Search Results for "machine" - Page 42
Sort By:
Showing 4715 open source projects for "machine"
View related business solutions-
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.
-
PRTG Catches Network Issues Before They Cause DowntimeReactive troubleshooting usually means hearing about a problem from frustrated users, not your monitoring tool. PRTG sets threshold-based alerts across devices, servers and applications, notifying your team by email, SMS or push the moment a metric crosses a set limit. That means catching a failing disk or overloaded server before it becomes an outage and getting time back from firefighting. Start a free trial and set your first alerts today.
-
1
SuperBased
Local-first control plane for AI coding agents
...A local dashboard, CLI, MCP server, and VS Code extension expose sessions, files, tokens, costs, and runtime state. Twenty-seven supported tools can also be launched as managed terminal sessions. Data stays on the user's machine by default, with no telemetry or remote reporting unless optional cloud features are explicitly enabled. SuperBased also supports backfills, resumable sessions, Tailscale-based remote viewing, and configurable compression profiles. -
2
Rune
the development environment for pros
...Its interface supports nine workspace slots along with many terminals, tabs, and windows. Rune instances can form an end-to-end encrypted peer network so users can connect to one development machine from another. The editor includes production-grade language support and can be extended through official or community packages. Its graphics pipeline uses OpenGL on Linux and Metal on macOS instead of Electron. The bundled Rune Agent is shipped as an extension so AI coding remains separate from the core editor. -
3
NVIDIA Personal AI Router (PAIR)
Router that virtually distributes inference across connected devices
...PAIR keeps fully local configurations on the local network and is especially useful for concurrent workloads such as multi-agent applications. It routes each request to one machine rather than combining GPU memory or splitting a model across devices. -
4
AI Copywriter
An AI copywriter that uses real copywriting skills + real marketing
AI Copywriter is a portable Markdown-based agent skill for producing persuasive marketing copy that still sounds human. It combines conversion-focused writing with a humanization process based on 33 recognizable patterns of machine-generated prose. Before drafting, the skill asks about the ideal customer, product category, and real story behind the message. It evaluates audience emotion, simplifies the explanation, and challenges vague inputs instead of hiding them behind generic language. The workflow can generate headlines, subject lines, descriptions, interface microcopy, social posts, and strategic articles. ... -
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
Shepherd
Runtime substrate that turns agent's execution into a Git-like trace
...Read-only and read-write repository grants are enforced through native operating-system sandboxing on supported macOS and Linux environments. Runs can be forked, replayed, reverted, and supervised, enabling counterfactual experiments, optimization, and training workflows. Shepherd also retains machine-readable records and supports offline deterministic examples, but its APIs may change while the project remains in alpha. -
6
SIA
AI framework to autonomously improve the performance of any AI system
...It uses an iterative loop where a meta-agent creates or updates a task-specific target agent, while a feedback agent studies results and proposes improvements. The framework can refine both the harness around the task and the agent implementation itself. It is aimed at research and experimentation across tasks such as machine learning benchmarks, legal classification, code optimization, and scientific workflows. It includes built-in tasks, a command-line runner, and a visual dashboard for following generations as they evolve. It also lets users define custom providers, profiles, seed agents, and task directories without changing the core code. -
7
How to Train Your GPT
Build a modern LLM from scratch. Every line commented
How to Train Your GPT is an interactive textbook that teaches users how to build, train, and run a modern language model from scratch. It is written for learners with minimal machine-learning background, using simple explanations, commented code, and practical examples. The project covers the same broad family of architecture behind systems such as GPT-style models, LLaMA-style models, Claude-style systems, and Mistral-style models. It includes chapters and topic explainers on tokenizers, embeddings, attention, RoPE, RMSNorm, SwiGLU, KV cache, AdamW, mixed precision, training loops, and inference. ... -
8
Ollama RAG Chatbot
Chat with multiple PDFs locally
Ollama RAG Chatbot is a local-first retrieval chatbot project built to let users chat with the contents of multiple PDF documents through a simple interface. The project is framed as an experiment, but its setup and packaging make it approachable for practical local use as well. It supports running on a local machine or in Kaggle, which lowers the barrier for users who want to test RAG workflows without building everything from scratch. Model support is flexible, with compatibility for both Hugging Face models and Ollama-based models, and the interface is delivered through Gradio for a lightweight user experience. The main value of the project is its ability to process multiple PDF inputs and turn them into a question-answering workflow centered on document retrieval. ... -
9
LaReview
The code review workbench
LaReview is a developer-first, local-first code review workbench designed to transform complex pull requests or diffs into structured, high-signal review workflows powered by AI assistance. Instead of overwhelming developers with raw diffs or automated comment spam, the tool analyzes code changes and generates an intent-driven review plan that groups changes into logical flows such as authentication, API behavior, or data handling, and prioritizes them based on risk. It operates as a desktop... -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
Worktale
Turns git history into a personal record of what you actually built
...Instead of relying on memory, scattered commits, or external tracking tools, it automatically captures and organizes commit activity into a cohesive narrative that reflects what was built, when, and how. The tool operates entirely on the user’s machine, scanning repositories and installing optional post-commit hooks to continuously track development activity without modifying the codebase itself. It extracts metadata such as commit messages, files changed, line counts, and timestamps, then structures that data into a searchable and browsable work log that can be used for performance reviews, portfolio building, or personal reflection. -
11
Writer Framework
No-code in the front, Python in the back. An open-source framework
...It follows a hybrid approach where user interfaces are created using a drag-and-drop editor while business logic is implemented in Python, allowing teams to balance speed and flexibility without sacrificing control. The framework is particularly focused on AI use cases, enabling developers to integrate large language models, knowledge graphs, and custom machine learning workflows into user-facing applications. Its architecture enforces a clear separation of concerns between frontend and backend, which improves maintainability and scalability as applications grow in complexity. The system is designed to support rapid prototyping, enabling developers to iterate on UI and backend logic independently and deploy changes quickly. -
12
Chicory
Native JVM WebAssembly runtime
Chicory is a WebAssembly runtime designed specifically for the Java Virtual Machine, enabling developers to run Wasm modules entirely within Java applications without requiring native dependencies or JNI. Implemented in pure Java, it provides a portable and secure execution environment that can run anywhere the JVM is available, including cloud, desktop, and embedded systems. The runtime loads WebAssembly binaries and exposes their functions as callable Java APIs, allowing seamless integration with existing Java codebases. ... -
13
Companion notebooks for Deep Learning
Jupyter notebooks for the code samples of the book
Companion notebooks for Deep Learning is a collection of Jupyter notebooks that accompany François Chollet’s deep learning curriculum, providing hands-on implementations of key concepts using practical examples. The project covers a wide range of topics, including neural networks, computer vision, natural language processing, and sequence modeling. Each notebook is structured to combine theoretical explanations with executable code, allowing users to experiment and learn interactively. The... -
14
Instill Core
Instill Core is a full-stack AI infrastructure tool for data
Instill Core is an open-source, full-stack AI infrastructure platform designed to orchestrate data pipelines, machine learning models, and unstructured data processing into a unified, production-ready system. It provides an end-to-end solution that enables developers to build, deploy, and manage AI-powered applications without needing to manually stitch together multiple tools across the data and model lifecycle. The platform focuses heavily on handling unstructured data such as documents, images, audio, and video, transforming them into AI-ready formats through integrated ETL pipelines and processing workflows. ... -
15
Numbast
Build an automated pipeline that converts CUDA APIs into Numba
...This approach significantly improves developer productivity by reducing boilerplate code and ensuring consistency between C++ and Python interfaces. Numbast is particularly useful for teams working with custom CUDA libraries or extending existing ones into Python ecosystems for data science and machine learning. It complements tools like Numba, which compile Python code into GPU-executable kernels, by expanding the range of accessible CUDA functionality. -
16
JAX Toolbox
Public CI, Docker images for popular JAX libraries
JAX Toolbox is a development toolkit designed to streamline and optimize the use of JAX for machine learning and high-performance computing on NVIDIA GPUs. It provides prebuilt Docker images, continuous integration pipelines, and optimized example implementations that help developers quickly set up and run JAX workloads without complex configuration. The project supports popular JAX-based frameworks and models, including architectures used for large-scale pretraining such as GPT and LLaMA variants. ... -
17
ARK
Unstyled, accessible UI components for your design System
Ark is a headless UI component library designed to provide the foundational logic required to build scalable and accessible design systems for modern web applications. The project focuses on separating component behavior from visual styling so developers can implement their own design language without being constrained by predefined styles. Built on top of Zag.js state machines, Ark delivers predictable and robust component logic that works consistently across multiple JavaScript frameworks.... -
18
MetaScreener
AI-powered tool for efficient abstract and PDF screening
...The system helps researchers analyze large collections of academic abstracts and research papers to determine which studies are relevant for inclusion in evidence synthesis projects. Instead of manually reviewing hundreds or thousands of documents, researchers can use MetaScreener to apply machine learning techniques that assist with classification and prioritization of candidate papers. The platform can analyze both abstracts and full PDF documents, enabling automated filtering based on research criteria defined by the user. By incorporating natural language processing techniques, the system can identify potentially relevant studies and reduce the workload associated with manual screening. -
19
Bespoke Curator
Synthetic data curation for post-training and data extraction
Curator is an open-source Python library designed to build synthetic data pipelines for training and evaluating machine learning models, particularly large language models. The system helps developers generate, transform, and curate high-quality datasets by combining automated generation with structured validation and filtering. It supports workflows where models are used to produce synthetic examples that can later be refined into reliable training datasets for reasoning, question answering, or structured information extraction tasks. ... -
20
LLM-Finetuning
LLM Finetuning with peft
LLM-Finetuning is an open educational repository that provides practical notebooks and tutorials for fine-tuning large language models using modern machine learning frameworks. The project focuses on parameter-efficient fine-tuning methods such as LoRA and QLoRA, which allow large models to be adapted to new tasks without requiring full retraining. Instead of requiring specialized hardware or complex training pipelines, many examples are designed to run in cloud notebook environments such as Google Colab. ... -
21
WeClone
One-stop solution for creating your digital avatar from chat history
...Developers can use the resulting model to create chatbots that simulate a specific user’s communication patterns for testing or research purposes. Overall, WeClone explores the idea of digital identity replication through machine learning and conversational modeling. -
22
Uncertainty Baselines
High-quality implementations of standard and SOTA methods
Uncertainty Baselines is a collection of strong, well-documented training pipelines that make it straightforward to evaluate predictive uncertainty in modern machine learning models. Rather than offering toy scripts, it provides end-to-end recipes—data input, model architectures, training loops, evaluation metrics, and logging—so results are comparable across runs and research groups. The library spans canonical modalities and tasks, from image classification and NLP to tabular problems, with baselines that cover both deterministic and probabilistic approaches. ... -
23
Sign-In with Ethereum
Sign-In with Ethereum library
...The goals of this specification are to provide a self-custodied alternative to centralized identity providers, improve interoperability across off-chain services for Ethereum-based authentication, and provide wallet vendors a consistent machine-readable message format to achieve improved user experiences and consent management. -
24
Superduper
Superduper: Integrate AI models and machine learning workflows
Superduper is a Python-based framework for building end-2-end AI-data workflows and applications on your own data, integrating with major databases. It supports the latest technologies and techniques, including LLMs, vector-search, RAG, and multimodality as well as classical AI and ML paradigms. Developers may leverage Superduper by building compositional and declarative objects that out-source the details of deployment, orchestration versioning, and more to the Superduper engine. This... -
25
SciML Style Guide for Julia
A style guide for stylish Julia developers
The SciML Style Guide is a style guide for the Julia programming language. It is used by the SciML Open Source Scientific Machine Learning Organization. As such, it is open to discussion with the community. If the standard for code contributions is that every PR needs to support every possible input type that anyone can think of, the barrier would be too high for newcomers. Instead, the principle is to be as correct as possible to begin with, and grow the generic support over time. ...
