State of AI Testing

SGLang is a high-performance serving framework for large language models and multimodal models.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

A project to improve skills of large language models

The RAS-Commander library provides a python API for automating HEC-RAS 6.x and accessing HDF data using Python, built with and driven by large language models.

NewsPilot is an automated intelligence analysis system based on Large Language Models (LLM), designed to transform massive global news into personalized, actionable insights. It is not just a news aggregation tool, but a 24/7 intelligent intelligence assistant that understands your profession, holdings, and interests.

AI system powered by large language models.

A unified Python library for interaction with multiple Large Language Model (LLM) providers. Write once, run everywhere.

🔍 Automate penetration testing with an intelligent agent that organizes security assessments, leveraging local LLMs and Kali Linux for effective exploitation.

Recipe Language Model (RLM): We introduce a domain-specific RLM developed through seven AI layers and interconnected robotic boxes to drive the evolution of physical AI for defining a new paradigm - Materials Intelligence.

Experiments in building Small/Medium/Large Language Models using JAX

Auto-GPT is an experimental open-source framework that transforms large language models like GPT into autonomous agents capable of self-directed reasoning, recursive goal execution, and dynamic tool use. Unlike traditional chat interfaces

This repository powers the “How Hungry is AI?” dashboard and provides the code + data release accompanying our paper on inference-phase (operational) environmental footprints of LLMs.

Daily automated tracking of 19 AI agent frameworks. Pulse Score ranks momentum via star velocity, release freshness, commit activity, and community health.

Persistent, LLM-maintained 3-level documentation for codebases. AST-driven line numbers, doc-only or edit-enabled doc passes, project-config'd cascade and verification. (Haven't taught the agent how to read the doc, will be included in v1.1 release)

MCP server to search across NVIDIA blogs and releases to empower LLMs to better answer NVIDIA specific queries

This project is to use python and Structured Query Language with some known exiting store data to predict if someone wanted to start a new store in the same area, how likely the new store would be visited. Using Huff Model.

Real-Time Fake News Detection offers an API-first approach to content moderation and journalistic verification. Powered by advanced Natural Language Processing (NLP) and ensemble tree models, this platform analyzes structure, sentiment, and context to deliver actionable credibility metrics.

[arxiv: 2603.11331] Scaling laws for the attack success rate under prompt-injection-based jailbreak attacks

Benchmarking the true internal knowledge cutoff dates and factual decay of Large Language Models (LLMs) using notable death records.

Chat With Documents is a Streamlit application designed to facilitate interactive, context-aware conversations with large language models (LLMs) by leveraging Retrieval-Augmented Generation (RAG). Users can upload documents or provide URLs, and the app indexes the content using a vector store called Chroma to supply relevant context during chats.

SGLang is a high-performance serving framework for large language models and multimodal models.

Accessible large language models via k-bit quantization for PyTorch.

Inspect: A framework for large language model evaluations

JiuwenClaw is an intelligent AI Agent built on openJiuwen. It extends the powerful capabilities of large language models directly to your fingertips through various communication apps you use daily.

[CVPR 2026] Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"

Official release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks

INFRA-COMPASS is a tool that leverages Large Language Models (LLMs) to create and maintain an inventory of state and local codes and ordinances applicable to energy infrastructure.

Code for "FORGETTING: A New Mechanism Towards Better Large Language Model Fine-Tuning" paper. Novel approach for LLM fine-tuning using token-level forgetting mechanism.

A Model Context Protocol (MCP) application for automated GitHub PR analysis and issue management. Enables LLMs to fetch PR details, analyse diffs, manage issues, and handle releases through a standardised interface

A structured end-to-end AI/ML engineering journey covering mathematics, machine learning, deep learning, large language models, MLOps, and production-grade projects. Built with a strong focus on fundamentals, implementation, and real-world systems.

🗣️ Build an interactive voice agent that leverages Speech-to-Text, a Large Language Model, and Text-to-Speech for real-time voice interactions.

synapz is a research prototype exploring how large language models can adapt teaching content to different cognitive styles. built over a 48-hour sprint with a strict $50 api budget, this project implements a scientific framework to test whether adaptive teaching produces measurably better results than static approaches.

Continual pretrainig experiments with large language models

AgentDeck is a research platform for studying AI behavior through game scenarios. Run controlled experiments with LLMs, collect comprehensive behavioral data, and replay matches for analysis. 🚧 Preview release - feedback welcome.

🔍 Automate penetration testing with an intelligent agent that organizes security assessments, leveraging local LLMs and Kali Linux for effective exploitation.

An end-to-end AI drug repurposing system based on knowledge graphs + large language models. Supported by CrewAI multi-agent collaboration, it quickly and efficiently identifies new indications for existing drugs.

🖥️ Execute Python commands with AIPy, unlocking the potential of large language models to solve complex problems seamlessly.

intelligent auditing tool powered by large language models, supporting GPT, . It automatically detects security vulnerabilities, performance issues

Local-first workspace for using large language models in a practical, understandable way. It makes reasoning, memory, tools, and workflows visible and reusable, so you can save thinking once, keep control of your data, and move on.

Benchmarking the ability of large language models to detect semantic conflicts across domains, documents, and evolving knowledge bases.

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"

We want to see whether ChatGPT or other AI-LLM (Microsoft New_Bing or Google Bard) are able to help the user to go to some test environment to run cmds to solve the CTF problems (Whether the AI large language models can understand the challenge question and capture the question flags)

A list of recent adversarial attack and defense papers (including those on large language models)

Self-Evolving RAG System with ChromaDB for continuous knowledge updates (6x daily), designed to overcome Large Language Model data cutoff limitations.

GitHub Action that uses LLM to analyze commits, suggest semantic version bumps, and generate multi-audience changelogs

A Model Context Protocol (MCP) application for automated GitHub PR analysis and issue management. Enables LLMs to fetch PR details, analyse diffs, manage issues, and handle releases through a standardised interface

Real-time LLM delay & quality comparison tool built on FastAPI + SSE, tailored for Azure OpenAI. Modular architecture, unified responses/exceptions, env-based config, docs, and automation scripts ready for production release

Set Supervised Fine-Tuning (SSFT): Training Large Language Models To Reason In Parallel With Global Forking Tokens (ICLR2026).

A desktop tool for inspecting and modifying ComfyUI workflows using LLMs.

This repository provides a comprehensive vLLM benchmarking framework for testing large language model performance and fairness across multiple scheduling strategies (ExFairS, VTC, FCFS, Queue-based) with built-in engine management, multi-experiment batch execution, and advanced plotting capabilities.

SEDAC is a next-generation framework that dynamically allocates computation during LLM inference. By using entropy-based gating, it routes predictable tokens through shallow subnetworks and sends ambiguous or high-impact tokens to deeper, specialized paths.

AgentDeck is a research platform for studying AI behavior through game scenarios. Run controlled experiments with LLMs, collect comprehensive behavioral data, and replay matches for analysis. 🚧 Preview release - feedback welcome.

This dataset is the first release from DLTHA Labs, focused on enhancing the logical reasoning and step-by-step problem-solving capabilities of Large Language Models (LLMs).

MCP server to search across NVIDIA blogs and releases to empower LLMs to better answer NVIDIA specific queries

🚀 Universal AI-Powered CAD & CFD Platform | Democratizing 3D Design & Simulation | Natural Language → Parametric Models | Build123d + Zoo.dev + Adam.new + OpenFOAM | Solar PV, Test Chambers, Digital Twins & More

Creating a large language model

🔍 Extract structured academic metadata from research abstracts using multiple Large Language Models and assess their performance effectively.

intelligent auditing tool powered by large language models, supporting GPT, . It automatically detects security vulnerabilities, performance issues

🔒 Enable secure Large Language Model inference with differential privacy for sensitive data protection using DP-Fusion-Lib.