Search Results for "memory" - Page 4
Sort By:
Showing 439 open source projects for "memory"
View related business solutions-
$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.
-
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.
-
1
Harmonist
Portable AI agent orchestration with mechanical protocol enforcement
...It is designed to make agent workflows more reliable by enforcing protocol rules mechanically instead of trusting prompts alone. The framework includes a catalog of specialized agents, validated memory behavior, supply-chain checks, and hooks that gate code-changing turns. If required reviewers do not run, memory is not updated, or shipped files fail integrity checks, Harmonist can block the workflow from completing. The project uses Python, has no runtime dependencies beyond the standard library, and is positioned as a drop-in agent coordination pack. ... -
2
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. ... -
3
TensorFlow Lite for Microcontrollers
Infrastructure to enable deployment of ML models
TensorFlow Lite for Microcontrollers is a TensorFlow Lite runtime designed for running machine learning models on tiny embedded devices. It targets microcontrollers, DSPs, and other resource-constrained hardware where memory, compute, and power are limited. The project enables on-device inference without depending on an operating system, standard C or C++ libraries, or dynamic memory allocation. It is useful for applications such as wake-word detection, sensor analysis, gesture recognition, anomaly detection, and small vision or audio models. Developers can train or convert models into TensorFlow Lite format and deploy them into embedded firmware. ... -
4
Memvid
Video-based AI memory library. Store millions of text chunks in MP4
Memvid encodes text chunks as QR codes within MP4 frames to build a portable “video memory” for AI systems. This innovative approach uses standard video containers and offers millisecond-level semantic search across large corpora with dramatically less storage than vector DBs. It's self-contained—no DB needed—and supports features like PDF indexing, chat integration, and cloud dashboards. -
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
Vibe-Trading
Vibe-Trading: Your Personal Trading Agent
...It features a swarm-based architecture with prebuilt expert agent teams for research, trading, and risk management. Advanced backtesting engines provide statistical validation, optimization, and performance metrics. The system also includes persistent memory, enabling it to learn from past interactions and refine strategies over time. Overall, it delivers an end-to-end AI-driven trading environment for both research and execution. -
6
Lightpanda Browser
Lightpanda: the headless browser designed for AI and automation
...The browser is implemented using the Zig programming language and integrates the V8 JavaScript engine to run modern web applications and scripts efficiently. Because it avoids graphical rendering and other heavy browser components, the system uses significantly less memory and launches almost instantly compared to conventional browsers such as Chrome. -
7
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). ... -
8
Team9
Team9 is a collaborative workspace for AI agents
...It builds on agent frameworks like OpenClaw and introduces a managed environment where agents can be assigned roles, share context, and execute tasks collaboratively. The system emphasizes a “local-first” architecture, allowing agents to run on user-controlled infrastructure while maintaining persistent memory and data privacy. It includes orchestration mechanisms that allow agents to operate continuously through scheduled tasks, event-driven triggers, and long-running processes. The platform also integrates messaging gateways and communication channels, enabling agents to interact with users and systems in real time. Its design reflects a shift toward treating AI agents as operational units within organizations rather than isolated tools. -
9
Mistral Finetune
Memory-efficient and performant finetuning of Mistral's models
mistral-finetune is an official lightweight codebase designed for memory-efficient and performant finetuning of Mistral’s open models (e.g. 7B, instruct variants). It builds on techniques like LoRA (Low-Rank Adaptation) to allow customizing models without full parameter updates, which reduces GPU memory footprint and training cost. The repo includes utilities for data preprocessing (e.g. reformat_data.py), validation scripts, and example YAML configs for training variants like 7B base or instruct models. ... -
Compliant and Reliable File Transfers Backed by Top Security CertificationsStop relying on non-certified, legacy file transfer tools that creak under the weight of modern security demands. Get full audit trails, advanced access controls and more supported by an award-winning team of experts. Start your free 25-day trial today.
-
10
Transformer Engine
A library for accelerating Transformer models on NVIDIA GPUs
...As the number of parameters in Transformer models continues to grow, training and inference for architectures such as BERT, GPT, and T5 become very memory and compute-intensive. Most deep learning frameworks train with FP32 by default. This is not essential, however, to achieve full accuracy for many deep learning models. -
11
Pro Workflow
Claude Code learns from your corrections: self-correcting memory
Pro Workflow is a productivity framework for Claude Code that introduces self-improving workflows through memory, context engineering, and structured agent orchestration. The system learns from user corrections over time, storing feedback and refining its behavior across sessions to improve accuracy and efficiency. It supports advanced development setups such as parallel worktrees, enabling multiple tasks to be handled simultaneously without interference. -
12
Mooncake
Mooncake is the serving platform for Kimi
...Its architecture centers on a high-performance transfer engine that provides unified data transfer across different storage and networking technologies. This engine enables efficient movement of tensors and model data across heterogeneous environments such as GPU memory, system memory, and distributed storage systems. Mooncake also introduces distributed key-value cache storage that allows inference systems to reuse previously computed attention states, significantly improving throughput in large-scale deployments. The system supports advanced networking technologies such as RDMA and NVMe over Fabric, enabling high-speed communication across clusters. -
13
claude-obsidian
Claude + Obsidian knowledge companion
...The system follows the LLM Wiki pattern, where information is stored as persistent markdown files that grow richer over time through cross-referencing and synthesis. It includes features such as contradiction detection, orphaned note identification, and automatic indexing. A persistent memory layer ensures continuity across sessions, eliminating the need for repeated context. It also performs autonomous research to fill knowledge gaps and expand the knowledge base. Overall, it turns note-taking into an active, compounding intelligence system. -
14
Agentex
Open source codebase for Scale Agentex
AgentEX is an open framework from Scale for building, running, and evaluating agentic workflows, with an emphasis on reproducibility and measurable outcomes rather than ad-hoc demos. It treats an “agent” as a composition of a policy (the LLM), tools, memory, and an execution runtime so you can test the whole loop, not just prompting. The repo focuses on structured experiments: standardized tasks, canonical tool interfaces, and logs that make it possible to compare models, prompts, and tool sets fairly. It also includes evaluation harnesses that capture success criteria and partial credit, plus traces you can inspect to understand where reasoning or tool use failed. ... -
15
Hermes Agent Orange Book
From Beginner to Master · Orange Book Series
Hermes Agent Orange Book is a structured knowledge resource and guide for building and understanding Hermes-style autonomous agents. It compiles principles, workflows, and patterns used in agent-based systems into an organized format. The project focuses on explaining how agents manage memory, tools, and iterative reasoning processes. It serves as both a reference and a learning resource for developers working with autonomous AI systems. The content emphasizes practical implementation strategies rather than abstract theory. It is particularly useful for those building or studying agent architectures. Overall, it provides a comprehensive overview of agent design and operation. -
16
PicoClaw
Ultra-Efficient AI Assistant in Go
PicoClaw is an ultra-lightweight, open-source personal AI assistant written in Go, architected from the ground up to operate with extremely low memory usage (under 10 MB) and fast boot times, making it suitable for inexpensive hardware platforms and embedded devices. Inspired by earlier AI assistant projects like “nanobot,” it was refactored to emphasize resource efficiency while still supporting meaningful AI-driven interactions such as conversational workflows, planning tasks, and automation. ... -
17
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. ... -
18
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 code. It begins with foundational concepts like conversational loops and tool integration, then expands into more advanced capabilities such as dynamic skill loading, web interaction, and context management. ... -
19
Cherry Studio
Cherry Studio is a desktop client that supports for multiple LLMs
Cherry Studio is a cross-platform desktop client that integrates multiple large language model providers into a unified interface for creating and using AI assistants, supporting customization and multi-model conversations. Selection Assistant with smart content selection enhancement. Deep Research with advanced research capabilities. Memory System with global context awareness. Document Preprocessing with improved document handling. MCP Marketplace for Model Context Protocol ecosystem. -
20
Omi
AI that sees your screen and listens to conversations
...The platform operates across multiple environments, including wearable devices, mobile apps, and desktop applications, ensuring seamless integration into a user’s daily workflow. At its core, omi uses a pipeline of speech-to-text systems, large language models, and memory storage services to transform raw audio and context into meaningful outputs like tasks and reminders. The architecture is modular and extensible, featuring APIs, SDKs, and plugin-like capabilities that allow developers to build custom applications. -
21
Cloudflare Agents
Build and deploy AI Agents on Cloudflare
...The project includes SDKs, templates, and deployment tooling that simplify the process of connecting agents to external APIs, storage systems, and workflows. Its architecture emphasizes persistent memory, enabling agents to maintain context across sessions and interactions. Developers can orchestrate complex behaviors using workflows and durable objects, making it suitable for production-grade autonomous systems. Overall, Cloudflare Agents aims to streamline the development of scalable AI automation that operates close to users for improved performance. -
22
LangChain Rust
LangChain for Rust, the easiest way to write LLM-based programs
...The library aims to provide Rust developers with a structured framework for orchestrating prompts, chains, agents, and external tools within LLM-driven workflows. By adapting LangChain concepts to the Rust programming language, the project emphasizes performance, safety, and efficient memory management. Developers can use the framework to build chatbots, autonomous agents, and knowledge-augmented AI systems that interact with external data sources. The library provides abstractions for model providers, prompt templates, conversation memory, and vector search integrations. It also enables the construction of multi-step pipelines where LLM outputs feed into subsequent actions or tool calls. -
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
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. -
25
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.
