Search Results for "memory" - Page 5
Sort By:
Showing 459 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.
-
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
1
SAM 2
The repository provides code for running inference with SAM 2
...It retains the core promptable interface—accepting points, boxes, or masks—but incorporates architectural and training enhancements to produce higher-fidelity masks, better boundary adherence, and robustness to complex scenes. The updated model is optimized for faster inference and lower memory use, enabling real-time interactivity even on larger images or constrained hardware. SAM2 comes with pretrained weights and easy-to-use APIs, enabling developers and researchers to integrate promptable segmentation into annotation tools, vision pipelines, or downstream tasks. The project also includes scripts and notebooks to compare SAM2 against SAM on edge cases, benchmarks showing improvements, and evaluation suites to measure mask quality metrics like IoU and boundary error. -
2
CTranslate2
Fast inference engine for Transformer models
...The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc. The model serialization and computation support weights with reduced precision: 16-bit floating points (FP16), 16-bit integers (INT16), and 8-bit integers (INT8). ... -
3
zclaw
Your personal AI assistant at all-in 888KiB
...The project focuses on delivering core assistant capabilities within an extremely small footprint, demonstrating how AI-driven automation can operate on microcontrollers. It includes support for GPIO control, scheduled tasks, memory handling, and other embedded automation features that enable real-world device interaction. The architecture is optimized for efficiency, allowing the full assistant stack to run in under one megabyte of space. By targeting low-power hardware, zclaw explores the future of edge AI assistants that operate independently of large cloud systems. ... -
4
MCP Server Qdrant
An official Qdrant Model Context Protocol (MCP) server implementation
The Qdrant MCP Server is an official Model Context Protocol server that integrates with the Qdrant vector search engine. It acts as a semantic memory layer, allowing for the storage and retrieval of vector-based data, enhancing the capabilities of AI applications requiring semantic search functionalities. -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
FramePack
Lets make video diffusion practical
...The idea is to “pack” frames by detecting shared structure and storing differences efficiently, which can accelerate training or inference on video-like data. By reducing I/O and memory bandwidth, datasets become lighter to load while models still see the essential temporal variation. The repository demonstrates both packing and unpacking steps, making it straightforward to integrate into preprocessing pipelines. It’s useful for diffusion and generative models that learn from sequential image datasets, as well as classical pipelines that batch many related frames. ... -
6
WanGP
AI video generator optimized for low VRAM and older GPUs use
Wan2GP is an open source AI video generation toolkit designed to make modern generative models accessible on consumer-grade hardware with limited GPU memory. It acts as a unified interface for running multiple video, image, and audio generation models, including Wan-based models as well as other systems like Hunyuan Video, Flux, and Qwen. A key focus of the project is reducing VRAM requirements, enabling some workflows to run on as little as 6 GB while still supporting older Nvidia and certain AMD GPUs. ... -
7
Atmosphere
Real-time transport layer for Java AI agents
Atmosphere is a Java framework for building streaming AI agents on the JVM. It lets developers declare agent behavior with an @Agent annotation while the framework handles transport, streaming, tool calls, memory, reconnect behavior, authorization, and observability. A single agent can be exposed over WebSocket, Server-Sent Events, long polling, gRPC, and WebTransport over HTTP/3 depending on the modules included. It also supports agent-facing protocols such as MCP, A2A, and AG-UI, along with external messaging channels such as Slack, Telegram, Discord, WhatsApp, and Messenger. ... -
8
Clawbolt
The AI Assistant that actually does things for the trades
...The platform allows users to interact with an AI assistant through iMessage, SMS, RCS, Telegram, and related messaging channels to handle tasks such as estimates, invoices, scheduling, reminders, and client communication. Clawbolt combines large language model orchestration with memory systems, file storage integrations, and tool-calling workflows to create an assistant capable of managing real operational tasks instead of only answering prompts. The project supports integrations with QuickBooks Online, Google Calendar, Dropbox, and Google Drive, enabling automated business workflows tied directly to conversations. ... -
9
AgentScope
Build and run agents you can see, understand and trust
...It provides essential abstractions that evolve with advancing LLM capabilities, emphasizing reasoning, tool use, and flexible orchestration rather than rigid prompt constraints. With built-in support for ReAct agents, memory, planning, human-in-the-loop control, and real-time voice interaction, developers can create powerful agents in minutes. AgentScope integrates seamlessly with tools, long-term memory systems, MCP, A2A (Agent-to-Agent) protocols, and observability frameworks. It also supports reinforcement learning workflows for tuning agents and improving performance across complex tasks. ... -
$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.
-
10
Moltis
A Rust-native claw you can trust
...The platform also includes long-term memory powered by hybrid vector and full-text search, allowing the assistant to retain context across sessions. With multi-channel access such as web UI, Telegram, and API endpoints, Moltis functions as a unified automation hub intended for developers and advanced users who want full control. -
11
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. These tutorials show how to implement things like secure tool calling with OAuth, dual-memory architectures, production RAG agents, multi-agent communication protocols, GPU deployment, containerization with Docker, FastAPI endpoints, and Streamlit chat UIs. ... -
12
Stable Diffusion WebUI Forge
Stable Diffusion WebUI Forge is a platform on top of Stable Diffusion
...It also focuses on stability during long sessions, aiming to reduce out-of-memory failures and provide clearer diagnostics when they occur. The UI surfaces advanced options in a way that remains recognizable to WebUI users, so migration costs are low while gaining experimental features. In practice, Forge serves as a proving ground for ideas that may later influence upstream tools, giving power users early access to cutting-edge techniques. -
13
FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
...It provides optimized kernels for MLA decoding, including support for variable-length sequences, helping reduce latency and increase throughput in model inference systems using that attention style. The library supports both BF16 and FP16 data types, and includes a paged KV cache implementation with a block size of 64 to efficiently manage memory during decoding. On very compute-bound settings, it can reach up to ~660 TFLOPS on H800 SXM5 hardware, while in memory-bound configurations it can push memory throughput to ~3000 GB/s. The team regularly updates it with performance improvements; for example, a 2025 update claims 5 % to 15 % gains on compute-bound workloads while maintaining API compatibility. -
14
AGI
The first distributed AGI system
...It aims to provide a foundation for creating agents that can reason, plan, and execute tasks across diverse domains by integrating multiple AI capabilities into a unified system. The project typically explores concepts such as agent orchestration, memory systems, task decomposition, and decision-making loops, enabling the development of more generalized and adaptive AI behaviors. It is designed to be extensible, allowing developers to plug in different models, tools, and data sources to enhance agent performance. The framework encourages experimentation with AGI-like architectures, making it useful for researchers and developers interested in advancing beyond narrow AI applications. -
15
Desktop Commander MCP
AI-powered MCP server for desktop file and terminal automation
...Desktop Commander MCP builds on top of an MCP filesystem server and enhances it with powerful search, replace, and code editing capabilities tailored for real-world development environments. It allows users to run terminal commands with streaming output, manage long-running processes, and even execute code in memory without saving files. It also supports working with structured and document formats such as Excel, PDF, and DOCX, enabling AI to read, modify, and generate these files directly. -
16
CowAgent
AI assistant based on large models that can actively think and plan
...It enables automated message handling by connecting WeChat accounts with AI models that can generate contextual replies, process voice messages, and produce images directly inside chats. The platform has evolved beyond a simple chatbot into a more autonomous agent capable of planning complex tasks, maintaining long-term memory, and invoking external tools to complete workflows. It supports multi-turn conversations with per-user context tracking, allowing more natural and persistent interactions across private and group chats. Developers can extend functionality through a plugin architecture and customizable rules, making it suitable for both personal assistants and enterprise automation scenarios. -
17
ACE-Step 1.5
The most powerful local music generation model
...It integrates cutting-edge generative techniques—such as diffusion-based synthesis combined with compressed autoencoders and lightweight transformer elements—to produce high-quality full-length music tracks with rapid inference times, capable of generating a complete song in seconds on modern GPUs while remaining efficient enough to run on consumer-grade hardware with minimal memory requirements. Beyond straightforward text-to-music synthesis, ACE-Step 1.5 enables flexible creative workflows, including tasks like cover generation, editing existing tracks, transforming vocals to background accompaniment, and stylistic personalization using low-rank adaptation from just a few example songs. -
18
GoCV
Go package for computer vision using OpenCV 4 and beyond
...Computer Vision (CV) is the ability of computers to process visual information, and perform tasks normally associated with those performed by humans. CV software typically processes video images, then uses the data to extract information in order to do something useful. Since memory allocations for images in GoCV are done through C based code, the go garbage collector will not clean all resources associated with a Mat. As a result, any Mat created must be closed to avoid memory leaks. -
19
Spring AI Alibaba Examples
Spring AI Alibaba examples for building and testing AI apps
...Each module focuses on a specific use case such as chat, image processing, audio handling, graph workflows, and retrieval-augmented generation. The examples highlight how to integrate AI models, manage prompts, handle memory, and build multi-model or multi-agent workflows. Developers can explore individual project folders for detailed instructions and implementation guidance. Spring AI Alibaba Examples also supports experimentation through playground modules and encourages contributions to expand real-world AI use cases and improve development practices. -
20
RisuAI
Make your own story. User-friendly software for LLM roleplaying
RisuAI (or Risu) is a cross-platform AI roleplay chat application—available as both a desktop and web solution—offering creative story-building and character interaction experiences with support for multiple APIs, in-chat assets, regex capabilities, and more. Supports OpenAI, Claude, Gemini, DeepInfra, Ooba, OpenRouter... and More. Display the image of the current character, according to his/her expressions. Modify model's output by regex, to make a custom GUI and others. -
21
pgvector
Open-source vector similarity search for Postgres
...An HNSW index creates a multilayer graph. It has better query performance than IVFFlat (in terms of speed-recall tradeoff), but has slower build times and uses more memory. Also, an index can be created without any data in the table since there isn’t a training step like IVFFlat. -
22
Datasets
Hub of ready-to-use datasets for ML models
...Load a dataset in a single line of code, and use our powerful data processing methods to quickly get your dataset ready for training in a deep learning model. Backed by the Apache Arrow format, process large datasets with zero-copy reads without any memory constraints for optimal speed and efficiency. We also feature a deep integration with the Hugging Face Hub, allowing you to easily load and share a dataset with the wider NLP community. There are currently over 2658 datasets, and more than 34 metrics available. Datasets naturally frees the user from RAM memory limitation, all datasets are memory-mapped using an efficient zero-serialization cost backend (Apache Arrow). ... -
23
GPU Hot
Real-time NVIDIA GPU dashboard
...The project offers a self-hosted web interface that streams hardware metrics directly from GPU servers, enabling developers, ML engineers, and system administrators to observe GPU utilization and system behavior in real time through a browser. The dashboard collects and displays a wide range of performance metrics including temperature, memory usage, power consumption, clock speeds, fan speed, and active processes. It can scale from monitoring a single GPU workstation to large distributed environments with dozens or even hundreds of GPUs by running lightweight containers on each node and aggregating the data centrally. -
24
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. -
25
Phidata
Build multi-modal Agents with memory, knowledge, tools and reasoning
Phidata is an open source platform for building, deploying, and monitoring AI agents. It enables users to create domain-specific agents with memory, knowledge, and external tools, enhancing AI capabilities for various tasks. The platform supports a range of large language models and integrates seamlessly with different databases, vector stores, and APIs. Phidata offers pre-configured templates to accelerate development and deployment, allowing users to quickly go from building agents to shipping them into production. ...
