Search Results for "stage" - Page 3
Sort By:
Showing 153 open source projects for "stage"
View related business solutions-
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.
-
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
1
BigMac
An open-source toolkit for BigMac-style pipeline-parallel training
...A Megatron-Core reference backend and Qwen3 and Qwen3-VL tutorials help developers connect the approach to real training workflows. The simulator lets researchers visualize schedules, compare pipeline strategies, and model timing imbalances caused by compute cost, input size, or uneven stage partitioning. Profiling tools also expose per-operator traces for diagnosing pipeline performance before or during experiments. -
2
LangChain Open Deep Research
Fully open source deep research agent
Open Deep Research is a configurable, fully open-source agent for producing detailed research reports from complex questions. It separates work across models used for summarization, active research, information compression, and final report generation. Users can select from multiple language model providers as long as the chosen models support tool calling and structured outputs. Search can be powered by several APIs, native provider search, or external tools connected through MCP. The agent... -
3
Shepherd
Runtime substrate that turns agent's execution into a Git-like trace
Shepherd is an early-stage Python runtime for building agents and meta-agents around reversible, inspectable execution traces. It records interactions and workspace changes as durable run histories instead of immediately applying an agent's output. Each result can be reviewed, executed separately, selected, merged, released, or discarded. Tasks are declared as Python functions whose signatures and documentation define the agent contract and required resources. -
4
gzh-design-skill
An AI-agent skill that turns Markdown into paste-ready WeChat article
gzh-design-skill is an AI-agent workflow that converts Markdown into polished HTML for the WeChat Official Account editor. It uses fully inline styling and platform-aware markup so pasted articles retain their formatting after WeChat filters the content. The skill recognizes headings, quotations, lists, code blocks, images, highlights, and other Markdown structures before assembling them from reusable components. Six built-in themes cover tutorials, reviews, essays, reports, technology... -
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
Cognita
Open source RAG framework for building scalable modular AI apps
...It addresses the gap between quick experimentation in notebooks and the complexity of deploying scalable AI systems by introducing a modular and API-driven architecture. Cognita provides reusable components such as parsers, data loaders, embedders, retrievers, and query controllers, allowing teams to customize each stage of the RAG pipeline independently. It includes both a backend service and a frontend interface, enabling users to upload documents, experiment with configurations, and perform question-answering tasks interactively. Cognita supports incremental indexing, meaning it processes only new or updated data to reduce computational overhead and improve efficiency. -
6
Parallax
Parallax is a distributed model serving framework
...Instead of relying on centralized GPU clusters in data centers, the system allows multiple heterogeneous machines to collaborate in serving AI inference workloads. Parallax divides model layers across different nodes and dynamically coordinates them to form a complete inference pipeline. A two-stage scheduling architecture determines how model layers are allocated to available hardware and how requests are routed across nodes during execution. This scheduling system optimizes latency, throughput, and hardware utilization even when nodes have different computational capabilities. The platform also supports model sharding and pipeline parallelism, allowing very large models to run across distributed resources. -
7
DATAGEN
AI-driven multi-agent research assistant automating hypothesis
...The system coordinates multiple specialized AI agents that collaborate to perform tasks such as hypothesis generation, data collection, analysis, visualization, and report creation. Instead of requiring users to manually orchestrate each stage of a research process, the platform allows these agents to coordinate automatically and handle the workflow end-to-end. The project integrates several modern AI frameworks including LangChain, LangGraph, and large language models to manage reasoning and data processing tasks. Through this architecture, the system can combine structured data analysis with natural language reasoning to generate insights and research outputs. ... -
8
video2robot
End-to-end pipeline converting generative videos
...This workflow allows users to generate robot motion files that specify joint angles, root positions, and orientations that can be deployed on supported robot platforms (e.g., Unitree models). Video2robot includes scripts for each stage of the pipeline (generation, extraction, conversion, visualization) and can run as a CLI or through a basic web UI. -
9
Coconut
Training Large Language Model to Reason in a Continuous Latent Space
Coconut is the official PyTorch implementation of the research paper “Training Large Language Models to Reason in a Continuous Latent Space.” The framework introduces a novel method for enhancing large language models (LLMs) with continuous latent reasoning steps, enabling them to generate and refine reasoning chains within a learned latent space rather than relying solely on discrete symbolic reasoning. It supports training across multiple reasoning paradigms—including standard... -
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.
-
10
IMS Toucan
Controllable and fast Text-to-Speech for over 7000 languages
IMS-Toucan is a toolkit for training, using, and teaching state-of-the-art text-to-speech systems, built at the Institute for Natural Language Processing (IMS), University of Stuttgart. It is the official home of ToucanTTS, a massively multilingual TTS system designed to support over 7,000 languages with a single unified framework. The toolkit focuses on being fast and controllable while not requiring huge amounts of compute, making it practical for research labs and smaller teams. It... -
11
Jenkins-Zero-To-Hero
Install Jenkins and configure Docker
...The course is designed around running Jenkins on an AWS EC2 instance, guiding you through installing Java, configuring Jenkins, and exposing it safely via security group rules. From there, it covers installing plugins like Docker Pipeline, configuring Docker as an agent, and wiring up multi-stage and multi-agent pipelines. The folder structure includes practical examples such as java-maven-sonar-argocd-helm-k8s and python-jenkins-argocd-k8s, showing real CI/CD flows that build, test, analyze, containerize, and deploy apps to Kubernetes via Argo CD in a GitOps style. The README walks through detailed step-by-step commands and screenshots, making it accessible to beginners who are unfamiliar with Jenkins, AWS, or pipelines. -
12
Ling-V2
Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI
...It introduces highly sparse architectures where only a fraction of the model’s parameters are activated per input token, enabling models like Ling-mini-2.0 to achieve reasoning and instruction-following capabilities on par with much larger dense models while remaining significantly more computationally efficient. Trained on more than 20 trillion tokens of high-quality data and enhanced through multi-stage supervised fine-tuning and reinforcement learning, Ling-V2’s models demonstrate strong general reasoning, mathematical problem-solving, coding understanding, and knowledge-intensive task performance. -
13
Synthetic Data Kit
Tool for generating high quality Synthetic datasets
Synthetic Data Kit is a CLI-centric toolkit for generating high-quality synthetic datasets to fine-tune Llama models, with an emphasis on producing reasoning traces and QA pairs that line up with modern instruction-tuning formats. It ships an opinionated, modular workflow that covers ingesting heterogeneous sources (documents, transcripts), prompting models to create labeled examples, and exporting to fine-tuning schemas with minimal glue code. The kit’s design goal is to shorten the “data... -
14
Ring
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI
Ring is a reasoning Mixture-of-Experts (MoE) large language model (LLM) developed by inclusionAI. It is built from or derived from Ling. Its design emphasizes reasoning, efficiency, and modular expert activation. In its “flash” variant (Ring-flash-2.0), it optimizes inference by activating only a subset of experts. It applies reinforcement learning/reasoning optimization techniques. Its architectures and training approaches are tuned to enable efficient and capable reasoning performance.... -
15
The Alignment Handbook
Robust recipes to align language models with human and AI preferences
The Alignment Handbook is an open-source resource created to provide practical guidance for aligning large language models with human preferences and safety requirements. The project focuses on the post-training stage of model development, where models are refined after pre-training to behave more helpfully, safely, and reliably in real-world applications. It provides detailed training recipes that explain how to perform tasks such as supervised fine-tuning, preference modeling, and reinforcement learning from human feedback. The handbook also includes reproducible workflows for training instruction-following models and evaluating alignment quality across different datasets and benchmarks. ... -
16
Build Your Own OpenClaw
A step-by-step guide to build your own AI agent
Build Your Own OpenClaw is a step-by-step educational framework that teaches developers how to construct a fully functional AI agent system from scratch, gradually evolving from a simple chat loop into a multi-agent, production-ready architecture. The project is structured into 18 progressive stages, each introducing a new concept such as tool usage, memory persistence, event-driven design, and multi-agent coordination, with each step including both explanatory documentation and runnable... -
17
kg-gen
Knowledge Graph Generation from Any Text
kg-gen is an open-source framework developed by the STAIR Lab that automatically generates knowledge graphs from unstructured text using large language models. The system is designed to transform plain text sources such as documents, articles, or conversation transcripts into structured graphs composed of entities and relationships. Instead of relying on traditional rule-based extraction techniques, KG-Gen uses language models to identify entities and their relationships, producing... -
18
QAnything
Question and Answer based on Anything
...Users can upload local files and receive fast, reliable answers based on the indexed content. The system supports formats such as PDF, Word, PowerPoint, Excel, Markdown, email, text, images, CSV, and web links. Its retrieval process uses a two-stage vector and reranking approach to maintain answer quality as the knowledge base grows. It is built to be hardware-friendly, easy to deploy with Docker, and usable across Windows, macOS, and Linux. -
19
MARS5
MARS5 speech model (TTS) from CAMB.AI
MARS5-TTS is CAMB.AI’s open-source English speech model designed for high-quality text-to-speech and voice emulation. It uses a two-stage architecture that combines an autoregressive (AR) model with a non-autoregressive (NAR) model, giving it both expressiveness and speed. The model is built to handle prosodically challenging content such as sports commentary, anime dialogue, and other high-energy or highly varied speech patterns with realistic rhythm and intonation. -
20
ManagerSheet
A one-page investment portfolio report
ManagerSheet is a one-page investment portfolio report, that analyses and presents an investment portfolio with respect to: - Performance - Investment style - Risk More information on the report concept and instructions on how to create one's own portfolio reports can be found at the ManagerSheet Web Site under the "Documentation" section. Please note that the project is in alpha stage. -
21
NAVAL-SEM
Award-winning open-source offline SEM platform for PLS-SEM & CB-SEM
NAVAL-SEM is an award-winning, free and open-source offline Structural Equation Modeling (SEM) platform supporting PLS-SEM and CB-SEM workflows. Designed for researchers, PhD scholars, professors, and analysts, it provides visual model building, measurement assessment, structural model analysis, and reproducible research workflows without subscriptions or cloud dependency. Features include: • PLS-SEM & CB-SEM • Bootstrapping, mediation, moderation & conditional process analysis • HTMT,... -
22
NVIDIA Merlin
Library providing end-to-end GPU-accelerated recommender systems
...The library enables data scientists, machine learning engineers, and researchers to build high-performing recommenders at scale. Merlin includes tools to address common feature engineering, training, and inference challenges. Each stage of the Merlin pipeline is optimized to support hundreds of terabytes of data, which is all accessible through easy-to-use APIs. For more information, see NVIDIA Merlin on the NVIDIA developer website. Transform data (ETL) for preprocessing and engineering features. Accelerate your existing training pipelines in TensorFlow, PyTorch, or FastAI by leveraging optimized, custom-built data loaders. ... -
23
minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm
...The repository is structured as a teaching-oriented implementation that shows how to train a tokenizer by learning merge rules, then apply those merges to encode text into token IDs and decode tokens back into text. It is intentionally small and readable so developers can understand each stage of BPE, including the mechanics of pair counting, merge application, and vocabulary growth. The project is especially useful for practitioners who want to demystify how LLM tokenizers work or who need a lightweight reference implementation for experimentation. -
24
FreeAskInternet
FreeAskInternet is a completely free running search aggregator
...The web interface is designed for desktop and mobile use and exposes the service only on the local machine by default. Docker Compose provides a straightforward deployment path without requiring a dedicated GPU. The project is still described as early-stage, and actual privacy depends partly on whether users select a local or external model provider. -
25
SalesGPT
Context-aware AI Sales Agent to automate sales outreach
This repo is an implementation of a context-aware AI Agent for Sales using LLMs and can work across voice, email and texting (SMS, WhatsApp, WeChat, Weibo, Telegram, etc.). SalesGPT is context-aware, which means it can understand what stage of a sales conversation it is in and act accordingly. Moreover, SalesGPT has access to tools, such as your own pre-defined product knowledge base, significantly reducing hallucinations.
