Search Results for "memory" - Page 3
Sort By:
Showing 497 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.
-
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
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. -
2
ex-skill
Distill your ex into an AI Skill
...The system works by ingesting various forms of personal data such as chat logs, social media content, photos, and user-provided descriptions, then structuring this information into a layered representation that combines memory and persona modeling. It is designed to run within Claude Code environments, where users can generate, manage, and interact with these personalized AI entities through command-based interfaces. The project emphasizes emotional realism by reconstructing conversational tone, habits, and contextual memories, enabling interactions that feel consistent with the original person. -
3
xFormers
Hackable and optimized Transformers building blocks
...One of its key goals is efficient attention: it supports dense, sparse, low-rank, and approximate attention mechanisms (e.g. FlashAttention, Linformer, Performer) via interchangeable modules. The library includes memory-efficient operator implementations in both Python and optimized C++/CUDA, ensuring that performance isn’t sacrificed for modularity. It also integrates with PyTorch seamlessly so you can drop in its blocks to existing models, replace default attention layers, or build new architectures from scratch. xformers includes training, deployment, and memory profiling tools. -
4
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. -
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.
-
5
Qwen-Agent
Agent framework and applications built upon Qwen>=3.0
Qwen-Agent is a framework for building applications / agents using Qwen models (version 3.0+). It provides components for instruction following, tool usage (function calling), planning, memory, RAG (retrieval augmented generation), code interpreter, etc. It ships with example applications (Browser Assistant, Code Interpreter, Custom Assistant), supports GUI front-ends, backends, server setups. Agent workflow can maintain context / memory to perform multi-turn or more complex logic over time. It acts as the backend for Qwen Chat among other use cases. ... -
6
JoyAI-Echo
Pushing the Frontier of Long Audio-Visual Generation
...It is designed to create minute-level, multi-shot video stories from structured prompts while preserving continuity across scenes. The system uses a paired cross-modal memory bank to maintain visual identity and voice consistency over longer sequences. It also uses a distilled DMD generator to reduce inference cost and improve generation speed compared with heavier multi-step pipelines. JoyAI-Echo focuses on text-to-video and multi-shot long-video generation, while image-to-video support is not part of the current release scope. ... -
7
AI Agent Book
Deep Understanding AI Agents
AI Agent Book is an open educational repository for Understanding AI Agents: Design Principles and Engineering Practice. It explains agents through the formula of a language model combined with context and tools. Ten chapters move from core concepts to context engineering, memory, RAG, knowledge graphs, MCP tools, and coding agents. Later material covers evaluation, supervised fine-tuning, reinforcement learning, self-improvement, multimodal interaction, robotics, and multi-agent cooperation. The repository includes 88 companion experiments, with more than 70 designed to run independently. Readers can access the source chapters, generated figures, code, and downloadable PDF or EPUB editions. ... -
8
MaiBot
Maimaibot, a (more focused) multi-platform intelligent agent
...It can generate responses that imitate human speech patterns, learn slang or expressions from chat participants, and adapt its conversational style based on previous interactions. The architecture includes a memory system that stores conversation history and contextual information, allowing the bot to recall previous events and maintain continuity in discussions. -
9
sqlite-utils
Python CLI utility and library for manipulating SQLite databases
...It focuses on making common tasks like importing CSV/JSON, exploring tables, and running ad-hoc queries feel ergonomic and scriptable. As a CLI, it lets you build databases from structured data in one line, run queries against local files or in-memory databases, output results as JSON, CSV, or pretty tables, and configure full-text search. As a library, it exposes high-level APIs for inserting records, creating or transforming tables, normalizing schemas, and running migrations that SQLite’s limited ALTER TABLE cannot handle directly. The project also embraces an ecosystem of plugins, so you can add custom SQL functions, extra commands, or UIs (including a terminal UI) via separate packages. ... -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
10
psutil
Cross-platform lib for process and system monitoring in Python
psutil is a widely adopted cross-platform Python library designed to retrieve detailed information about system utilization and running processes in a consistent and programmatic way. It exposes a rich API that allows developers to inspect CPU usage, memory consumption, disk activity, network statistics, and hardware sensors without relying on platform-specific tools. The library effectively replicates and unifies the capabilities of classic UNIX utilities such as ps, top, netstat, and free, making it especially valuable for monitoring, profiling, and process management workflows. Because it supports multiple operating systems including Linux, Windows, macOS, and BSD variants, psutil enables developers to build portable observability tools and automation scripts. ... -
11
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. ... -
12
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. -
13
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. ... -
14
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. ... -
15
Hello-Agents
Building an Intelligent Agent from Scratch
...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. Its goal is to demystify agent engineering and help developers move from simple prompt scripts to robust autonomous systems. -
16
Timbal
Simple, performant, battle-tested framework for building reliable AI
...The framework supports multiple model providers and can automatically fail over between configured models. Human approval gates can pause runs, preserve their state, and resume them after a process restart. Built-in capabilities cover persistent memory, context compaction, structured outputs, reusable skills, MCP servers, tracing, and evaluations. Applications can run locally, be self-hosted, or be deployed through the Timbal platform with an accompanying API and user interface. -
17
Linux insides
A book-in-progress about the Linux kernel and its insides
Linux insides is an extensive open-source educational book project that explores the internal architecture and behavior of the Linux kernel. The repository contains a structured series of chapters that explain low-level topics such as booting, memory management, interrupts, system calls, and synchronization primitives. The project’s stated goal is to share knowledge about Linux kernel internals and related low-level concepts in an accessible narrative format. It is written for readers who already have some familiarity with C and assembly language and want to understand what happens under the hood of Linux. ... -
18
MiroFish
A Simple and Universal Swarm Intelligence Engine
...The system extracts “seed” information from sources such as breaking news, policy documents, and market signals to construct a high-fidelity digital parallel world populated by thousands of virtual agents with independent memory and behavior rules. Users can inject variables or conditions into this simulated environment from a “god’s eye view,” enabling iterative prediction of future trends under different assumptions, which can be useful for decision support, scenario planning, or creative exploration. The engine includes both backend and frontend components, with configuration and deployment instructions for local and containerized setups, and is designed to produce detailed predictive reports based on interactions and emergent patterns within the simulated world. -
19
OpenSage
An agent framework that enables AI to create their own agent
...Unlike traditional agent frameworks that require developers to manually define workflows, tools, and structures, OpenSage introduces a system where large language models can dynamically generate their own agent architectures, including sub-agents, toolchains, and execution strategies. The framework is built around the concept of an Agent Development Kit (ADK), providing structured components for memory, reasoning, and task decomposition while allowing agents to iteratively improve their own design. A key innovation is its hierarchical and graph-based memory system, which enables agents to store, retrieve, and organize information across complex workflows with improved efficiency and contextual awareness. -
20
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. ... -
21
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. ... -
22
bitnet.cpp
Official inference framework for 1-bit LLMs
bitnet.cpp is the official open-source inference framework and ecosystem designed to enable ultra-efficient execution of 1-bit large language models (LLMs), which quantize most model parameters to ternary values (-1, 0, +1) while maintaining competitive performance with full-precision counterparts. At its core is bitnet.cpp, a highly optimized C++ backend that supports fast, low-memory inference on both CPUs and GPUs, enabling models such as BitNet b1.58 to run without requiring enormous compute infrastructure. The project’s focus on extreme quantization dramatically reduces memory footprint and energy consumption compared with traditional 16-bit or 32-bit LLMs, making it practical to deploy advanced language understanding and generation models on everyday machines. ... -
23
zpdf
Zero-copy PDF text extraction library written in Zig
zpdf is a high-performance PDF text extraction library written in Zig that focuses on speed, low overhead, and modern parsing techniques. It leans heavily on memory-mapped file reading and zero-copy patterns where possible, so it can scan large PDFs without repeatedly copying data around in memory. The library supports streaming extraction using efficient arena allocation, making it well suited for workloads that need to process big documents quickly or in batches. It implements multiple PDF decompression filters and handles common font encoding pathways, which are essential for turning raw PDF content streams into readable text. ... -
24
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. ... -
25
Stable Diffusion Version 2
High-Resolution Image Synthesis with Latent Diffusion Models
...The repository provides code for training and running Stable Diffusion-style models, instructions for installing dependencies (with notes about performance libraries like xformers), and guidance on hardware/driver requirements for efficient GPU inference and training. It’s organized as a practical, developer-focused toolkit: model code, scripts for inference, and examples for using memory-efficient attention and related optimizations are included so researchers and engineers can run or adapt the model for their own projects. The project sits within a larger ecosystem of Stability AI repositories (including inference-only reference implementations like SD3.5 and web UI projects) and the README points users toward compatible components, recommended CUDA/PyTorch versions.