Search Results for "ai" - Page 4
Sort By:
Showing 148 open source projects for "ai"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
1
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,... -
2
NNCF
Neural Network Compression Framework for enhanced OpenVINO
NNCF (Neural Network Compression Framework) is an optimization toolkit for deep learning models, designed to apply quantization, pruning, and other techniques to improve inference efficiency. -
3
Neuro SAN Studio
A playground for neuro-san
Neuro SAN Studio is a development environment and playground for building, testing, and deploying multi-agent AI systems using the Neuro SAN framework. It provides a hands-on interface where users can design agent networks, run experiments, and observe how multiple agents collaborate to solve complex tasks. The platform is built around a data-driven approach, where entire agent systems can be defined using configuration files rather than extensive code, making it accessible to both developers and domain experts. ... -
4
Frontend Slides
Create beautiful slides on the web using Claude's frontend skills
...It also supports converting existing PowerPoint files into web-based presentations while preserving content such as images, text, and structure. The tool includes curated design presets that avoid generic AI-generated aesthetics, ensuring presentations feel distinctive and intentional. Its architecture uses progressive disclosure, loading only necessary components at each step to keep the workflow efficient and intuitive. -
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.
-
5
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. -
6
Make It heavy
A Python framework that emulates Grok Heavy functionality
Make It heavy is a Python framework for producing deeper AI analysis through multi-agent orchestration. It is designed to emulate the style of Grok Heavy by splitting a user query into several specialized research angles. The system runs four agents in parallel so each one can explore the problem from a different perspective. It then combines their outputs into one unified answer through an intelligent synthesis step. -
7
Claude for Legal
A suite of plugins for legal workflows
...It is designed for in-house teams, law firms, clinics, and legal students who need structured assistance across commercial, corporate, employment, privacy, product, litigation, regulatory, AI governance, and IP work. The project can run as a Claude plugin or through Claude’s Managed Agents API, giving teams flexibility in how they deploy the same prompts and skills. Its workflows include contract review, NDA triage, diligence review, DSAR response, employment policy drafting, trademark screening, regulatory monitoring, and litigation support. ... -
8
Mistral Inference
Official inference library for Mistral models
Open and portable generative AI for devs and businesses. We release open-weight models for everyone to customize and deploy where they want it. Our super-efficient model Mistral Nemo is available under Apache 2.0, while Mistral Large 2 is available through both a free non-commercial license, and a commercial license. -
9
GPT-Image2-Skill
GPT Image 2 prompt gallery, image prompt library, agentic skill
...The repository is designed for practical reuse, showing both how prompts are structured and how they can be executed. Its value is in combining inspiration, examples, and runnable tooling for repeatable AI image creation. -
Error to trace to log to deploy. One click. No SSH.AppSignal links every error to the trace, the trace to the log, the log to the deploy that shipped it.
-
10
Flower
Flower: A Friendly Federated Learning Framework
...Flower allows for a wide range of different configurations depending on the needs of each individual use case. Flower originated from a research project at the University of Oxford, so it was built with AI research in mind. Many components can be extended and overridden to build new state-of-the-art systems. Different machine learning frameworks have different strengths. Flower can be used with any machine learning framework, for example, PyTorch, TensorFlow, Hugging Face Transformers, PyTorch Lightning, scikit-learn, JAX, TFLite, MONAI, fastai, MLX, XGBoost, Pandas for federated analytics, or even raw NumPy for users who enjoy computing gradients by hand. -
11
Robusta
Kubernetes observability and automation
Keep your Kubernetes microservices up and running. Connect your existing Prometheus, gain 360° observability. Robusta is both an automation engine for Kubernetes and a multi-cluster observability platform. Robusta is commonly used alongside Prometheus, but other tools are supported too. By listening to all the events in your cluster, Robusta can tell you why alerts fired, what happened at the same time, and what you can do about it. Robusta can either improve your existing alerts or be used... -
12
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. ... -
13
colleague-skill
Transform a cold separation into a warm Skill
colleague-skill is a specialized agent skill designed to simulate a collaborative teammate within AI-driven workflows, enabling agents to behave more like human colleagues in problem-solving scenarios. The project focuses on enhancing interaction quality by introducing role-based behavior, contextual awareness, and cooperative task execution. It allows agents to provide suggestions, feedback, and alternative approaches, mimicking real-world collaboration dynamics. -
14
Awesome Free ChatGPT
List of free ChatGPT mirror sites, continuously updated
This is a curated directory of freely accessible ChatGPT-style services and mirror sites that offer AI chatbot interfaces without login or payment requirements. Resources often support multiple models like GPT-4, Claude, Gemini, and more. Data collected from multiple independent sites with descriptions and tags. Includes services with image upload and drawing capabilities. Aggregates free, no-login-required ChatGPT-like web services. -
15
Cortex AI Infrastructure
Open-source multi-chain data routing & low-latency scanning framework.
Cortex AI Infrastructure is an institutional-grade open-source crypto arbitrage bot framework for low-latency multi-chain data routing across TON, Solana, and EVM layers. The engine optimizes high-frequency distributed pipelines to eliminate execution lag and network jitter. Core Technical Modules: 1. Cross-Exchange Telemetry Scanner: Monitors order book depth and spreads across 18 venues concurrently (Binance, ByBit, OKX, HTX) with zero thread-locking. 2. -
16
kagglehub
Python library to access Kaggle resources
...It is useful for machine learning workflows where data, models, and notebook artifacts need to be pulled into scripts, experiments, or pipelines. kagglehub also supports authentication so users can access private or restricted resources when their account has permission. Its main value is making Kaggle assets easier to consume programmatically in Python-first data science and AI development workflows. -
17
PageIndex
Document Index for Vectorless, Reasoning-based RAG
PageIndex is an innovative open-source framework that reimagines retrieval-augmented generation (RAG) by eliminating conventional vector similarity search and instead building hierarchical semantic indexes that mirror a document’s natural structure. Rather than chunking text and embedding it into a vector database, PageIndex constructs a tree-structured index — similar to a detailed, AI-enhanced table of contents — that a large language model can traverse to locate the most relevant sections of long documents. This reasoning-driven retrieval aligns more naturally with how humans explore complex texts, improving relevance and traceability, especially in professional domains like financial reports, legal contracts, and technical manuals. ... -
18
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. -
19
CoreNet
CoreNet: A library for training deep neural networks
...CoreNet integrates tightly with Apple’s proprietary ML stack and hardware, serving as the foundation for research in computer vision, language models, and multimodal systems within Apple AI. The framework includes monitoring tools, fault tolerance mechanisms, and efficient checkpointing for massive training runs. -
20
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. ... -
21
EKS Best Practices
A best practices guide for day 2 operations
The Amazon EKS Best Practices Guide is a public repository containing comprehensive documentation and guidance for operating production-grade Kubernetes clusters on AWS’s managed service, Amazon EKS. Rather than a code library, it serves as a reference catalogue of patterns, anti-patterns, checklists and architectures across domains such as security, reliability, scalability, networking, cost optimization and hybrid cloud deployments. The repository is maintained by AWS but open to... -
22
GenAI Processors
GenAI Processors is a lightweight Python library
GenAI Processors is a lightweight Python library for building modular, asynchronous, and composable AI pipelines around Gemini. Its central abstraction is the Processor, a unit of work that consumes an asynchronous stream of parts (text, images, audio, JSON) and produces another stream, making it natural to chain operations and keep everything streaming end-to-end. Processors can be composed sequentially (to build multi-step flows) or in parallel (to fan-out work and merge results), which makes sophisticated agent behaviors easy to express with simple operators. ... -
23
Maestro Framework
A framework for Claude Opus to intelligently orchestrate subagents
...It can maintain context between subtasks so later steps can build on earlier work. The project can also generate exchange logs and save them as Markdown for review. Overall, it is useful for experimenting with multi-agent task decomposition, AI-assisted planning, and model orchestration workflows. -
24
Kornia
Open Source Differentiable Computer Vision Library
...Inspired by existing packages, this library is composed by a subset of packages containing operators that can be inserted within neural networks to train models to perform image transformations, epipolar geometry, depth estimation, and low-level image processing such as filtering and edge detection that operate directly on tensors. With Kornia we fill the gap between classical and deep computer vision that implements standard and advanced vision algorithms for AI. Our libraries and initiatives are always according to the community needs. -
25
Jina
Build cross-modal and multimodal applications on the cloud
...Seamless Docker container integration: sharing, exploring, sandboxing, versioning and dependency control via Jina Hub. Fast deployment to Kubernetes, Docker Compose and Jina Cloud. Improved engineering efficiency thanks to the Jina AI ecosystem, so you can focus on innovating with the data applications you build.
