Search Results for "memory usage"
Sort By:
Showing 103 open source projects for "memory usage"
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.
-
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.
-
1
AirLLM
AirLLM 70B inference with single 4GB GPU
AirLLM is an open source Python library that enables extremely large language models to run on consumer hardware with very limited GPU memory. The project addresses one of the main barriers to local LLM experimentation by introducing a memory-efficient inference technique that loads model layers sequentially rather than storing the entire model in GPU memory. This layer-wise inference approach allows models with tens of billions of parameters to run on devices with only a few gigabytes of... -
2
leak-check
Personal Information “Leakage ” Detection Interface
leak-check is a utility designed to help developers detect memory leaks and resource mismanagement in applications. It provides tools to monitor allocations, track usage patterns, and identify potential leaks during runtime. The project focuses on improving application stability by highlighting inefficiencies in memory handling. It can be integrated into development workflows to catch issues early in the debugging process. leak-check is particularly useful in performance-critical applications where memory management is essential. ... -
3
HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
...The framework aims to push the boundaries of video generation quality, incorporating multiple innovative approaches to improve the realism and coherence of the generated content. Release of FP8 model weights to reduce GPU memory usage / improve efficiency. Parallel inference code to speed up sampling, utilities and tests included. -
4
Hermes Web UI
The best way to use Hermes Agent from the web or from your phone
...It offers a clean, multi-panel layout that includes chat interaction, session management, and workspace file browsing. The interface allows users to manage agent sessions, configure models, and interact with persistent memory systems directly from a web environment. It is built using simple technologies like Python and vanilla JavaScript, avoiding complex frontend frameworks. The UI supports real-time interaction, context tracking, and visualization of token usage. It connects to a self-hosted agent that continuously learns and evolves over time. The project emphasizes usability, accessibility, and seamless integration with existing workflows. -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
5
Hello-Agents
Building an Intelligent Agent from Scratch
Hello Agents is an open educational project designed to teach developers how to understand, design, and build AI-native agents from the ground up through structured tutorials and practical examples. The project focuses on guiding learners beyond superficial framework usage toward deeper comprehension of agent architecture, reasoning loops, and real-world implementation patterns. It walks users through core concepts such as ReAct-style reasoning, tool usage, memory handling, and multi-step task execution, enabling hands-on experimentation with modern LLM-powered agent systems. The repository is structured as a progressive learning path, combining theory, exercises, and runnable code so users can incrementally build more capable agents. ... -
6
QwenPaw
A personal AI assistant, easy to install
QwenPaw is an AI agent framework developed by the AgentScope ecosystem to provide a desktop-style intelligent assistant powered by Qwen language models and modular agent orchestration. The project combines conversational AI, memory systems, tool usage, workflow automation, and multimodal interaction into a unified assistant environment designed for daily productivity and experimentation. It supports structured reasoning, autonomous task execution, and integration with external tools and APIs, allowing the assistant to perform actions beyond standard chatbot conversations. ... -
7
MemU
MemU is an open-source memory framework for AI companions
MemU is an agentic memory layer for LLM applications, specifically designed for AI companions. Transform your memory into an intelligent file system that automatically organizes, connects, and evolves with your memories. Simple, fast, and reliable memory infrastructure for AI applications. Powerful tools and dedicated support to scale your AI applications with confidence. -
8
Tencent-Hunyuan-Large
Open-source large language model family from Tencent Hunyuan
...It is designed with long-context capabilities, quantization support, and high performance on benchmarks across general reasoning, mathematics, language understanding, and Chinese / multilingual tasks. It aims to provide competitive capability with efficient deployment and inference. FP8 quantization support to reduce memory usage (~50%) while maintaining precision. High benchmarking performance on tasks like MMLU, MATH, CMMLU, C-Eval, etc. -
9
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
...In large language models, the key-value cache stores intermediate attention states that enable efficient token generation during inference, but these caches can consume large amounts of GPU memory when handling long contexts. KVCache-Factory provides a platform for implementing and evaluating multiple compression strategies that reduce memory usage while preserving model performance. The framework integrates several state-of-the-art methods such as PyramidKV, SnapKV, H2O, and StreamingLLM, allowing researchers to compare and experiment with different approaches within the same environment. ... -
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.
-
10
OpenAI Agents (Python)
A lightweight, powerful framework for multi-agent workflows
openai-agents-python is a library developed by OpenAI to simplify the process of creating and running agents that interact with tools and APIs using OpenAI models. It provides abstractions for tool usage, memory management, and agent workflows, enabling developers to define function-calling agents that reason through multi-step tasks. Ideal for building custom AI workflows, the library supports dynamic tool definitions and contextual memory handling. -
11
xLSTM
Neural Network architecture based on ideas of the original LSTM
...The architecture aims to provide competitive performance with transformer-based models while maintaining advantages such as linear computational scaling and efficient memory usage for long sequences. Researchers have demonstrated that xLSTM models can scale to billions of parameters and large training datasets while maintaining efficient inference speeds. -
12
Claude How-To
A visual, example-driven guide to Claude Code
...Its main value is helping developers move from casual Claude Code usage to more organized, automated, and agent-driven software development. -
13
jetson-stats
Simple package for monitoring and control your NVIDIA Jetson
...It supports Jetson platforms such as Orin, Xavier, Nano, TX, and newer Jetson families. The project includes jtop, a terminal-based dashboard that gives users a live view of CPU, GPU, memory, power, temperature, engine usage, and system status. It can also be imported into Python scripts, which makes it useful for custom monitoring, robotics dashboards, automation, and diagnostics. Developers working with embedded AI systems can use it to understand performance limits and troubleshoot hardware behavior during deployment. ... -
14
Pedalboard
A Python library for audio
pedalboard is a Python library for working with audio: reading, writing, rendering, adding effects, and more. It supports the most popular audio file formats and a number of common audio effects out of the box and also allows the use of VST3® and Audio Unit formats for loading third-party software instruments and effects. pedalboard was built by Spotify’s Audio Intelligence Lab to enable using studio-quality audio effects from within Python and TensorFlow. Internally at Spotify, pedalboard... -
15
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch
bitsandbytes is an open-source library designed to make training and inference of large neural networks more efficient by dramatically reducing memory usage. Built primarily for the PyTorch ecosystem, the library introduces advanced quantization techniques that allow models to operate using reduced numerical precision while maintaining high accuracy. These optimizations enable large language models and other deep learning architectures to run on hardware with limited memory resources, including consumer-grade GPUs. ... -
16
R-KV
Redundancy-aware KV Cache Compression for Reasoning Models
R-KV is an open-source research project that focuses on improving the efficiency of large language model inference through key-value cache compression techniques. Modern transformer models rely heavily on KV caches during autoregressive decoding, which store intermediate attention states to accelerate generation. However, these caches can consume large amounts of memory, especially in reasoning-oriented models with long context windows. R-KV introduces a method for compressing the KV cache... -
17
Cactus
Low-latency AI inference engine optimized for mobile devices
...It provides a full-stack architecture composed of an inference engine, a computation graph system, and highly optimized hardware kernels tailored for ARM-based processors. Cactus emphasizes efficient memory usage through techniques such as zero-copy computation graphs and quantized model formats, allowing large models to run within the constraints of mobile hardware. It supports a wide range of AI tasks including text generation, speech-to-text, vision processing, and retrieval-augmented workflows through a unified API interface. A notable feature of Cactus is its hybrid execution model, which can dynamically route tasks between on-device processing and cloud services when additional compute is required. -
18
AI Agent Deep Dive
AI Agent Source Code Deep Research Report
AI Agent Deep Dive is a comprehensive educational repository designed to provide a deep and structured understanding of how modern AI agents work, focusing on architecture, workflows, and real-world implementation patterns. It breaks down complex concepts such as planning, tool usage, memory management, and multi-step reasoning into digestible explanations and practical examples. The project is organized as a learning resource rather than a standalone framework, making it particularly useful for developers who want to move beyond surface-level prompt engineering into full agent system design. It explores how agents interact with environments, execute tasks, and maintain context over time, highlighting both strengths and limitations of current approaches. ... -
19
claude-code-best-practice
Practice made claude perfect
...By combining conceptual guidance with concrete examples and configuration patterns, the project helps teams move from experimental AI usage toward more production-ready agent orchestration. -
20
Windrecorder
Windrecorder is a memory search app by records everything
Windrecorder is an open-source personal memory search engine that continuously records on-screen activity in a highly optimized and storage-efficient format. It captures screen content locally and builds a searchable database using OCR and image understanding, allowing users to rewind and rediscover anything they have previously seen. The system indexes only meaningful visual changes, extracting text, browser data, and contextual information to improve search accuracy and reduce storage... -
21
DeepEP
DeepEP: an efficient expert-parallel communication library
...Because MoE architectures require routing inputs to different experts, communication overhead can become a bottleneck — DeepEP addresses that by providing optimized GPU kernels and efficient dispatch/combining logic. The library also supports low-precision operations (such as FP8) to reduce memory and bandwidth usage during communication. DeepEP is aimed at large-scale model inference or training systems where expert parallelism is used to scale model capacity without replicating entire networks. -
22
Unsloth Studio
Unified web UI for training and running open models locally
Unsloth Studio is a web-based interface for running and training AI models locally with a unified and user-friendly experience. It allows users to work with a wide range of models for text, audio, vision, embeddings, and more without relying heavily on cloud infrastructure. Built on top of the Unsloth framework, it focuses on high-performance training with reduced VRAM usage and faster speeds compared to traditional methods. The platform supports fine-tuning, pretraining, and reinforcement... -
23
FlexLLMGen
Running large language models on a single GPU
...The system focuses on high-throughput generation workloads where large batches of text must be processed quickly, such as large-scale data extraction or document analysis tasks. Instead of requiring expensive multi-GPU systems, the framework uses techniques such as memory offloading, compression, and optimized batching to run large models on commodity hardware. The architecture distributes computation and memory usage across the GPU, CPU, and disk in order to maximize the number of tokens processed during inference. This design allows organizations to deploy powerful language models for high-volume tasks without the infrastructure costs typically associated with large-scale AI systems. ... -
24
codex-orange-book
A Full-Link Guide to Using Codex from Installation to Real-World Cases
...The guide covers installation, configuration, core concepts, standard workflows, practical examples, and extension paths. It explains Codex App, Codex CLI, Codex IDE Extension, Codex Web, cloud workflows, Skills, MCP, Git, GitHub, automation, and memory-related usage. It is aimed at developers, independent builders, AI tool users, and technical teams that want a structured way to adopt Codex. Overall, it functions as a practical handbook for moving from basic Codex setup to real project execution and review-ready deliverables. -
25
Claude Cognitive
Persistent context and multi-instance coordination
Claude Cognitive is an advanced memory and context-management extension designed to address the stateless limitations of Claude Code by giving the model a form of persistent “working memory” and multi-instance coordination. It introduces an attention-based context router that prioritizes files and content relevant to the current development discussion — tagging them as HOT, WARM, or COLD based on recency and keyword activation — so Claude Code doesn’t waste token budget rereading irrelevant code. ...