Search Results for "open source kms" - Page 92
Sort By:
Showing 16932 open source projects for "open source kms"
View related business solutions-
Stop Storing Third-Party Tokens in Your DatabaseRolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
Parallax
Parallax is a distributed model serving framework
Parallax is a decentralized inference framework designed to run large language models across distributed computing resources. Instead of relying on centralized GPU clusters in data centers, the system allows multiple heterogeneous machines to collaborate in serving AI inference workloads. Parallax divides model layers across different nodes and dynamically coordinates them to form a complete inference pipeline. A two-stage scheduling architecture determines how model layers are allocated to... -
2
DATAGEN
AI-driven multi-agent research assistant automating hypothesis
DATAGEN is an AI-driven multi-agent research and data analysis platform designed to automate complex analytical workflows. The system coordinates multiple specialized AI agents that collaborate to perform tasks such as hypothesis generation, data collection, analysis, visualization, and report creation. Instead of requiring users to manually orchestrate each stage of a research process, the platform allows these agents to coordinate automatically and handle the workflow end-to-end. The... -
3
AI Engineering Academy
Mastering Applied AI, One Concept at a Time
AI-Engineering.academy is a community-driven educational repository that organizes practical knowledge and learning paths for applied AI engineering. The project aims to make complex AI concepts accessible by structuring them into progressive learning modules covering topics such as prompt engineering, retrieval-augmented generation, LLM deployment, and AI agents. Rather than focusing purely on theoretical explanations, the repository emphasizes hands-on understanding of how modern AI... -
4
nano-graphrag
A simple, easy-to-hack GraphRAG implementation
nano-graphrag is a lightweight implementation of the GraphRAG approach designed to simplify experimentation with graph-based retrieval-augmented generation systems. GraphRAG expands traditional RAG pipelines by constructing knowledge graphs from documents and using relationships between entities to improve the quality and reasoning of AI responses. The nano-GraphRAG project focuses on reducing complexity by providing a compact and readable codebase that preserves the core functionality of... -
Earn up to 16% annual interest with Nexo.Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
5
rag-search
RAG Search API
rag-search is a lightweight Retrieval-Augmented Generation API service designed to provide structured semantic search and answer generation through a simple FastAPI backend. The project integrates web search, vector embeddings, and reranking logic to retrieve relevant context before passing it to a language model for response generation. It is built to be easily deployable, requiring only environment configuration and dependency installation to run a functional RAG service. The system... -
6
Pathway AI Pipelines
Ready-to-run cloud templates for RAG
Pathway AI Pipelines is a collection of ready-to-deploy AI pipeline templates designed to help developers rapidly build production-grade retrieval-augmented generation and enterprise search applications. The project provides end-to-end examples that connect live data sources to LLM workflows, enabling applications to stay synchronized with continuously changing information. It supports numerous connectors including local files, Google Drive, SharePoint, Kafka, PostgreSQL, and real-time APIs,... -
7
s-tui
Terminal-based CPU stress and monitoring utility
s-tui (Stress Terminal UI) is a terminal-based performance monitoring and stress-testing tool focused specifically on CPU behavior analysis in Linux and other UNIX-like systems. It provides real-time graphical visualization of CPU temperature, frequency, power consumption, and utilization directly within a text-based interface, eliminating the need for a graphical desktop environment. The utility is particularly useful for diagnosing thermal throttling, validating cooling solutions, and... -
8
Megatron-LM
Ongoing research training transformer models at scale
Megatron-LM is a GPU-optimized deep learning framework from NVIDIA designed to train extremely large transformer-based language models efficiently at scale. The repository provides both a reference training implementation and Megatron Core, a composable library of high-performance building blocks for custom large-model pipelines. It supports advanced parallelism strategies including tensor, pipeline, data, expert, and context parallelism, enabling training across massive multi-GPU and... -
9
papermill
Parameterize, execute, and analyze notebooks
papermill is a Python library and command-line tool that transforms Jupyter Notebooks into repeatable, parameterized workflows by allowing users to define editable parameters within notebooks and then programmatically execute them with different inputs. Instead of manually opening and running a notebook inside JupyterLab or Notebook every time, Papermill lets you inject new values into a specially tagged parameters cell and execute the entire notebook automatically via a script or automation... -
$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.
-
10
LatentMAS
Latent Collaboration in Multi-Agent Systems
LatentMAS is an advanced framework for multi-agent reinforcement learning (MARL) that uses latent variable modeling to bridge perception and decision-making in environments where agents must coordinate under uncertainty. It provides mechanisms for agents to learn high-level latent representations of states, which simplifies complex sensory inputs into compact, actionable embeddings that facilitate both individual policy learning and inter-agent coordination. Using this latent space, the... -
11
WYGIWYH
A simple but powerful self-hosted finance tracker
WYGIWYH (What You Get Is What You Have) is a self-hosted, principles-first personal finance tracker built for people who prefer a simple, intuitive approach to tracking money without complicated budgets or categories. Based on a philosophy that you should use what you earn each month for that month, it helps you understand where your funds go while keeping savings clearly separated so they aren’t accidentally dipped into for everyday expenses. The app supports multiple currencies,... -
12
StoryMem
Official code for StoryMem: Multi-shot Long Video Storytelling
StoryMem is a narrative-focused memory accumulation system that lets users build, store, and reference past conversational context or story elements with an AI, effectively enabling the AI to maintain and recall personalized story memories or character arcs over time. Instead of treating each interaction as stateless, it tracks user-defined memory nodes, tags, and story threads so that future interactions can draw on established narrative context like character traits, past events, or... -
13
fast-stable-diffusion
Fast-stable-diffusion + DreamBooth
fast-stable-diffusion is a community-curated GitHub repository that provides Colab notebooks and integration examples for running Stable Diffusion and associated UIs like AUTOMATIC1111, ComfyUI, and DreamBooth directly on Google Colab environments. Rather than being a standalone packaged application, this project offers ready-to-use interactive notebooks that install and launch full-feature Stable Diffusion web UIs inside Colab without requiring complex local setups or GPU installations.... -
14
SkillForge
Ultimate meta-skill for generating best-in-class Claude Code skills
SkillForge is a systematic methodology and tooling framework for creating high-quality AI “skills” specifically optimized for Claude Code integrations, treating skill creation as an engineering discipline rather than an ad-hoc art form. It introduces a multi-phase architecture where every input or request is triaged intelligently, analyzed deeply through structured lenses, specified formally, synthesized with automated generation, and finally subjected to multi-agent review before... -
15
Claude Cognitive
Persistent context and multi-instance coordination
Claude Cognitive is an advanced memory and context-management extension designed to address the stateless limitations of Claude Code by giving the model a form of persistent “working memory” and multi-instance coordination. It introduces an attention-based context router that prioritizes files and content relevant to the current development discussion — tagging them as HOT, WARM, or COLD based on recency and keyword activation — so Claude Code doesn’t waste token budget rereading irrelevant... -
16
SimpleMem
SimpleMem: Efficient Lifelong Memory for LLM Agents
SimpleMem is a lightweight memory-augmented model framework that helps developers build AI applications that retain long-term context and recall relevant information without overloading model context windows. It provides easy-to-use APIs for storing structured memory entries, querying those memories using semantic search, and retrieving context to augment prompt inputs for downstream processing. Unlike monolithic systems where memory management is ad-hoc, SimpleMem formalizes a memory... -
17
Engram
A New Axis of Sparsity for Large Language Models
Engram is a high-performance embedding and similarity search library focused on making retrieval-augmented workflows efficient, scalable, and easy to adopt by developers building search, recommendation, or semantic matching systems. It provides utilities to generate embeddings from text or other structured data, index them using efficient approximate nearest neighbor algorithms, and perform real-time similarity queries even on large corpora. Engineered with speed and memory efficiency in... -
18
Recursive Language Models
General plug-and-play inference library for Recursive Language Models
RLM (short for Reinforcement Learning Models) is a modular framework that makes it easier to build, train, evaluate, and deploy reinforcement learning (RL) agents across a wide range of environments and tasks. It provides a consistent API that abstracts away many of the repetitive engineering patterns in RL research and application work, letting developers focus on modeling, experimentation, and fine-tuning rather than infrastructure plumbing. Within the framework, you can define custom... -
19
Flask-SocketIO
Socket.IO integration for Flask applications
Flask-SocketIO is an extension for the Flask web framework that enables real-time bi-directional communication between clients and servers using WebSockets or long-polling fallbacks, making it possible to build interactive applications like chat systems, live dashboards, and collaborative tools. It abstracts the complexities of asynchronous sockets by providing a familiar Flask-style API where developers can define event handlers that trigger on client messages, broadcast to connected users,... -
20
Motor
The async Python driver for MongoDB and Tornado or asyncio
Motor is an asynchronous Python driver for MongoDB that enables developers to work with MongoDB using non-blocking I/O patterns, making it ideal for high-performance and scalable applications. Built on top of Python’s Tornado and asyncio frameworks, Motor lets you issue database operations without blocking the event loop, enabling concurrency in web servers, real-time systems, and microservices. It provides a familiar API surface similar to the official synchronous PyMongo driver, so you can... -
21
rate.sx
Curl cryptocurrencies exchange rates
rate.sx is a command-line-friendly cryptocurrency rate service designed to be queried with curl or a browser, returning clean text or minimal markup. It emphasizes human-readable output by default, with options for concise one-liners or richer summaries including sparkline-style ASCII charts. The service supports multiple coins, fiat conversions, and historical lookups so you can compare prices over time without leaving the terminal. Under the hood it aggregates price feeds and normalizes... -
22
DevOps Exercises
Linux, Jenkins, AWS, SRE, Prometheus, Docker, Python, Ansible, Git
DevOps Exercises is a massive, community-maintained collection of questions, tasks, and mini-challenges that cover the breadth of modern DevOps and platform engineering. It spans Linux, networking, Docker, Kubernetes, CI/CD, monitoring, cloud providers, security, and even soft skills and troubleshooting. The idea is to give candidates and teams a realistic practice ground for interviews, certifications, and day-to-day operational work. Because it’s structured as Q&A and exercises, you can go... -
23
TensorRT Node for ComfyUI
Enables the best performance on NVIDIA RTX Graphics Cards
ComfyUI_TensorRT is an extension that lets ComfyUI run AI inference through NVIDIA’s TensorRT, aiming to get faster, more efficient execution on supported GPUs. It bridges the gap between ComfyUI’s flexible, node-based workflows and TensorRT’s highly optimized engine format. The result is that complex diffusion or image-processing graphs can be accelerated without the user having to rewrite the pipeline. The repo typically includes instructions for converting models to TensorRT engines and... -
24
Hello SQL
Spanish-language course repository that teaches fundamentals of SQL
hello-sql is a beginner-friendly, Spanish-language course repository that teaches the fundamentals of SQL and relational databases through practical examples. It focuses mainly on MySQL for lessons due to its ubiquity in education and professional environments, while also introducing PostgreSQL to broaden learners’ exposure to modern database tooling. The materials emphasize real-world query writing, schema design basics, and the mental model behind SELECT, JOIN, GROUP BY, and subqueries.... -
25
plexe
Build a machine learning model from a prompt
plexe lets you build machine-learning systems from natural-language prompts, turning plain English goals into working pipelines. You describe what you want—a predictor, a classifier, a forecaster—and the tool plans data ingestion, feature preparation, model training, and evaluation automatically. Under the hood an agent executes the plan step by step, surfacing intermediate results and artifacts so you can inspect or override choices. It aims to be production-minded: models can be exported,...