Search Results for "stack" - Page 5
Sort By:
Showing 162 open source projects for "stack"
View related business solutions-
$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.
-
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.
-
1
A.I.G (AI-Infra-Guard)
A full-stack AI Red Teaming platform securing AI ecosystems
AI-Infra-Guard is an open-source AI red teaming platform for evaluating security risks across modern AI ecosystems. It combines scanning for AI agents, agent skills, MCP servers, AI infrastructure, and OpenClaw deployments. Its infrastructure scanner fingerprints AI services and checks them against a large library of known vulnerabilities. Agent and skill analysis detects risks involving malicious instructions, unsafe code execution, privilege abuse, compromised tools, and insecure... -
2
JoyAI-VL-Interaction
An Open Real-time Video-Language Interaction System
JoyAI-VL-Interaction is an open real-time video-language interaction system built around an 8B-scale vision-first model. It is designed to watch a webcam or livestream continuously and decide whether to speak, stay silent, or delegate a harder task. Unlike turn-based assistants, it focuses on event-driven interaction where timing matters as much as answer quality. The repository releases the model, training recipe, time-aligned interaction data, and deployable system together. Its system... -
3
TokenSpeed
TokenSpeed is a speed-of-light LLM inference engine
...The project is focused on the specific needs of agentic systems, where latency, throughput, and efficient scheduling matter across many short or tool-heavy requests. It builds on ideas and components from the broader open-source inference ecosystem while presenting its own execution stack. TokenSpeed is useful for developers building local or server-side LLM infrastructure for agents, coding systems, and high-volume AI applications. Its main value is providing an inference layer optimized for fast token generation under practical agent workloads. -
4
OpenMonoAgent
Terminal-native coding agent powered by local LLMs
...The system can run on CPU or GPU and is designed to auto-configure itself when possible. OpenMonoAgent.ai is best suited for developers who want a local AI development stack with no API keys, no cloud dependency, and no telemetry. -
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
5
II ElevenLabs UI
Component library and custom registry built on top of shadcn/ui
ElevenLabs UI is an open-source component library designed to accelerate the development of multimodal AI applications, particularly those involving voice agents and audio-based interactions. Built on top of modern frontend tooling such as React, Tailwind CSS, and shadcn/ui, it provides a collection of pre-built, customizable components that developers can easily integrate into their applications. The library includes specialized UI elements such as audio players, waveform visualizers,... -
6
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... -
7
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... -
8
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. -
9
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. -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
10
A.I.G (AI-Infra-Guard)
Full-stack AI Red Teaming platform
AI-Infra-Guard is a powerful open-source security platform from Tencent’s Zhuque Lab designed to assess the safety and resilience of AI infrastructures, codebases, and components through automated scanning and evaluation tools. It brings together AI infrastructure vulnerability scanning, MCP server risk analysis, and jailbreak evaluation into a unified workflow so that enterprises and individuals can identify critical security issues without relying on external services. Users can deploy it... -
11
Personal AI Infrastructure
Agentic AI Infrastructure for magnifying HUMAN capabilities
...Unlike once-stateless chatbots, this platform captures context, memory, goals, preferences, and feedback to enable an AI that understands you and improves over time, using a full agentic stack rather than simple question-answer loops. PAI blends tools like browsing, code editing, execution, and more into a continuous Observe → Think → Plan → Execute → Verify → Learn cycle, letting the system refine its behavior with each use. Its architecture supports long-term memory, verification of actions, and ongoing self-improvement, blurring the line between “assistant” and persistent, evolving collaborator. -
12
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... -
13
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. ... -
14
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. -
15
MCP Server Chart
A visualization mcp contains 25+ visual charts
mcp-server-chart is a TypeScript Model Context Protocol (MCP) server that turns AntV’s visualization stack into agent-callable tools for automatic chart generation and lightweight data analysis. Out of the box it exposes more than 20–25 chart generators—covering staples like bar, line, area, histogram and pie, plus advanced visuals such as dual-axes, heatmaps, radar, flow and fishbone diagrams—so an AI client can request a chart and receive an image URL in return. -
16
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... -
17
Swirl
Swirl queries any number of data sources with APIs
...It's intended for use by developers and data scientists who want to solve multi-silo search problems from enterprise search to new monitoring & alerting solutions that push information to users continuously. Built on the Python/Django/RabbitMQ stack, SWIRL includes connectors to Apache Solr, ChatGPT, Elastic, OpenSearch | PostgreSQL, Google BigQuery plus generic HTTP/GET/JSON with configurations for premium services. -
18
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... -
19
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. -
20
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. -
21
Self-hosted AI Package
Run all your local AI together in one package
Self-hosted AI Package is an open-source Docker Compose-based starter kit that makes it easy to bootstrap a full local AI and low-code development environment with commonly used open tools, empowering developers to run LLMs and AI workflows entirely on their infrastructure. The stack typically includes Ollama for running local large language models, n8n as a low-code workflow automation platform, Supabase for database and vector storage, Open WebUI for interacting with models, Flowise for agent building, and additional services like SearXNG, Neo4j, and Langfuse for search, knowledge graphs, and observability. ... -
22
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. ... -
23
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. ... -
24
NVIDIA NeMo Framework
Scalable generative AI framework built for researchers and developers
NVIDIA NeMo is a scalable, cloud-native generative AI framework aimed at researchers and PyTorch developers working on large language models, multimodal models, and speech AI (ASR and TTS), with growing support for computer vision. It provides collections of domain-specific modules and reference implementations that make it easier to pre-train, fine-tune, and deploy very large models on multi-GPU and multi-node infrastructure. NeMo 2.0 introduces a Python-based configuration system,... -
25
DGL
Python package built to ease deep learning on graph
Build your models with PyTorch, TensorFlow or Apache MXNet. Fast and memory-efficient message passing primitives for training Graph Neural Networks. Scale to giant graphs via multi-GPU acceleration and distributed training infrastructure. DGL empowers a variety of domain-specific projects including DGL-KE for learning large-scale knowledge graph embeddings, DGL-LifeSci for bioinformatics and cheminformatics, and many others. We are keen to bringing graphs closer to deep learning researchers....
