Search Results for "stack" - Page 3
Sort By:
80 projects for "stack" with 2 filters applied:
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
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.
-
1
OP Vault
Give ChatGPT long-term memory using the OP Stack
OP Vault is an open-source system designed to give large language models long-term memory by enabling them to interact with a custom knowledge base built from user-provided documents. It combines a backend written in Go with a React frontend, allowing users to upload files such as PDFs, text documents, and books to create a searchable repository of information. The system uses vector databases like Pinecone alongside OpenAI models to index and retrieve relevant content, enabling precise... -
2
Jina-Serve
Build multimodal AI applications with cloud-native stack
Jina Serve is an open-source framework designed for building, deploying, and scaling AI services and machine learning pipelines in production environments. The framework allows developers to create microservices that expose machine learning models through APIs that communicate using protocols such as HTTP, gRPC, and WebSockets. It is built with a cloud-native architecture that supports deployment on local machines, containerized environments, or large orchestration platforms such as... -
3
TTRL
Test-Time Reinforcement Learning
...The repository is implemented on top of the verl ecosystem, which allows users to enable TTRL as part of an existing reinforcement learning workflow rather than building a new stack from scratch. -
4
ANE Training
Training neural networks on Apple Neural Engine via APIs
...The repository implements a from-scratch transformer training pipeline capable of running both forward and backward passes on ANE hardware without relying on CoreML, Metal, or GPU acceleration. It explores the internal software stack of the Apple Neural Engine by interfacing with private classes such as _ANEClient and compiling custom compute graphs in the MIL format. The project includes performance benchmarks and kernel breakdowns that show how different components of the training loop are distributed between the ANE and CPU. It is primarily intended as a research and educational proof of concept rather than a production library, highlighting what is technically possible with undocumented hardware access. -
Veeam Data Platform v13.1 - Get Your Free TrialTry 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
DeployStack
Centralized credential vault, governance, and token optimization
DeployStack is an open-source framework that helps developers and teams define and deploy production infrastructure stacks using modular, reusable templates, often with IaC (infrastructure as code) principles. It provides a structured way to compose resources such as cloud networking, compute, and managed services into coherent deployment blueprints that can be versioned and reused across projects. By abstracting common deployment patterns and capturing them as templates, Deploystack reduces... -
6
Dafthunk
A workflow execution platform built on top of the fantastic Cloudflare
Dafthunk is a browser-first visual workflow automation platform that lets you build, run, and monitor workflows without standing up a traditional server stack. It’s designed around durable, multi-step execution so workflows can keep going (and recover) even when individual steps fail, time out, or need retries. The platform is closely aligned with Cloudflare’s ecosystem, using edge-native building blocks for execution, orchestration, and storage so workflows can run near users with low latency. ... -
7
handson-ml
Teaching you the fundamentals of Machine Learning in python
...The examples underscore fundamentals like bias-variance trade-offs, regularization, and proper validation, grounding learners before they move to deep nets. Even though the deep learning stack evolved, the classical ML sections remain highly relevant for production data problems. The code is crafted to be clear rather than clever, prioritizing readability for newcomers. As a historical snapshot and a still-useful primer, it pairs well with the second edition for understanding how the ecosystem matured. -
8
MiniMax-M2.1
MiniMax M2.1, a SOTA model for real-world dev & agents.
MiniMax-M2.1 is an open-source, state-of-the-art agentic language model released to democratize high-performance AI capabilities. It goes beyond a simple parameter upgrade, delivering major gains in coding, tool use, instruction following, and long-horizon planning. The model is designed to be transparent, controllable, and accessible, enabling developers to build autonomous systems without relying on closed platforms. MiniMax-M2.1 excels in real-world software engineering tasks, including... -
9
draw-a-ui
Draw wireframe sketches and generate HTML with AI vision models
draw-a-ui is an experimental open source application that converts hand-drawn interface wireframes into working HTML code using artificial intelligence. draw-a-ui combines the tldraw canvas drawing tool with a vision-capable language model to interpret user-created mockups and translate them into a single HTML layout styled with Tailwind CSS. When a user sketches a UI on the canvas, the application captures the current drawing as SVG, converts it into a PNG image, and sends that image to a... -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
Chat with LLMs Everywhere
Run PyTorch LLMs locally on servers, desktop and mobile
...It is intended primarily as a reference implementation that shows developers how to integrate large language models into applications without requiring a large or complex infrastructure stack. TorchChat supports running models through Python interfaces as well as integrating them directly into native applications written in languages such as C or C++. The project also demonstrates how modern LLMs like LLaMA-style models can be deployed locally while maintaining good performance across different hardware platforms. -
11
Nano-vLLM
A lightweight vLLM implementation built from scratch
...Despite its compact design, nano-vllm incorporates advanced optimization techniques such as prefix caching, tensor parallelism, and CUDA graph execution to achieve high performance during model inference. The engine is intended primarily for educational use, experimentation, and lightweight deployments where a full production-grade inference stack may be unnecessary. Its API closely mirrors that of the original vLLM framework, allowing developers familiar with vLLM to adopt the tool with minimal changes. -
12
FastVLM
This repository contains the official implementation of FastVLM
FastVLM is an efficiency-focused vision-language modeling stack that introduces FastViTHD, a hybrid vision encoder engineered to emit fewer visual tokens and slash encoding time, especially for high-resolution images. Instead of elaborate pruning stages, the design trades off resolution and token count through input scaling, simplifying the pipeline while maintaining strong accuracy. Reported results highlight dramatic speedups in time-to-first-token and competitive quality versus contemporary open VLMs, including comparisons across small and larger variants. ... -
13
Agents Towards Production
Code-first tutorials covering every layer of GenAI agents
Agents Towards Production is an opinionated, code-first playbook for taking AI agents from prototype to production-ready systems. Instead of focusing only on toy examples, it dives into every layer of an agent stack: orchestration, memory, RAG, tool and API integration, security, observability, deployment, evaluation, and UI. The repository is built around runnable tutorials, each in its own folder, often sponsored by or built in collaboration with infrastructure providers like LangChain, Redis, Bright Data, Contextual AI, Tavily, Runpod, Portia, and others. ... -
14
VideoChat
Real-time voice interactive digital human
...The system is customizable: you can define your own avatar appearance and voice, and it supports voice cloning so you can generate a new voice from a short 3–10 second reference sample. The tech stack integrates FunASR for speech recognition, Qwen for language understanding, multiple TTS engines like GPT-SoVITS, CosyVoice, or edge-tts, and MuseTalk for talking-head generation. -
15
Agentic Commerce Protocol (ACP)
Interaction model for connecting buyers to complete purchases
ACP is an open, draft specification for letting buyers, their AI agents, and businesses complete purchases through a standardized interaction model. It’s maintained by OpenAI and Stripe and licensed under Apache-2.0, with the goal of being easy to adopt alongside a merchant’s existing commerce stack rather than replacing it. The repository organizes the spec as human-readable RFCs plus machine-readable OpenAPI and JSON Schema definitions, along with worked examples and a changelog so integrators can track breaking changes. Practically, ACP defines three main pieces; a Product Feed for discovery, an Agentic Checkout API for stateful, in-conversation checkout, and a Delegated Payment flow so a merchant’s existing PSP securely handles payment credentials and settlement. ... -
16
Matcha-TTS
A fast TTS architecture with conditional flow matching
...The model is fully probabilistic, so it can generate diverse realizations of the same text while still sounding stable and intelligible. The repository provides an end-to-end TTS pipeline: a PyTorch/Lightning training stack, configuration files, pre-trained checkpoints, a command-line interface, and a Gradio app for interactive testing. Users can train on standard datasets like LJSpeech or plug in their own corpora, with helper tools for computing dataset statistics, extracting phoneme durations, and running multi-GPU training. -
17
Text-to-image Playground
A playground to generate images from any text prompt using SD
...The platform demonstrates how large generative models can be integrated into user-friendly tools for creative exploration and rapid prototyping. It also serves as a reference architecture for building full-stack generative AI applications that connect model inference pipelines with web interfaces. -
18
DeepSeek VL
Towards Real-World Vision-Language Understanding
DeepSeek-VL is DeepSeek’s initial vision-language model that anchors their multimodal stack. It enables understanding and generation across visual and textual modalities—meaning it can process an image + a prompt, answer questions about images, caption, classify, or reason about visuals in context. The model is likely used internally as the visual encoder backbone for agent use cases, to ground perception in downstream tasks (e.g. answering questions about a screenshot). -
19
Amphion
Toolkit for audio, music, and speech generation
...Built on the broader OpenMMLab ecosystem, Amphion follows modular design patterns and configuration systems similar to other OpenMMLab projects, easing adoption for users who are already familiar with that stack. -
20
autollm
Ship RAG based LLM web apps in seconds
autollm is an open-source Python framework designed to make it much faster to build retrieval-augmented generation applications and expose them as usable services with minimal setup. The project focuses on simplifying the usual stack of model selection, document ingestion, vector storage, querying, and API deployment into a more unified developer experience. Its core idea is that a developer can create a query engine from a document set in just a few lines and then turn that same engine into a FastAPI application almost instantly. AutoLLM supports a broad range of language models and vector databases, which makes it useful for teams that want flexibility without rewriting their application architecture every time they switch providers. ... -
21
axflow
The TypeScript framework for AI development
Axflow is a modular TypeScript framework designed to support the development of natural language powered AI applications. The framework provides a collection of independent modules that can be adopted individually or combined to create a full AI application stack. Its core SDK enables developers to integrate language model capabilities into web applications while maintaining strong modular design principles. Additional components support data ingestion, evaluation, and model interaction workflows that are commonly required when building production AI systems. For example, the framework includes modules for connecting application data to language models, evaluating the quality of model outputs, and building streaming user interfaces. ... -
22
Clarity AI
A Perplexity clone
Clarity AI is an AI-powered “search + chat” tool (similar in spirit to a simplified “AI-powered search engine / assistant”) created by Mckay Wrigley — intended to let users ask questions, get answers, and explore information via conversational interface rather than traditional search. The codebase (TypeScript) leverages LLMs / embeddings to process user queries, retrieve relevant data or context, and respond conversationally; this makes it useful as a personal knowledge assistant, research... -
23
UnionML
Build and deploy machine learning microservices
...Using industry-standard machine learning methods, implement endpoints for fetching data, training models, serving predictions (and much more) to write a complete ML stack in one place. Data science, ML engineering, and MLOps practitioners can all gather around UnionML apps as a way of defining a single source of truth about your ML system’s behavior. This helps you maintain consistent code across your ML stack, from training to prediction logic. -
24
Apache TVM
TVM Documentation in Chinese Simplified
tvm-cn is a community-driven project that provides Chinese documentation for the Apache TVM deep learning compiler stack. Apache TVM is an open-source system designed to optimize and deploy machine learning models efficiently across different hardware platforms such as CPUs, GPUs, and ARM devices. The goal of the repository is to centralize translated learning materials and technical documentation so that Chinese-speaking developers can study the TVM ecosystem more easily. -
25
WaveRNN
WaveRNN Vocoder + TTS
WaveRNN is a PyTorch implementation of DeepMind’s WaveRNN vocoder, bundled with a Tacotron-style TTS front end to form a complete text-to-speech stack. As a vocoder, WaveRNN models raw audio with a compact recurrent neural network that can generate high-quality waveforms more efficiently than many traditional autoregressive models. The repository includes scripts and code for preprocessing datasets such as LJSpeech, training Tacotron to produce mel spectrograms, training WaveRNN on those spectrograms (with optional GTA data), and finally generating audio. ...
