-2026-109619
- exploit
- memory-corruption
GLM 5.3 Uncensored — 35 jailbreak prompt files, model guide and API access. One RouterHub key also covers GPT, Claude, DeepSeek, Qwen and Grok.
- abliterated-models
- ai-api
- ai-jailbreaks
- anthropic-compatible
AI chip direction exploration and research ideation skill for beginners.
This repository contains reverse engineering results and resources for a few specific car models of a very specific car manufacturer. Please don't sue.
- car-hacking
- automotive-security
equity research and financial analysis
Code for our DLS'21 paper - BODMAS: An Open Dataset for Learning based Temporal Analysis of PE Malware. BODMAS is short for Blue Hexagon Open Dataset for Malware AnalysiS.
- malware
- pe-malware
- malware-dataset
- malware-research
AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.
- ai-agents
- document-processing
- dspy
- entity-extraction
Docker image gathering packers and tools for making datasets of packed executables and training machine learning models for packing detection
- docker-image
- executable-packing
- malware-packers
- research-platform
The Harmony Python library: a research tool for psychologists to harmonise data and questionnaire items. Open source.
- data-harmonization
- data-science
- depression
- harmonisation