Search Results for "ai coding model" - Page 4
Sort By:
Showing 183 open source projects for "ai coding model"
View related business solutions-
Intelligent Retail ManagementQuant offers a wide range of solutions for retail. Within one integrated software system, it allows you to efficiently combine the management of retail space, shelf labels and marketing materials with task management, reporting and automatic replenishment.
-
AI-Powered Identity GovernanceDefine governance policies, manage access, and optimize licenses with unified visibility across every identity, app, and file.
-
1
Bot Framework SDK for Python
Build and connect intelligent bots that interact naturally
This repository contains code for the Python version of the Microsoft Bot Framework SDK, which is part of the Microsoft Bot Framework - a comprehensive framework for building enterprise-grade conversational AI experiences. This SDK enables developers to model conversation and build sophisticated bot applications using Python. SDKs for JavaScript and .NET are also available. The Microsoft Bot Framework provides what you need to build and connect intelligent bots that interact naturally wherever your users are talking, from text/sms to Skype, Slack, Office 365 mail and other popular services. -
2
Bot Framework SDK for .NET
Welcome to the Bot Framework SDK for .NET repository
This repository contains code for the .NET version of the Microsoft Bot Framework SDK, which is part of the Microsoft Bot Framework - a comprehensive framework for building enterprise-grade conversational AI experiences. This SDK enables developers to model conversation and build sophisticated bot applications using .NET. SDKs for JavaScript, Python and Java (preview) are also available. To get started building bots using the SDK, see the Azure Bot Service Documentation. -
3
Bot Framework SDK for JavaScript
Welcome to the Bot Framework SDK for JavaScript repository
This repository contains code for the JavaScript version of the Microsoft Bot Framework SDK, which is part of the Microsoft Bot Framework - a comprehensive framework for building enterprise-grade conversational AI experiences. This SDK enables developers to model conversation and build sophisticated bot applications using JavaScript. SDKs for .NET, Python and Java (preview) are also available. To get started building bots using the SDK, see the Azure Bot Service Documentation. If you are an existing user, then you can also find out what's new with Bot Framework. -
4
bu-agent-sdk
An agent is just a for-loop
The bu-agent-sdk from the Browser Use project is a minimalistic Python framework that defines an AI agent as a simple loop of tool calls, aiming to keep abstractions low so developers can build autonomous agents without unnecessary complexity. At its core, the agent loop repeatedly queries a large language model, interprets its output, and executes defined “tools” — functions annotated with task names — to perform actions, allowing the agent to complete tasks like arithmetic, decision-making, or domain-specific work. ... -
Shoplogix Smart Factory PlatformReal-time Visibility into Your Shop Floor's Performance. The Shoplogix smart factory platform enables manufacturers to increase overall equipment effectiveness, reduce operational costs, sustain growth and improve profitability by allowing them to visualize, integrate and act on production and machine performance in real-time. Manufacturers that trust us to drive efficiency in their factories. Real-time visual data and analytics provide valuable insights to make better informed decisions. Uncover hidden shop floor potential and drive rapid time to value. Develop a continuously improving culture through training, education and data-driven decisions. Compete in the i4.0 world by making the Shoplogix Smart Factory Platform the cornerstone of your digital transformation. Connect to any equipment or device to automate data collection and exchange it with other manufacturing technologies. Automatically monitor, report and analyze machine states to track real-time production.
-
5
PydanticAI
Agent Framework / shim to use Pydantic with LLMs
When I first found FastAPI, I got it immediately. I was excited to find something so innovative and ergonomic built on Pydantic. Virtually every Agent Framework and LLM library in Python uses Pydantic, but when we began to use LLMs in Pydantic Logfire, I couldn't find anything that gave me the same feeling. PydanticAI is a Python Agent Framework designed to make it less painful to build production-grade applications with Generative AI. Built by the team behind Pydantic (the validation layer... -
6
agentOS
A portable open-source operating system for agents. ~6 ms coldstarts
...AgentOS is designed to run directly within an application process, enabling agents to interact with host functions and resources without network overhead or complex orchestration layers. It includes a permission-based security model that restricts access to system resources such as file systems and networks by default, ensuring safe execution of potentially untrusted code. -
7
Ollama Python
Ollama Python library
...Developers use it to load models, send prompts, manage sessions, and stream responses directly from Python code. It simplifies integration of Ollama-based models into applications, supporting synchronous and streaming modes. This tool is ideal for those building AI-driven apps with local model deployment. -
8
Ollama4j
A simple Java library for interacting with Ollama server
...It provides a clean and developer-friendly API that abstracts the underlying REST communication, allowing users to focus on building features rather than handling low-level networking details. The library supports a wide range of core capabilities, including chat-based interactions, text generation, embeddings, and model management, making it suitable for both simple applications and more advanced AI-driven systems. It integrates seamlessly into Java ecosystems through Maven or Gradle dependencies, and it works with standard Java environments starting from JDK 11 and above. Ollama4j also includes support for advanced features such as tool or function calling, enabling models to interact with external systems and execute more complex workflows. -
9
Ollama-rs
A simple and easy-to-use library for interacting with the Ollama API
...It follows the official Ollama API closely, ensuring compatibility while offering an idiomatic Rust experience with strong typing and asynchronous execution. The library supports a wide range of operations, including text generation, chat interactions, embeddings, and model management, making it suitable for both simple applications and more advanced AI workflows. It includes streaming capabilities for real-time output, allowing developers to process responses incrementally rather than waiting for full completions. The project also introduces support for tool calling and custom function integration, enabling more dynamic and agent-like behavior within applications. -
Software Defined StorageQuantaStor is a unified Software-Defined Storage platform designed to scale up and out to make storage management easy while reducing overall enterprise storage costs.
-
10
Vouch
A community trust management system based on explicit vouches
Vouch is an open-source community trust management system that introduces an explicit vouching model to govern who is allowed to contribute to a project’s critical interactions, such as opening issues or submitting pull requests. Traditional open source has relied on implicit trust earned through effort, but the advent of AI-generated low-quality contributions has made maintainers seek more intentional vetting processes. With Vouch, existing trusted contributors explicitly “vouch” for new community members before they can participate in selected parts of the project, and they can also “denounce” users to block them should they act in bad faith. ... -
11
DeepSeed
Deep learning optimization library making distributed training easy
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective. DeepSpeed delivers extreme-scale model training for everyone, from data scientists training on massive supercomputers to those training on low-end clusters or even on a single GPU. Using current generation of GPU clusters with hundreds of devices, 3D parallelism of DeepSpeed can efficiently train deep learning models with trillions of parameters. With just a single GPU,... -
12
SDGym
Benchmarking synthetic data generation methods
The Synthetic Data Gym (SDGym) is a benchmarking framework for modeling and generating synthetic data. Measure performance and memory usage across different synthetic data modeling techniques – classical statistics, deep learning and more! The SDGym library integrates with the Synthetic Data Vault ecosystem. You can use any of its synthesizers, datasets or metrics for benchmarking. You also customize the process to include your own work. Select any of the publicly available datasets from the... -
13
YData Synthetic
Synthetic data generators for tabular and time-series data
A package to generate synthetic tabular and time-series data leveraging state-of-the-art generative models. Synthetic data is artificially generated data that is not collected from real-world events. It replicates the statistical components of real data without containing any identifiable information, ensuring individuals' privacy. This repository contains material related to Generative Adversarial Networks for synthetic data generation, in particular regular tabular data and time-series. It... -
14
FATE
An industrial grade federated learning framework
FATE (Federated AI Technology Enabler) is the world's first industrial grade federated learning open source framework to enable enterprises and institutions to collaborate on data while protecting data security and privacy. It implements secure computation protocols based on homomorphic encryption and multi-party computation (MPC). Supporting various federated learning scenarios, FATE now provides a host of federated learning algorithms, including logistic regression, tree-based algorithms,... -
15
ComfyUI Examples
Examples of ComfyUI workflows
ComfyUI_examples is the companion repository for ComfyUI that collects ready-made example workflows, nodes, and compositions to help users learn the node-based interface for AI image generation. Instead of starting from an empty graph, you can open an example and see how prompts, samplers, models, and image processing steps are wired together. This makes ComfyUI more approachable for people coming from “one text box” generators, because they can reverse-engineer complex pipelines visually. The examples also serve as references for best practices like model loading order, latent handling, upscaling chains, and conditioning. ... -
16
Visual Blocks
Visual Blocks for ML is a Google visual programming framework
Visual Blocks is a node-based, in-browser environment for building AI and data-processing workflows with drag-and-drop components. It lets you connect sources, transforms, models, and visualizers into a live graph, so changes propagate instantly and results are observable without writing glue code. Under the hood it leans on web-friendly runtimes (e.g., WebGPU/WebGL/WebNN or TensorFlow.js backends) to execute pipelines locally, which is great for demos, teaching, and privacy-sensitive prototypes. ... -
17
Courses (Anthropic)
Anthropic's educational courses
Anthropic’s courses repository is a growing collection of self-paced learning materials that teach practical AI skills using Claude and the Anthropic API. It’s organized as a sequence of hands-on courses—starting with API fundamentals and prompt engineering—so learners build capability step by step rather than in isolation. Each course mixes short readings with runnable notebooks and exercises, guiding you through concepts like model parameters, streaming, multimodal prompts, structured outputs, and evaluation. ... -
18
FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
FlashMLA is a high-performance decoding kernel library designed especially for Multi-Head Latent Attention (MLA) workloads, targeting NVIDIA Hopper GPU architectures. It provides optimized kernels for MLA decoding, including support for variable-length sequences, helping reduce latency and increase throughput in model inference systems using that attention style. The library supports both BF16 and FP16 data types, and includes a paged KV cache implementation with a block size of 64 to... -
19
FastMCP Framework
A TypeScript framework for building MCP servers
...Developers can use it to build server back-ends that expose data or capabilities to LLM applications in a standardized way, reducing the custom boilerplate required for integrating with AI systems. It includes tooling for development (examples, CLI) and is open-source, inviting contributions and extensions. -
20
Starter Applets
Google AI Studio Starter Apps
starter-applets is a collection of minimal, sandboxed example “applets” that demonstrate how to compose Gemini-powered microapps (chat widgets, image generation, workflows) that can be embedded in other applications or used standalone. The applets are structured with a focus on simplicity: each presents a prompt input, minimal UI logic, and inline display of the resulting output or widget (e.g. generated text, images). They are built to illustrate best practices (e.g. safety guards, prompt... -
21
Ollama Copilot
Proxy that allows you to use ollama as a copilot like Github copilot
Ollama Copilot is a proxy-based tool that transforms locally hosted language models into a GitHub Copilot-style coding assistant for popular development environments. It acts as an intermediary server that exposes Ollama or other model providers through a Copilot-compatible interface, allowing developers to use local or self-hosted models for inline code completion. The project supports multiple providers such as Ollama, DeepSeek, and Mistral, enabling flexibility between local and remote inference depending on user needs. ... -
22
JeeSite
A basic enterprise information development platform
JeeSite is a high-efficiency, high-performance, and strong security open source Java EE rapid development platform based on a number of excellent open source projects, highly integrated and packaged. JeeSite is the best basic platform solution for you to quickly complete your project. JeeSite is the best study case for you to learn the Java platform. JeeSite is also the best assistant for private work. JeeSite is a Java-based development platform built on the Spring Framework, with Spring... -
23
CodinIT.dev
Free, local, open-source AI app builder
CodinIT.dev is a free, local, open source AI app builder that lets you go from idea to full-stack application entirely on your machine, no coding required, just chat with AI. You can build unlimited apps with real-time previews, instant undo, and responsive, frictionless workflows. Deep Supabase integration means you can create UI and backend logic in one cohesive environment, while the model-agnostic architecture lets you connect to any AI, whether cloud-based (Gemini 3 Pro, GPT-5, Claude Sonnet 4.5) or local via Ollama, so you’re never locked in. ... -
24
claude-code-transcripts
Tools for publishing transcripts for Claude Code sessions
claude-code-transcripts is a command-line utility that takes session files exported from Claude Code (in JSON or JSONL format) and turns them into clean, navigable HTML transcripts that can be viewed in any modern web browser. It is designed to make the often dense and verbose outputs from AI coding sessions easier to read, share, and archive by breaking conversations into paginated, annotated pages with navigable timelines of prompts and responses. Users can run this tool locally or fetch sessions from the Claude API, giving flexibility for individual workflows or team documentation practices. The generated HTML includes interactive navigation and can optionally be published to GitHub Gists for sharing with collaborators or embedding in other documentation. ... -
25
TensorRT
C++ library for high performance inference on NVIDIA GPUs
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for deep learning inference applications. TensorRT-based applications perform up to 40X faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and deploy to hyperscale data centers,...
