Search Results for "research"
Sort By:
1438 projects for "research" with 2 filters applied:
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
1
AI Berkshire
AI-era Berkshire: a value investing research framework
AI Berkshire is an AI-assisted value investing research framework designed for Claude Code and Codex workflows. It turns the investment methods of Warren Buffett, Charlie Munger, Duan Yongping, and Li Lu into structured research agents. The project is meant to improve research depth, decision discipline, and analytical consistency compared with asking a general AI model for a one-off stock opinion. -
2
RedSun
The Red Sun vulnerability repository
...By carefully manipulating this process, the exploit enables attackers to overwrite protected system files and gain SYSTEM-level privileges from a low-privilege account. The repository provides a minimal C++ implementation that showcases this behavior for research and educational purposes. It highlights flaws in endpoint protection logic and emphasizes how race conditions and file system interactions can be abused. The project is not designed as a full framework but as a focused demonstration of a real-world vulnerability. It serves as a stark example of how defensive systems can be turned into attack vectors. -
3
nature-skills
Skill that conforms to the academic expression and scientific research
nature-skills is an open-source collection of AI agent skills and structured workflows designed to enhance autonomous reasoning and tool usage in AI assistants. The project organizes reusable “skills” that agents can invoke for different operational contexts, helping AI systems perform specialized tasks more consistently and effectively. It appears to focus on modularity and interoperability, allowing skills to be combined, extended, or integrated into broader agent ecosystems. The... -
4
Copy Fail - CVE-2026-31431
epository that demonstrates and analyzes a Linux kernel vulnerability
...The repository includes tested configurations across multiple Linux distributions and kernel versions. It emphasizes reproducibility and technical clarity in demonstrating the issue. The project serves as both a research tool and an educational resource for vulnerability analysis. Overall, it contributes to the study of system-level security flaws and mitigation strategies. -
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
5
Deep Learning Essay Reading
Read classic and new deep learning papers paragraph by paragraph
Deep Learning Essay Reading repository is a comprehensive collection of machine learning and deep learning research summaries designed to make cutting-edge academic work more accessible. Instead of reading entire dense academic papers, contributors provide structured breakdowns and insights into the most influential research from the past decade, often including explanation highlights and key takeaways. The content spans foundational models, architectures, and training methodologies across computer vision, natural language processing, generative models, and other machine learning domains. ... -
6
xqvm-py
A python implementation of the Quip Network's quantum virtual machine
xq-py is a Python implementation of the Quip Network’s quantum virtual machine, offering a more accessible and flexible alternative to the Rust-based version for experimentation and rapid development. It is designed to provide similar functionality to xq-rs while prioritizing ease of use, readability, and integration with Python-based data science and research tools. The project enables developers to simulate or prototype quantum-inspired computations without needing to work at a lower systems level. It integrates into the broader Quip ecosystem, allowing interoperability with other components such as blockchain nodes and management tools. Python’s dynamic nature makes it suitable for testing new algorithms, educational purposes, and exploratory research. -
7
fvcore
Collection of common code shared among different research projects
...It provides numerics and loss layers (e.g., focal loss, smooth-L1, IoU/GIoU) implemented for speed and clarity, along with initialization helpers and normalization layers for building PyTorch models. Its common modules include timers, logging, checkpoints, registry patterns, and configuration helpers that reduce boilerplate in research code. A standout capability is FLOP and activation counting, which analyzes arbitrary PyTorch graphs to report cost by operator and by module for precise profiling. The file I/O layer (PathManager) abstracts local/remote storage so the same code can read from disks, cloud buckets, or HTTP endpoints. Because it is small, stable, and well-tested, fvcore is frequently imported by projects like Detectron2 and PyTorchVideo to avoid duplicating infrastructure and to keep research repos. -
8
Must Reading on ISAC
Must Reading Papers, Research Library, Open-Source Code
...Supported by IEEE ComSoc ISAC Emerging Technology Initiative (ETI). Integrating Sensing and Communications for Ubiquitous IoT. Include reproducible codes, good papers and a research libary. -
9
PaperSpine
Motivation-driven skill for learning from strong academic papers
...It emphasizes the central motivation of a paper, helping writers connect claims, structure, evidence, citations, and revisions into a coherent argument. The suite includes specialized skills for research, citation, rewriting, LaTeX, auditing, translation, humanization, and updates. It is best suited for users who need format-aware, evidence-aware academic writing support rather than generic text generation. -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
10
Make It heavy
A Python framework that emulates Grok Heavy functionality
Make It heavy is a Python framework for producing deeper AI analysis through multi-agent orchestration. It is designed to emulate the style of Grok Heavy by splitting a user query into several specialized research angles. The system runs four agents in parallel so each one can explore the problem from a different perspective. It then combines their outputs into one unified answer through an intelligent synthesis step. The framework uses OpenRouter for model access and can also run in single-agent mode for simpler tasks. Overall, it is useful for users who want broader research coverage, richer reasoning diversity, and structured multi-agent responses from one command-line workflow. -
11
PM Skills Marketplace
100+ agentic skills, commands, and plugins
PM Skills Marketplace is a repository designed to provide structured knowledge and guidance for product management skills, combining practical frameworks, templates, and conceptual explanations. It aims to help both aspiring and experienced product managers develop competencies across areas such as strategy, user research, prioritization, and execution. The project organizes information in a way that makes it easy to navigate different skill domains, offering actionable insights rather than purely theoretical descriptions. It emphasizes real-world application, helping users understand how to approach common product challenges and decision-making processes. ... -
12
Exclusively Dark Image Dataset
ExDARK dataset is the largest collection of low-light images
The Exclusively Dark (ExDARK) dataset is one of the largest curated collections of real-world low-light images designed to support research in computer vision tasks under challenging lighting conditions. It contains 7,363 images captured across ten different low-light scenarios, ranging from extremely dark environments to twilight. Each image is annotated with both image-level labels and object-level bounding boxes for 12 object categories, making it suitable for detection and classification tasks. ... -
13
DeltaForce-OBS-Locker
Delta Action OBS Lock Plugin
DeltaForce-OBS-Locker is a research-oriented repository around OBS-based computer vision experiments for the game Delta Force. The project includes desktop and mobile components and discusses image recognition, rendering capture, simulated input, and real-time detection ideas. Its README states that a YOLOv14-based real-time object detection framework was integrated into the desktop side for visual recognition experiments. -
14
Agent Executor (AX)
Google's open source distributed agent runtime
Agent Executor (AX) is a Google research project for learning discrete choice models through differentiable maximum likelihood estimation. It is designed for situations where a model needs to predict choices from a finite set of alternatives, such as ranking, recommendation, preference modeling, or decision behavior analysis. The project provides JAX-based tools for defining and training choice models with automatic differentiation. -
15
Anomalib
An anomaly detection library comprising state-of-the-art algorithms
...Its design supports unsupervised or semi-supervised paradigms, making it especially powerful for scenarios where only “normal” data is readily available and defects must be detected without exhaustive labeling. Combined with its CLI and integration with optimization tools like OpenVINO, it’s suitable for both research and edge deployment tasks. -
16
VGGT-Ω
[CVPR 2026 Oral] VGGT Omega
VGGT-Omega is a Facebook Research computer vision project for feed-forward camera and depth reconstruction. It takes images as input and predicts camera parameters, depth maps, confidence values, and related scene tokens. The project is associated with 3D understanding workflows where models infer scene geometry without a traditional multi-stage reconstruction pipeline. -
17
GPTs
Leaked prompts of GPTs
...Because the project involves prompts described as leaked or contributed from multiple sources, users should approach it carefully and avoid reusing anything that may be private, proprietary, or unauthorized. Its main value is as a research reference for understanding prompt design patterns in real assistant configurations. -
18
Tunix
A JAX-native LLM Post-Training Library
...Examples and reference configs demonstrate end-to-end runs for common model families, helping teams reproduce baselines before customizing. Tunix also leans into research ergonomics: logging, checkpointing, and metrics are built in, and the code is written to be hackable rather than monolithic. Overall it aims to shorten the path from an off-the-shelf base model to a well-aligned, task-ready model using scalable JAX primitives. -
19
Tailslayer
Library for reducing tail latency in RAM reads
...The tool helps investigators identify residual data such as logs, configurations, or usage traces that may persist despite Tails’ security features. It is particularly relevant for digital forensics and research into privacy systems. Tailslayer emphasizes practical analysis techniques rather than theoretical exploration. Its design reflects the need to balance privacy with investigative capabilities. Overall, it provides insight into how secure systems behave under forensic scrutiny. -
20
LangExtract
A Python library for extracting structured information
LangExtract is a Python library developed by Google that leverages large language models (LLMs) to extract structured information from unstructured text—such as clinical notes, research papers, or literary works—based on user-defined instructions. It is designed to transform free-form text into reliable, schema-constrained data while maintaining traceability back to the source material. Each extracted entity is precisely grounded in its original context, allowing visual inspection and validation via automatically generated interactive HTML visualizations. ... -
21
Kodus
AI code reviews, just like your senior dev would do
...It provides a structured set of tools and abstractions that help teams design agent behaviors, orchestrate data pipelines, optimize inference, and integrate AI capabilities with applications or services. The platform often includes model management, scalable training workflows, and orchestration patterns that help teams move from research or prototypes to production-ready AI deployments. Through configurable pipelines and a focus on modularity, it supports experimentation while maintaining reproducibility and performance. Its tooling is typically designed to handle real-world imperatives like logging, monitoring, versioning, and hooking into operational infrastructure. -
22
cuda-oxide
cuda-oxide is an experimental Rust-to-CUDA compiler
...It supports a single-source programming style where host and device code can live together and be built through Cargo-oriented tooling. cuda-oxide is still experimental, so it is best suited for research, early exploration, and developers interested in Rust-based GPU programming. Its main value is giving Rust developers a more direct path into NVIDIA GPU kernels while preserving familiar Rust syntax and tooling concepts. -
23
How-To-Ask-Questions-The-Smart-Way
Correctly propose technical questions and get the answers you want
...It focuses on improving the quality of questions by emphasizing clarity, context, and effort before asking for assistance. The document explains common mistakes, such as vague descriptions or lack of research, and provides strategies for formulating precise and useful questions. It also highlights the importance of respecting the time and expertise of others, encouraging a culture of constructive collaboration. The guide is particularly valuable for beginners who are learning how to interact in open-source communities and forums. By improving communication, it increases the likelihood of receiving helpful and accurate responses. ... -
24
redshirt
Operating system
...It includes components for task scheduling, device interaction, and system services, all implemented in a highly modular fashion. The project is still experimental but serves as a research platform for exploring how WebAssembly can be used as a foundation for operating systems. -
25
scalar_objects
Extension that adds support for method calls on primitive types in PHP
...It allows API ideas to be prototyped in userland before any proposal for deeper language integration. Overall, it is most useful for PHP language experimentation, API design research, and exploring how object-style operations on scalar values could work.
