Directory
Published directory entries matching your search.
Pipeline Conversations is a podcast from ZenML featuring interviews with platform engineers, ML practitioners and technical leaders building production AI systems. Episodes cover MLOps and LLMOps topics including Kubernetes workflows, model fine-tuning and evaluation, LLM security, cost optimization, prompt engineering and agents in production.
PlantUML is an open-source tool that uses simple textual descriptions to draw UML diagrams. It supports diagram types including sequence, use case, class, object, activity, component, deployment, state and timing diagrams, plus non-UML diagrams. Images can be exported in PNG, LaTeX, EPS and SVG.
pnpm is a package manager distributed as a native executable for version 12, with prebuilt binaries for multiple operating system and architecture targets. It can be installed through a standalone script on Windows and POSIX systems or through npm, which requires Node.js 22.13 or newer. Updating to pnpm 12 is possible via self-update if pnpm 11.10.0 or newer is already installed.
Portainer is a platform for deploying, running, securing, and governing Kubernetes across a fleet from a single control plane. It provides multi-cluster fleet management, GitOps deployment workflows, self-service with guardrails, and enterprise identity and access. Docker, Swarm, and Podman hosts join the same console. Portainer Business Edition is free for 3 nodes and includes RBAC, GitOps, fleet governance, and audit logs.
Portkey is a production stack for generative AI builders that offers a suite of tools including an AI gateway, observability features, guardrails and prompt management modules. It is designed to help organizations democratize and productionize generative AI.
A free course for people with some coding experience who want to learn how to apply deep learning and machine learning to practical problems. It includes 9 lessons of around 90 minutes each, covering computer vision, natural language processing, tabular analysis, and collaborative filtering, plus building and training models, random forests, deployment, and use of PyTorch, fastai and Hugging Face.
PromptLayer is a prompt management platform for AI engineering teams. It offers prompt versioning, large language model evaluation tools, and AI agent observability via tracing, logs, and regression sets, plus a visual editor for prompt iteration and collaboration.
PyGPT is a free, open-source desktop AI assistant compatible with Windows, Linux and macOS operating systems. It supports both cloud-based and local AI models, and offers features including AI chat, multi-agent workflows, RAG-powered knowledge retrieval from user files, skills and plugin support, Python and MCP automation, and voice, vision and content generation capabilities.
Python Library for Probabalistic Programming (Bayesian Inference and Machine Learning).
Quix is described as an agentic AI platform for hardware engineering. It turns test-rig and sensor data into real-time insight and is presented as automating engineering workflows across the V, from requirements through verification, validation and operation.
Reaparr is a Plex downloader that transfers content from accessible Plex servers into a user's own Plex server. It offers multi-threaded, resumable downloads, browsing and filtering of libraries, multi-account management, and Docker-based deployment. It can act as an indexer and download client for Sonarr and Radarr.
Rufus is a lightweight Windows system utility that creates bootable USB drives. These drives can be used to install or run Microsoft Windows, Linux, or DOS on a computer. The tool is designed for speed and simplicity, requiring only a small number of clicks and a few minutes of time to generate a functional bootable drive for operating system deployment, testing, or recovery use cases.
RunThisLLM is a website that provides hardware requirements for running local AI models. It lists over 295 models with full build specifications, performance estimates, and benchmarks. It also offers a Chrome extension and a custom machine building service.
SAS Viya is a cloud native AI, analytic and data management platform supporting teams across the analytics life cycle. It unifies data, analytics and governance, and supports building, validating and deploying AI with governance, fairness and transparency. Deployment options cover cloud, hybrid and on-premises environments.
CodeFormer, developed by sczhou, is a robust open-source face restoration algorithm designed for restoring old photos and AI-generated faces. The associated web demo is intended for research purposes. It is available via the Replicate platform or for local deployment, runs on Nvidia L40S GPUs, and typically completes predictions in 3 seconds. The associated research was published at NeurIPS 2022.
Sierra Protocol is described as an institutional-grade layer for deploying permissionless yield vaults. It offers vault deployment, curated vaults, Liquid Yield Tokens and earn products. Vaults issue ERC-20 tokens tracking underlying segregated reserves, with optional upgrade to a Liquid Yield Token. The site lists asset managers, fintechs and exchanges among intended users.
SinglebaseCloud is an AI-native backend platform and Firebase alternative that combines document and vector databases, authentication, storage, and built-in AI services to support the development and scaling of modern applications.
SocialBu is a social media management tool for planning, scheduling, responding to, automating, and analyzing social media across connected accounts. It offers AI-assisted drafting and refinement of posts and captions, content curation, listening streams for mentions and keywords, a unified inbox, automation rules, and performance reports. A 7-day free trial is mentioned. An MCP Server connects compatible AI clients to supported tasks.
Stan is software for Bayesian data analysis that combines statistical modeling capabilities with user-friendly interfaces and open-source development. Its probabilistic programming language supports applications from simple linear regression to multi-level models and time-series analysis. Interfaces exist for Python, Julia, R, and the Unix shell, usable on laptops, clusters, or in the cloud. Official documentation covers the language, inference algorithms, and built-in functions.
Stanford CS336: Language Modeling from Scratch is the official course website for a Stanford class offered in Spring 2026. The course walks students through the process of developing a language model, including data collection and cleaning for pre-training, transformer model construction, model training, and evaluation before deployment. The site provides logistics, schedule, assignments, and course materials.
Superwise is a platform offering AI Gateway, Secure AI Chat, and AI Services. Its Sentinel product prevents sensitive data from leaking into external AI tools, Chat provides a safe AI workspace for teams, and its services help organizations plan, build, and govern AI use cases.
System Designer is a learning site offering interactive lessons and case studies on system design. Its Machine Learning Systems section covers building production ML systems, from data pipelines to deployment, with topics such as distributed training, model serving, MLOps monitoring and A/B testing. Lessons are organized into units with stated difficulties and durations.
Self-hosted control plane that sits between connected AI clients, model providers, and tools. It applies access rules to users and agents, routes supported model requests through a gateway, checks governed tool calls before execution, and records policy decisions, execution records, and usage in the operator's environment. It deploys a Rust runtime with PostgreSQL on infrastructure the operator controls.
TeamoRouter provides machine-learning models, research, training resources, or evaluation tools.
