Search Results for "research" - Page 26
Sort By:
Showing 15058 open source projects for "research"
View related business solutions-
Paessler: Easy to Use With Enterprise Power. Free TrialYou shouldn't have to choose between a monitoring tool that's easy to use and one that's powerful enough for a complex environment. PRTG's low-code interface lets any admin build dashboards, set alerts and monitor devices without scripting, while custom sensors and full API access are there when your team needs deeper control. One platform, no compromise. Download a free 30-day trial now.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
PilotDeck
Task-oriented AI Agent productivity platform
PilotDeck is an open-source agent operating system built around the idea of a task-oriented WorkSpace. It is designed to help users manage multi-task AI agent work from a structured productivity environment. The project is jointly developed by Tsinghua University THUNLP, ModelBest, OpenBMB, and AI9Stars. Its goal is to serve as a practical productivity platform for the agent era rather than a simple chat interface. PilotDeck organizes agent activities around work contexts, tasks, and... -
2
OpenGNB
GNB is open source de-centralized SDVN to achieve layer3 network
...Built using SDR (Software Defined Radio) principles, it allows researchers, developers, and enthusiasts to deploy and experiment with 5G RAN technology using commodity hardware. OpenGNB integrates with open-core networks and provides a valuable tool for advancing innovation in private 5G networks, research labs, and rural communication deployments. -
3
Adapters
A Unified Library for Parameter-Efficient Learning
...Q-LoRA, Q-Bottleneck Adapters, or Q-PrefixTuning), adapter merging via task arithmetics or the composition of multiple adapters via composition blocks, allowing advanced research in parameter-efficient transfer learning for NLP tasks. -
4
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. -
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
5
Olmo-core
PyTorch building blocks for the OLMo ecosystem
...Direct autoregressive generation is also available for experimentation and chat-style inference. The project is Apache-2.0 licensed and designed for transparent, reproducible LLM research. -
6
TileLang
Domain-specific language designed to streamline the development
...The project includes autotuning, debugging tools, layout visualization, compiler diagnostics, and an LSP for editor assistance. Kernels can be integrated with PyTorch and compiled for several modern accelerator families. TileLang aims to combine research-friendly productivity with performance close to specialized hand-tuned kernels. -
7
MSA: Memory Sparse Attention
Trainable latent-memory framework for 100M-token contexts
MSA, or Memory Sparse Attention, is a research framework for scaling language-model memory to extremely long contexts. It replaces full attention over all tokens with sparse selection of compressed latent memory states. Document-wise rotary position encoding and top-k routing keep training and inference close to linear complexity. A tiered KV-cache design stores routing keys on GPU while larger content states can remain on CPU. -
8
pi-subagents
Pi extension for async subagent delegation with truncation
pi-subagents is an extension for the Pi coding agent that lets a parent session delegate focused work to independent child agents. Built-in specialists handle tasks such as codebase scouting, external research, planning, implementation, review, context gathering, and second-opinion analysis. Child sessions can run in the foreground with streamed results or continue asynchronously as background jobs. Agents can be composed into sequential chains, parallel groups, reusable workflows, and more durable missions. Custom agent definitions control prompts, models, tools, skills, context inheritance, permissions, timeouts, and output behavior through Markdown frontmatter. ... -
9
bilibili-API-collect
Community-maintained documentation project
bilibili-API-collect was a community-maintained documentation project that cataloged Bilibili interfaces used by its web, mobile, and TV clients. It researched undocumented endpoints through techniques such as black-box testing, traffic inspection, application analysis, and controlled experimentation. The documentation covered REST, gRPC, and WebSocket interfaces along with request structures, response formats, authentication concepts, errors, and platform-specific behavior. Major sections... -
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
Advanced Search Operators List
List of the links to the docs for different services
...The repository also catalogs browser extensions and tools that help users construct advanced queries. It is intended to make precise information retrieval easier across platforms with very different search languages. The collection functions as a research reference rather than an executable search tool. -
11
WooYun Legacy
wooyun-legacy skill for claude code
...The repository organizes information into methodology references, technical knowledge, vulnerability categories, examples, and evaluation data. A lightweight installation provides condensed indexes, while the full repository exposes the complete case collection for deeper research. It is intended for authorized testing, risk analysis, code review, and defensive security work. The maintainers have stated that the project is no longer actively maintained. -
12
NeMo Automodel
Pytorch Distributed native training library for LLMs/VLMs
...The library supports composable parallelism, optimized kernels, MoE acceleration, mixed precision, sequence packing, and asynchronous checkpointing. Jobs can run through interactive environments, Slurm, SkyPilot, or Kubernetes-based workflows. It targets both rapid research experiments and high-performance large-scale fine-tuning. -
13
HTML5 Security Cheatsheet
A collection of HTML5 related XSS attack vectors
...Redirect utilities cover several URI schemes and HTTP status codes used during security experiments. The material is published through the html5sec interface for easier browsing. It is intended for authorized testing, defensive research, and the validation of sanitizers and browser protections. -
14
DISCORD.js-selfbot
An unofficial discord.js fork for creating selfbots
...Because automating Discord user accounts violates Discord’s Terms of Service and can lead to account penalties, this project should be treated as a risky proof-of-concept or research library. It is not appropriate for compliant production bot development. -
15
DeepSpec
A full-stack codebase for training and evaluating speculative decoding
DeepSpec is a full-stack codebase for training and evaluating draft models used in speculative decoding. It provides the components needed to prepare data, train draft models, and measure acceptance behavior against target models. The workflow starts with data preparation, including prompt download, target answer regeneration, and target cache construction. It then trains a draft model using configuration files for different algorithms and target model setups. The evaluation pipeline... -
16
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. -
17
Popcorn
Running Elixir in the browser
...It is intended for developers who want to explore client-side Elixir workflows without relying entirely on server-side execution. The project is still early and may introduce breaking changes, so it is best suited for experimentation, prototypes, and research rather than stable production use. Popcorn connects Elixir’s programming model with browser-based execution, opening the door for local interactive experiences and future LiveView-style ideas. It is useful for developers interested in WebAssembly, local-first interfaces, and alternative ways to build browser applications. Its main value is exploring what Elixir development can look like when part of the application logic runs directly on the client. -
18
invisible_playwright
Anti-Detect Browser that passes every bot detection test
...It includes claims about passing common browser-fingerprint and bot-detection checks, which makes it technically notable but also sensitive in how it should be used. Responsible use should be limited to authorized testing, internal automation, QA, and research environments. It is best understood as a specialized automation compatibility layer for developers who need Playwright-like control with stronger stealth characteristics. -
19
forkd
Fork() for AI agent microVMs
...Instead of cold-booting a separate virtual machine for every worker, it forks children from a warmed parent snapshot and uses copy-on-write behavior to share the initial memory state. This makes it useful for spawning many isolated agent environments quickly during parallel research, testing, or code execution. The project is focused on runtime performance, sandbox isolation, and efficient branching from a live or prepared VM state. It is especially relevant for developers building agent infrastructure where many short-lived execution branches need to run safely. forkd is best understood as a low-level systems tool for scalable, isolated AI-agent workloads. -
20
programmer-job-blacklist
Programmer job search blacklist, be careful when changing jobs
...It primarily focuses on the Chinese technology sector but has gained broader recognition as an example of community-driven labor awareness in software engineering. The repository organizes reports, discussions, and references in a structured format that allows developers to research employers before accepting positions. Its existence reflects growing concern within the software industry regarding burnout, labor exploitation, and workplace accountability. -
21
discrawl
cli for Discord with sqlite backend
discrawl is a command-line and database-driven tool for archiving, syncing, and searching Discord server content locally using a SQLite backend. The project allows users to mirror Discord conversations and metadata into a searchable offline database, making it useful for analytics, moderation, research, and long-term archival workflows. It supports synchronization through both Discord bot APIs and local desktop cache imports, giving users flexibility in how data is collected and updated. The system includes commands for searching messages, tailing live updates, and maintaining synchronized archives through incremental sync operations. ... -
22
dive-into-llms
"Dive into LLMs" series of practical programming tutorials
...The repository is structured as a learning pathway, making it accessible to both beginners and intermediate practitioners interested in understanding how LLMs work. It includes code samples, tutorials, and conceptual breakdowns that bridge the gap between academic research and real-world implementation. The project also highlights best practices for working with LLMs, including prompt design and optimization strategies. By focusing on clarity and depth, it serves as both a teaching tool and a reference for developers. Overall, dive-into-llms provides a structured and practical approach to mastering modern language model technology. -
23
Claude Code Architecture Study
Research on Coding Agents
Claude Code Architecture Study is an educational and experimental repository designed to teach developers how to build, configure, and understand AI coding agents from first principles. The project focuses on breaking down the architecture of agentic systems, including how models perceive context, make decisions, and execute actions in a coding environment. It likely provides step-by-step examples, conceptual explanations, and practical implementations that guide users through creating their... -
24
MetaClaw
Just talk to your agent
...The architecture suggests scalability, allowing the system to handle multiple agents or complex workflows simultaneously. It is likely designed for experimentation with next-generation agent systems that combine planning, learning, and execution. Overall, MetaClaw represents a research-driven effort to push the boundaries of intelligent agent coordination and adaptability. -
25
Understand Anything
Turn any codebase into an interactive knowledge graph
...The system leverages language models to provide layered insights, allowing users to explore topics at different levels of detail. It is particularly useful for learning, research, and quick comprehension of new concepts across various domains. The project emphasizes accessibility, making advanced knowledge more approachable for a wider audience. It also supports iterative questioning, enabling users to refine their understanding through follow-up queries.
