Search Results for "memory" - Page 10
Sort By:
Showing 499 open source projects for "memory"
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.
-
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
1
Lightweight' GAN
Implementation of 'lightweight' GAN, proposed in ICLR 2021
...The general recommendation is to use suitable augs for your data and as many as possible, then after some time of training disable the most destructive (for image) augs. You can turn on automatic mixed precision with one flag --amp. You should expect it to be 33% faster and save up to 40% memory. Aim is an open-source experiment tracker that logs your training runs, and enables a beautiful UI to compare them. -
2
BigMac
An open-source toolkit for BigMac-style pipeline-parallel training
BigMac is an open-source toolkit for pipeline-parallel training of multimodal large language models. It preserves optimized language-model pipeline schedules while placing encoder and generator work around them. This design reduces activation memory without bringing back cross-module pipeline bubbles. Its scheduler creates global operator plans, while its executor runs those plans through a shared schedule abstraction. 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. ... -
3
Swarms
Enterprise multi-agent orchestration framework for scalable AI apps
...It supports integration with multiple model providers and existing ecosystems, allowing developers to combine different AI tools and frameworks within a unified system. Swarms also includes mechanisms for agent lifecycle management, memory handling, and dynamic composition, making it adaptable to evolving workloads. Additionally, it focuses on developer productivity through APIs, CLI tools, and templates that simplify building and deploying agent-based applications. -
4
Engram
A New Axis of Sparsity for Large Language Models
...It provides utilities to generate embeddings from text or other structured data, index them using efficient approximate nearest neighbor algorithms, and perform real-time similarity queries even on large corpora. Engineered with speed and memory efficiency in mind, Engram supports batched indexing, incremental updates, and custom distance metrics so developers can tailor search behaviors to their domain’s needs. In addition to raw similarity search, the project includes tools for clustering, ranking, and filtering results, enabling richer user experiences like “related content”, semantic auto-completion, and contextual filtering. -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
5
Z80-μLM
Z80-μLM is a 2-bit quantized language model
...The project sits at the intersection of machine learning and systems constraints, showing how model architecture, quantization, and inference code generation can be adapted to extreme memory and compute limits. It also functions as an educational reference for how to reduce inference to operations that fit an old-school instruction set and runtime environment. -
6
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model
ChatGLM-6B is an open bilingual (Chinese + English) conversational language model based on the GLM architecture, with approximately 6.2 billion parameters. The project provides inference code, demos (command line, web, API), quantization support for lower memory deployment, and tools for finetuning (e.g., via P-Tuning v2). It is optimized for dialogue and question answering with a balance between performance and deployability in consumer hardware settings. Support for quantized inference (INT4, INT8) to reduce GPU memory requirements. Automatic mode switching between precision/memory tradeoffs (full/quantized). -
7
GRR
GRR Rapid Response, remote live forensics for incident response
GRR Rapid Response is an incident response framework focused on remote live forensics. It consists of a python client (agent) that is installed on target systems, and python server infrastructure that can manage and talk to clients. The goal of GRR is to support forensics and investigations in a fast, scalable manner to allow analysts to quickly triage attacks and perform analysis remotely. GRR client is deployed on systems that one might want to investigate. On every such system, once... -
8
DocArray
The data structure for multimodal data
...Data in transit: optimized for network communication, ready-to-wire at anytime with fast and compressed serialization in Protobuf, bytes, base64, JSON, CSV, DataFrame. Perfect for streaming and out-of-memory data. One-stop k-NN: Unified and consistent API for mainstream vector databases. -
9
DeepSpeed
Deep learning optimization library: makes distributed training easy
DeepSpeed is an easy-to-use deep learning optimization software suite that enables unprecedented scale and speed for Deep Learning Training and Inference. With DeepSpeed you can: 1. Train/Inference dense or sparse models with billions or trillions of parameters 2. Achieve excellent system throughput and efficiently scale to thousands of GPUs 3. Train/Inference on resource constrained GPU systems 4. Achieve unprecedented low latency and high throughput for inference 5. Achieve extreme... -
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.
-
10
AWS Serverless Application Model
An open-source framework for building serverless applications
The AWS Serverless Application Model (SAM) is an open-source framework for building serverless applications. It provides shorthand syntax to express functions, APIs, databases, and event source mappings. With just a few lines per resource, you can define the application you want and model it using YAML. During deployment, SAM transforms and expands the SAM syntax into AWS CloudFormation syntax, enabling you to build serverless applications faster. To get started with building SAM-based... -
11
BeeAI Framework
Build production-ready AI agents in both Python and Typescript
BeeAI Framework is an open-source, production-grade toolkit designed for building intelligent AI agents and complex multi-agent systems that can reason, act, and collaborate to solve real-world problems at scale. It goes beyond simple prompt-based interactions by introducing rule-based governance and constraint enforcement, enabling developers to create agents with predictable and controllable behavior while still preserving advanced reasoning capabilities. The framework supports both Python... -
12
deepjazz
Deep learning driven jazz generation using Keras & Theano
...The repository demonstrates how machine learning can learn musical structure and produce original compositions. It uses the Keras and Theano libraries to build a two-layer Long Short-Term Memory network capable of learning temporal patterns in music. The system analyzes musical sequences from an input MIDI file and then generates new musical notes that follow similar stylistic patterns. The project was originally created during a hackathon and was designed to show how neural networks can emulate creative tasks traditionally associated with human musicians. ... -
13
LLM-Pruner
On the Structural Pruning of Large Language Models
LLM-Pruner is an open-source framework designed to compress large language models through structured pruning techniques while maintaining their general capabilities. Large language models often require enormous computational resources, making them expensive to deploy and inefficient for many practical applications. LLM-Pruner addresses this issue by identifying and removing non-essential components within transformer architectures, such as redundant attention heads or feed-forward... -
14
Cradle framework
The Cradle framework is a first attempt at General Computer Control
...This approach allows agents to interact with any software interface without relying on specialized APIs or predefined automation scripts. The framework integrates reasoning, planning, and memory modules that help the agent understand its environment and execute long sequences of actions. Cradle agents are capable of performing tasks across a wide variety of environments, including computer applications and video games, demonstrating the generality of the approach. The architecture includes modules that allow agents to observe their environment, reflect on past actions, plan future steps, and accumulate useful skills for later tasks. -
15
MatMul-Free LM
Implementation for MatMul-free LM
...The architecture relies on quantization-aware training and lightweight operations to replace conventional dense matrix multiplications with more efficient alternatives. These optimizations can significantly reduce memory consumption and potentially improve computational efficiency during both training and inference. The repository provides implementations of models at several parameter scales and includes tools for experimenting with the architecture using modern machine learning frameworks. -
16
LuxTTS
A high-quality rapid TTS voice cloning model
...Intended for developers, hobbyists, and creators, the repository includes installation instructions, usage examples, and Python APIs that make it feasible to integrate the model in local workflows, web demos, or production systems. Its design emphasizes efficiency and practicality, fitting within modest GPU memory footprints. -
17
LMCache
Supercharge Your LLM with the Fastest KV Cache Layer
LMCache is an extension layer for LLM serving engines that accelerates inference, especially with long contexts, by storing and reusing key-value (KV) attention caches across requests. Instead of rebuilding KV states for repeated or shared text segments, LMCache persists and retrieves them from multiple tiers—GPU memory, CPU DRAM, and local disk—then injects them into subsequent requests to reduce TTFT and increase throughput. Its design supports reuse beyond strict prefix matching and enables sharing across serving instances, improving efficiency under real multi-tenant traffic. The broader project includes examples, tests, a server component, and public posts describing cross-engine sharing and inter-GPU KV transfers. ... -
18
DINOv2
PyTorch code and models for the DINOv2 self-supervised learning
...The repository includes code for training, evaluating, and feature extraction, with utilities to run k-NN or linear evaluation baselines to assess representation quality. Pretrained checkpoints cover multiple model sizes so practitioners can trade accuracy for speed and memory depending on their deployment constraints. -
19
tsai
Time series Timeseries Deep Learning Machine Learning Pytorch fastai
...If you require any of the dependencies that is not installed, tsai will ask you to install it when necessary) We've also added a new PredictionDynamics callback that will display the predictions during training. This is the type of output you would get in a classification task. New tutorial notebook on how to train your model with larger-than-memory datasets in less time achieving up to 100% GPU usage! See our new tutorial notebook on how to track your experiments with Weights & Biases -
20
Pal
A personal context-agent that learns how you work
Pal is an open-source AI personal agent built within the Agno ecosystem that functions as an intelligent digital assistant designed to learn from user activity over time. The system acts as an AI-powered “second brain” capable of capturing, organizing, and retrieving personal knowledge such as notes, bookmarks, research findings, people, and meeting information. Instead of acting as a simple chatbot, Pal continuously builds a structured database of a user’s knowledge and context so it can... -
21
NSync
nsync is a C library that exports various synchronization primitives
...This approach simplifies concurrency management and often improves readability and maintainability of multithreaded code. The library emphasizes efficiency, with locks and condition variables occupying minimal memory and supporting cancellation mechanisms through nsync_note objects rather than thread-level cancellation. Designed with portability and performance in mind, nsync can be compiled on Unix-like systems and Windows using a C90 compiler. -
22
Scrapling
An adaptive Web Scraping framework
...Its powerful spider system supports multi-session crawling, pause and resume functionality, and real-time streaming of scraped data. Scrapling combines high performance, memory efficiency, and extensive async support to deliver blazing-fast scraping workflows. With a developer-friendly API, CLI tools, MCP server integration for AI-assisted extraction, and Docker support, it offers a complete solution for modern web scrapers. -
23
OpenAI Swarm
Educational framework exploring multi-agent orchestration
Swarm focuses on making agent coordination and execution lightweight, highly controllable, and easily testable. It accomplishes this through two primitive abstractions; Agents and handoffs. An Agent encompasses instructions and tools, and can at any point choose to hand off a conversation to another Agent. These primitives are powerful enough to express rich dynamics between tools and networks of agents, allowing you to build scalable, real-world solutions while avoiding a steep learning... -
24
Universal Tool Calling Protocol (UTCP)
Official python implementation of UTCP. UTCP is an open standard
The python-utcp repository is the official Python SDK implementation of the Universal Tool Calling Protocol (UTCP). UTCP is an open, modern standard designed to let AI agents call any tool or API directly—over HTTP, CLI, WebSocket, gRPC, and more—without the overhead of extra wrapper layers or middleware. It leverages a modular, plugin-based architecture built around Pydantic models and separates the core functionality into a lightweight client and extensible protocol plugins, enabling... -
25
Qiling
Qiling Advanced Binary Emulation Framework
...Using Qiling Framework saves you time. The API-rich Qiling Framework brings reverse and instrument binary to the next level quicker. Additionally, Qiling provides API access to register, memory, filesystem, operating system and debugger. Qiling also provides virtual machine-level API such as save and restore execution state. It combines binary instrumentation and binary emulation into one single framework.