Search Results for "foundation"
Sort By:
Showing 32 open source projects for "foundation"
View related business solutions-
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
1
GLM-4.6
Agentic, Reasoning, and Coding (ARC) foundation models
GLM-4.6 is the latest iteration of Zhipu AI’s foundation model, delivering significant advancements over GLM-4.5. It introduces an extended 200K token context window, enabling more sophisticated long-context reasoning and agentic workflows. The model achieves superior coding performance, excelling in benchmarks and practical coding assistants such as Claude Code, Cline, Roo Code, and Kilo Code. -
2
GLM-5
From Vibe Coding to Agentic Engineering
GLM-5 is a next-generation open-source large language model (LLM) developed by the Z .ai team under the zai-org organization that pushes the boundaries of reasoning, coding, and long-horizon agentic intelligence. Building on earlier GLM series models, GLM-5 dramatically scales the parameter count (to roughly 744 billion) and expands pre-training data to significantly improve performance on complex tasks such as multi-step reasoning, software engineering workflows, and agent orchestration... -
3
GLM-V
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning
GLM-V is an open-source vision-language model (VLM) series from ZhipuAI that extends the GLM foundation models into multimodal reasoning and perception. The repository provides both GLM-4.5V and GLM-4.1V models, designed to advance beyond basic perception toward higher-level reasoning, long-context understanding, and agent-based applications. GLM-4.5V builds on the flagship GLM-4.5-Air foundation (106B parameters, 12B active), achieving state-of-the-art results on 42 benchmarks across image, video, document, GUI, and grounding tasks. ... -
4
Qwen-Image
Qwen-Image is a powerful image generation foundation model
Qwen-Image is a powerful 20-billion parameter foundation model designed for advanced image generation and precise editing, with a particular strength in complex text rendering across diverse languages, especially Chinese. Built on the MMDiT architecture, it achieves remarkable fidelity in integrating text seamlessly into images while preserving typographic details and layout coherence. -
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
LMOps
General technology for enabling AI capabilities w/ LLMs and MLLMs
LMOps is a research initiative and open-source toolkit focused on the development and operational management of AI applications built with large language models and generative AI systems. The project explores the technologies and methodologies required to move foundation models from research environments into production-grade AI products. It includes experimental tools and frameworks that help developers optimize prompts, design workflows for generative models, and manage the lifecycle of LLM-based systems. The initiative also investigates techniques for improving the reliability, scalability, and maintainability of applications powered by large models. ... -
6
StarVector
StarVector is a foundation model for SVG generation
StarVector is a multimodal foundation model designed for generating Scalable Vector Graphics (SVG) from images or textual descriptions. The system treats vector graphics creation as a code generation problem, producing SVG code that can render detailed vector images. Its architecture combines computer vision techniques with language modeling capabilities so it can understand visual inputs and textual prompts simultaneously. -
7
Granite 3.0 Language Models
New set of lightweight state-of-the-art, open foundation models
This repository introduces Granite 3.0 language models as lightweight, state-of-the-art open foundation models built to natively support multilinguality, coding, reasoning, and tool usage. A central goal is efficient deployment, including the potential to run on constrained compute resources while remaining useful for a broad span of enterprise tasks. The repo positions the models for both research and commercial use under an Apache-2.0 license, signaling permissive adoption paths. ... -
8
llama.cpp
LLM inference in C/C++
llama.cpp is a high-performance C and C++ project for running large language models locally and in the cloud with minimal setup. It is built around efficient inference, broad hardware support, and the GGUF model format. The project supports many model families and has become a major foundation for local AI tools, model serving, and embedded inference workflows. It provides command-line tools, a server mode with an OpenAI-compatible API style, model conversion utilities, and extensive backend acceleration options. llama.cpp runs on CPUs and GPUs, with support for Apple silicon, x86, RISC-V, CUDA, HIP, Vulkan, SYCL, Metal, and hybrid CPU-GPU execution. ... -
9
LLM Foundry
LLM training code for MosaicML foundation models
Introducing MPT-7B, the first entry in our MosaicML Foundation Series. MPT-7B is a transformer trained from scratch on 1T tokens of text and code. It is open source, available for commercial use, and matches the quality of LLaMA-7B. MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention at a cost of ~$200k. Large language models (LLMs) are changing the world, but for those outside well-resourced industry labs, it can be extremely difficult to train and deploy these models. ... -
Stop vibe-debugging.AppSignal's MCP server hands Claude, Cursor, or Zed your real errors, traces, and the deploy that shipped them. AI writes the fix; you review the diff.
-
10
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
GLM-4.5 is a cutting-edge open-source large language model designed by Z.ai for intelligent agent applications. The flagship GLM-4.5 model has 355 billion total parameters with 32 billion active parameters, while the compact GLM-4.5-Air version offers 106 billion total parameters and 12 billion active parameters. Both models unify reasoning, coding, and intelligent agent capabilities, providing two modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for... -
11
Cybersecurity AI
Cybersecurity AI (CAI), the framework for AI Security
CAI (Cybersecurity AI) is a lightweight open-source framework intended to help security practitioners build and deploy AI-assisted automation for defensive and offensive security workflows. The project frames itself as a practical foundation for “AI security,” focusing on turning security tasks into agentic workflows that can be composed, executed, and iterated on by practitioners. Rather than being a single-purpose tool, CAI is positioned as a framework that supports building multiple security automations and integrating them into existing processes. It is designed for real-world usability, aiming to reduce friction for teams experimenting with AI agents in security operations, assessment, and response contexts. ... -
12
LLaMA Models
Utilities intended for use with Llama models
This repository serves as the central hub for the Llama foundation model family, consolidating model cards, licenses and use policies, and utilities that support inference and fine-tuning across releases. It ties together other stack components (like safety tooling and developer SDKs) and provides canonical references for model variants and their intended usage. The project’s issues and releases reflect an actively used coordination point for the ecosystem, where guidance, utilities, and compatibility notes are published. ... -
13
CogView4
CogView4, CogView3-Plus and CogView3(ECCV 2024)
CogView4 is the latest generation in the CogView series of vision-language foundation models, developed as a bilingual (Chinese and English) open-source system for high-quality image understanding and generation. Built on top of the GLM framework, it supports multimodal tasks including text-to-image synthesis, image captioning, and visual reasoning. Compared to previous CogView versions, CogView4 introduces architectural upgrades, improved training pipelines, and larger-scale datasets, enabling stronger alignment between textual prompts and generated visual content. ... -
14
Prompt in-context learning
Resources for in-context learning and prompt engineering
...The project gathers research papers, tutorials, prompt examples, and practical guides that help developers and researchers learn how to design effective prompts for models such as GPT-3, ChatGPT, and other foundation models. In-context learning refers to the ability of language models to learn a task directly from examples provided in the prompt without updating the model’s parameters, allowing them to perform new tasks through demonstration alone. The repository organizes this growing field by categorizing materials related to prompt design strategies, chain-of-thought reasoning, agents, and general large language model usage. ... -
15
LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
LLMs-from-scratch is an educational codebase that walks through implementing modern large-language-model components step by step. It emphasizes building blocks—tokenization, embeddings, attention, feed-forward layers, normalization, and training loops—so learners understand not just how to use a model but how it works internally. The repository favors clear Python and NumPy or PyTorch implementations that can be run and modified without heavyweight frameworks obscuring the logic. Chapters... -
16
HolmesGPT
CNCF Sandbox Project
...Rather than requiring engineers to manually correlate large volumes of monitoring data, HolmesGPT automatically synthesizes evidence and presents explanations in natural language. The project is developed by Robusta and has been accepted as a Cloud Native Computing Foundation Sandbox project, highlighting its relevance to the cloud-native ecosystem. It is designed to operate as an automated troubleshooting assistant that can analyze incidents continuously and support on-call engineers during outages. -
17
ChatJS
Production-ready AI chat. Start here and make it your own
ChatJS is a production-ready AI chat foundation for developers who want to launch customizable chat applications without rebuilding common infrastructure from scratch. The project presents itself as a starting point that already includes authentication, model access, streaming, and tool support so teams can focus on their own product-specific features. Its stack is centered on modern TypeScript web development, using technologies such as Next.js, AI SDK tooling, PostgreSQL, Redis, and type-safe configuration patterns. ... -
18
NeMo Curator
Scalable data pre processing and curation toolkit for LLMs
NeMo Curator is a Python library specifically designed for fast and scalable dataset preparation and curation for large language model (LLM) use-cases such as foundation model pretraining, domain-adaptive pretraining (DAPT), supervised fine-tuning (SFT) and paramter-efficient fine-tuning (PEFT). It greatly accelerates data curation by leveraging GPUs with Dask and RAPIDS, resulting in significant time savings. The library provides a customizable and modular interface, simplifying pipeline expansion and accelerating model convergence through the preparation of high-quality tokens. ... -
19
tt-metal
TT-NN operator library, and TT-Metalium low level kernel programming
tt-metal, also referred to in its documentation as TT-Metalium, is Tenstorrent’s low-level software development kit for programming applications on Tenstorrent AI accelerators. The project is designed for developers who need direct access to the company’s Tensix processor architecture, exposing a programming model that is closer to hardware control than high-level inference frameworks. Instead of following a traditional GPU model centered on massive thread parallelism, the platform is built... -
20
Magicoder
Empowering Code Generation with OSS-Instruct
...The project focuses on improving the quality and diversity of code generation by training models with a novel dataset construction approach known as OSS-Instruct. This technique uses open-source code repositories as a foundation for generating more realistic and diverse instruction datasets for training language models. By grounding training data in real open-source examples, Magicoder aims to reduce bias and improve the reliability of code generation results compared to models trained solely on synthetic instructions. The project includes model implementations, training resources, and evaluation benchmarks that demonstrate how the approach improves instruction-following and code synthesis capabilities. ... -
21
llms-from-scratch-cn
Build a large language model from 0 only with Python foundation
llms-from-scratch-cn is an educational open-source project designed to teach developers how to build large language models step by step using practical code and conceptual explanations. The repository provides a hands-on learning path that begins with the fundamentals of natural language processing and gradually progresses toward implementing full GPT-style architectures from the ground up. Rather than focusing on using pre-trained models through APIs, the project emphasizes understanding... -
22
Flexpilot IDE
Open-Source AI Native IDE
Flexpilot IDE is an open-source integrated development environment designed specifically for AI-assisted software development. Built as a fork of Visual Studio Code, the project provides a familiar development interface while integrating advanced AI capabilities directly into the coding workflow. The platform is designed to be privacy-focused and flexible, allowing developers to use their own API keys for different large language models rather than relying on a single proprietary AI... -
23
Qwen3-Omni
Qwen3-omni is a natively end-to-end, omni-modal LLM
Qwen3-Omni is a natively end-to-end multilingual omni-modal foundation model that processes text, images, audio, and video and delivers real-time streaming responses in text and natural speech. It uses a Thinker-Talker architecture with a Mixture-of-Experts (MoE) design, early text-first pretraining, and mixed multimodal training to support strong performance across all modalities without sacrificing text or image quality. -
24
MiniMax-M2.5
State of the art LLM and coding model
MiniMax-M2.5 is a state-of-the-art foundation model extensively trained with reinforcement learning across hundreds of thousands of real-world environments. It delivers leading performance in coding, agentic tool use, search, and complex office workflows, achieving top benchmark scores such as 80.2% on SWE-Bench Verified and 76.3% on BrowseComp. Designed to reason efficiently and decompose tasks like an experienced architect, M2.5 plans features, structure, and system design before generating code. ... -
25
MiniMax-M1
Open-weight, large-scale hybrid-attention reasoning model
MiniMax-M1 is presented as the world’s first open-weight, large-scale hybrid-attention reasoning model, designed to push the frontier of long-context, tool-using, and deeply “thinking” language models. It is built on the MiniMax-Text-01 foundation and keeps the same massive parameter budget, but reworks the attention and training setup for better reasoning and test-time compute scaling. Architecturally, it combines Mixture-of-Experts layers with lightning attention, enabling the model to support a native context length of 1 million tokens while using far fewer FLOPs than comparable reasoning models for very long generations. ...
