Search Results for "working memory"
Sort By:
Showing 159 open source projects for "working memory"
View related business solutions-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
$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.
-
1
Windows Memory Cleaner (WMC)
Free RAM cleaner uses native Windows features to optimize memory areas
Windows Memory Cleaner (aka WMC or WinMemoryCleaner) is a lightweight, portable Windows utility designed to optimize system memory using native Windows API functions. It provides a transparent and user-friendly interface for freeing up RAM that is often held unnecessarily by cached data or inefficient processes. Unlike many “RAM booster” tools, it relies entirely on documented system methods rather than hidden tricks or unsafe optimizations. The application can automatically clean memory... -
2
DataFrames.jl
In-memory tabular data in Julia
DataFrames.jl is a powerful Julia package for working with in-memory tabular data. It provides a familiar, flexible, and efficient interface for handling datasets, making it easy to load, manipulate, join, and analyze structured data. With syntax inspired by data frames in R and pandas in Python, it offers intuitive tools while taking advantage of Julia’s speed and type system. The package is actively maintained by the JuliaData community, with contributions from over 200 developers worldwide. ... -
3
MemGuard
Secure software enclave for storage of sensitive information in memory
This package attempts to reduce the likelihood of sensitive data being exposed when in memory. It aims to support all major operating systems and is written in pure Go. Sensitive data is encrypted and authenticated in memory with XSalsa20Poly1305. The scheme used also defends against cold-boot attacks. Memory allocation bypasses the language runtime by using system calls to query the kernel for resources directly. This avoids interference from the garbage collector. Buffers that store... -
4
ReMe
Memory Management Kit for Agents
ReMe is a memory management kit for AI agents that gives them structured, persistent memory capabilities, enabling agents to extract, store, and reuse information across sessions, tasks, and interactions. It is designed to support long-running agent workflows where context matters and working memory alone isn’t enough, helping agents remember user preferences, task histories, and relevant past observations. -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
5
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. ... -
6
Letta Code
The memory-first coding agent
Letta Code is a memory-first CLI coding agent built on the Letta platform that offers developers a persistent AI assistant capable of learning and improving over time rather than resetting state each session, giving agents a sense of continuity and context across coding tasks. Unlike traditional session-based coding tools, Letta Code attaches a long-lived agent to a working directory so that the agent accumulates memory about a project’s structure, preferences, and history, effectively acting as a collaborative partner rather than a stateless helper. ... -
7
LangChain
⚡ Building applications with LLMs through composability ⚡
Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. But using these LLMs in isolation is often not enough to create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge. This library is aimed at assisting in the development of those types of applications. -
8
Neuron AI
The PHP Agentic Framework to build production-ready AI driven apps
Neuron AI is a PHP agentic framework for building production-ready AI applications that connect models, memory, vector databases, and tools into working agents. It is designed for developers who want to create systems such as RAG pipelines, multi-agent workflows, and business process automations without having to hand-build every integration from scratch. The framework provides an Agent class that can be extended to inherit core capabilities like memory, tools, function calling, and retrieval-augmented generation. ... -
9
Agrona
High Performance data structures and utility methods for Java
Agrona provides a library of data structures and utility methods that are a common need when building high-performance applications in Java. Many of these utilities are used in the Aeron efficient reliable UDP unicast, multicast, and IPC message transport and provides high-performance buffer implementations to support the Simple Binary Encoding Message Codec. -
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.
-
10
AvCpp
C++ wrapper for FFmpeg
AvCpp is a modern C++ wrapper library for FFmpeg designed to provide a safer and more intuitive interface for multimedia processing. It leverages modern C++ features to simplify memory management and reduce the complexity of working with FFmpeg’s C APIs. The library enables developers to handle encoding, decoding, and streaming tasks with cleaner and more maintainable code. It focuses on performance while improving developer productivity through abstraction. avcpp supports integration into multimedia applications requiring efficient processing pipelines. ... -
11
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. -
12
Explorer
Series (one-dimensional) and dataframes (two-dimensional)
Explorer brings series (one-dimensional) and data frames (two-dimensional) to Elixir for fast data exploration. -
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
InMemoryDatasets.jl
Multithreaded package for working with tabular data in Julia
InMemoryDatasets.jl is a multithreaded package for data manipulation and is designed for Julia 1.6+ (64-bit OS). The core computation engine of the package is a set of customized algorithms developed specifically for columnar tables. -
15
SkyEmu
Game Boy Advance, Game Boy, Game Boy Color, and DS Emulator
SkyEmu is a modern, multi-system handheld emulator that supports Game Boy, Game Boy Color, Game Boy Advance, and experimental Nintendo DS emulation, with a strong focus on balancing accuracy, performance, and usability. It is designed as a low-level emulator that accurately reproduces hardware behavior while still offering a smooth and accessible user experience across a wide range of platforms. The emulator is highly portable, supporting desktop operating systems, mobile devices, and even... -
16
Go Container Registry
Go library and CLIs for working with container registries
go-containerregistry is a Go library (with companion tools) for interacting with container images and registries using OCI/Docker formats. It provides primitives to read, write, mutate, sign, and copy images and indexes across registries without shelling out to Docker. High-level utilities like crane and gcrane offer convenient CLIs for everyday tasks—listing tags, copying images between registries, flattening, creating tarballs, and more. The library handles authentication via a pluggable... -
17
Planning with Files
Claude Code skill implementing Manus-style persistent planning
...Inspired by high-profile agent workflows and context engineering patterns, it uses persistent markdown files (like task_plan.md, progress.md, and findings.md) as the “working memory” for AI agents, overcoming the limitations of ephemeral memory and large context windows that often lead to drift or information loss. Once installed, the plugin supports commands to create and manage planning files, integrates with multiple IDEs and CLI environments, and ensures sessions can recover progress even when context limits are reached. -
18
Gocache
Go cache library that brings you multiple ways to manage caches
Guess what is Gocache? a Go cache library. This is an extendable cache library that brings you a lot of features for caching data. Multiple cache stores: actually in memory, redis, or your own custom store. A chain cache: use multiple cache with a priority order (memory then fallback to a redis shared cache for instance) A loadable cache: allow you to call a callback function to put your data back in cache. A metric cache to let you store metrics about your caches usage (hits, miss, set success, set error, ...) ... -
19
Bumper.jl
Bring Your Own Stack
Bumper.jl is a package that aims to make working with bump allocators (also known as arena allocators) easier and safer. You can dynamically allocate memory to these bump allocators, and reset them at the end of a code block, just like Julia's stack. Allocating to a bump allocator with Bumper.jl can be just as efficient as stack allocation. Bumper.jl is still a young package, and may have bugs. -
20
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. -
21
Simple StyleGan2 for Pytorch
Simplest working implementation of Stylegan2
Simple Pytorch implementation of Stylegan2 that can be completely trained from the command-line, no coding needed. You will need a machine with a GPU and CUDA installed. You can also specify the location where intermediate results and model checkpoints should be stored. You can increase the network capacity (which defaults to 16) to improve generation results, at the cost of more memory. By default, if the training gets cut off, it will automatically resume from the last checkpointed file.... -
22
Laravel IDE Helper Generator
Complete PHPDocs, directly from the source
...Avoid caching the configuration in your development environment, it may cause issues after installing certain packages; respectively clear the cache beforehand via php artisan cache:clear if you encounter problems when running the commands. Some classes need a working database connection. If you do not have a default working connection, some facades will not be included. You can use an in-memory SQLite driver by adding the -M option. If you need additional information on your model from sources that are not handled by default, you can hook in to the generation process with model hooks to add extra information on the fly. -
23
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... -
24
CUDA Python
Performance meets Productivity
...It integrates tightly with the broader Python GPU ecosystem, including Numba for kernel compilation and CCCL for parallel primitives, allowing developers to write performant code without leaving Python. The toolkit also includes utilities for profiling, memory management, distributed computing, and numerical operations, making it suitable for scientific computing, AI, and data processing workloads. -
25
Skytable
Skytable is a fast, secure and reliable realtime NoSQL database
...Automated background saving, snapshots and remote snapshots are there when you need them. Natively multithreaded to exploit all CPU cores which helps lower your TCO. Written in Rust with expert analyzed unsafe code for memory safety and TLS for encrypted connections. Have 1MB memory? That's all Skytable needs. With no platform-specific dependencies, Skytable can virtually run on anything that has an OS. Features like keyspaces, tables, data types, authn+authz, snapshots and more are ready for you to use while we're working on several new data models and features.
