Search Results for "memory" - Page 21
Sort By:
Showing 3192 open source projects for "memory"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
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.
-
1
etcd
Distributed reliable key-value store for the most critical data
...It gracefully handles leader elections during network partitions and can tolerate machine failure, even in the leader node. etcd is a consistent distributed key-value store. Mainly used as a separate coordination service, in distributed systems. And designed to hold small amounts of data that can fit entirely in memory. Read and write values using standard HTTP tools, such as curl. Store data in hierarchically organized directories, as in a standard filesystem. Watch specific keys or directories for changes and react to changes in values. -
2
LobeHub
Workspace to find, build, and collaborate with AI agents
LobeHub is an all-in-one workspace designed to help humans and AI agents collaborate, grow, and evolve together. It treats AI agents as true teammates rather than one-off tools, enabling deeper context, continuity, and productivity. Users can build personalized agent teams that understand their workflows, preferences, and goals over time. LobeHub brings multiple models, tools, and modalities into a single unified environment under the user’s control. With built-in collaboration features,... -
3
FLUX.2-klein-4B
Flux 2 image generation model pure C inference
...Because the implementation is in plain C and focuses on data locality and vectorized operations, flux2.c can be integrated into performance-critical code paths where control over memory layout and execution behavior matters, such as GPU kernels, embedded systems, or custom ML runtime engines. -
4
dashdot
A simple, modern server dashboard
dashdot is a modern server dashboard primarily used by smaller private servers, offering real-time monitoring of system metrics through a sleek and customizable web interface. -
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.
-
5
pg_activity
pg_activity is a top like application for PostgreSQL server activity
Command line tool for PostgreSQL server activity monitoring. pg_activity is a PostgreSQL monitoring tool that provides real-time insights into database performance, helping database administrators manage and troubleshoot PostgreSQL instances. -
6
PartitionedArrays.jl
Vectors and sparse matrices partitioned into pieces
This package provides distributed (a.k.a. partitioned) vectors and sparse matrices in Julia. See the documentation for further details. -
7
opentype.js
Read and write OpenType fonts using JavaScript
...Support for WOFF, OTF, TTF (both with TrueType glyf and PostScript cff outlines) Support for kerning (Using GPOS or the kern table). Support for ligatures. Support for TrueType font hinting. Support arabic text rendering (See issue #364 & PR #359 #361) A low memory mode is available as an option (see #329) Runs in the browser and Node.js. -
8
UniTask
Provides efficient allocation free async/await integration for Unity
...Runs completely on Unity's PlayerLoop so doesn't use threads and runs on WebGL, wasm, etc. Asynchronous LINQ, with Channel and AsyncReactiveProperty. TaskTracker window to prevent memory leaks. Highly compatible behavior with Task/ValueTask/IValueTaskSource. In UniTask v2, almost everything is zero-allocated due to a thorough rewrite of the code (Technical details to follow). In addition to significant performance improvements, the new asynchronous sequences, and Asynchronous LINQ. -
9
OpenClaw Opik Observability Plugin
Official plugin for OpenClaw that exports agent traces to Opik
...The project integrates directly with OpenClaw’s plugin architecture so that developers can capture detailed runtime information about how their agents behave while executing tasks. Each time an AI agent performs an action—such as calling a large language model, invoking a tool, accessing memory, or delegating to a sub-agent—the plugin records the full interaction and sends it to Opik for analysis and visualization. This allows developers to inspect inputs, outputs, token usage, latency, and execution flow across complex multi-step agent workflows. The goal of the project is to provide transparency into the internal reasoning and operational pipeline of agent systems so developers can diagnose failures, control costs, and improve reliability. -
$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.
-
10
AWS GenAI LLM Chatbot
A modular and comprehensive solution to deploy a Multi-LLM
...A major part of the design is its RAG layer, which enables the chatbot to pull contextual knowledge from connected data sources so responses can be grounded in enterprise content rather than relying only on model memory. -
11
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. -
12
mergekit
Tools for merging pretrained large language models
...This approach allows researchers to combine specialized models into a more versatile system capable of performing multiple tasks. mergekit implements a variety of merging algorithms and strategies that control how model parameters are blended together during the merging process. The library is designed to operate efficiently even in environments with limited hardware resources by using memory-efficient processing methods that can run entirely on CPUs. It also provides configuration-driven workflows that allow users to experiment with different merging strategies without modifying source code. -
13
Learn Claude Code
Bash is all you need, write a claude code with only 16 line code
...It emphasizes a hands-on learning path where each version (from v0 to v4) adds conceptual building blocks like the core agent loop, todo planning, task decomposition, and domain knowledge skills, illuminating the patterns behind what makes a true AI agent tick. The goal is to demystify agent architectures like Claude Code by having learners build simplified versions themselves and observe how tools, memory management, planning constraints, and context isolation contribute to reliable agent behavior. Along the way, the project teaches fundamentals such as how to let models call external tools, maintain clean memory for long tasks, and inject domain expertise without retraining the model. -
14
EasyR1
An Efficient, Scalable, Multi-Modality RL Training Framework
...The project’s philosophy is practicality: sensible defaults, one-command recipes, and compatibility with popular base models let you stand up experiments without wrestling infrastructure. It emphasizes memory-efficient training strategies so you can train long-context or reasoning-dense models on commodity GPUs. The framework is also organized to help you compare training strategies (e.g., pure SFT vs. preference optimization) so you can see what actually moves metrics in math, code, and multi-step reasoning. For teams exploring open reasoning models, EasyR1 provides an opinionated yet flexible path from dataset to deployable checkpoints. -
15
Koog
Koog is the official Kotlin framework for building AI agents
...Ready‑to‑use components address common AI engineering challenges, while intelligent history compression optimizes token usage and preserves context. A powerful streaming API enables real‑time response processing and parallel tool calls. Persistent memory allows agents to retain knowledge across sessions and between agents, and comprehensive tracing facilities provide detailed debugging and monitoring. -
16
ImageSharp
A modern, cross-platform, 2D Graphics library for .NET
...Metadata editing support (IPTC EXIF). Colorspace transforms (RGB/CMYK/Grayscale/CIELab and many more). Over 40 common processing operations. Great performance and memory friendly; work with any dimensions (even hundreds of megapixels). ImageSharp is brimming with features. Common operations are only a few keystrokes away. -
17
EaseProbe
A simple, standalone, and lightweight tool
...Support the bastion/jump server. Connect to a given port using TLS and (optionally) validate for revoked or expired certificates. Run an SSH command on a remote host and check the CPU, Memory, and Disk usage. MySQL. Connect to a MySQL server and run the SHOW STATUS SQL. Redis. Connect to a Redis server and run the PING command. Memcache. Connect to a Memcache server and run the version command or validate a given key/value pair. MongoDB. Connect to a MongoDB server and perform a ping. Kafka. Connect to a Kafka server and perform a list of all topics. -
18
Checked C
Checked C is an extension to C that lets programmers write C code
...Checked C does not address use-after-free errors. Checked C adds static and dynamic checking to C to detect or prevent common programming errors such as buffer overruns and out-of-bounds memory accesses. The goal of the project is to improve systems programming by making fundamental improvements to C. This repo contains sample code, the extension specification, and test code. The Checked C project is extending the C programming language so that programmers can write more secure and reliable C programs. The project is developing an extension to C called Checked C that adds checking to C to detect or prevent common programming errors such as buffer overruns, out-of-bounds memory accesses, and incorrect type casts. -
19
Unified Communication X
Communication framework for data-centric high-performance applications
...UCX exposes a set of abstract communication primitives which utilize the best of available hardware resources and offloads. These include RDMA (InfiniBand and RoCE), TCP, GPUs, shared Memory, and network atomic operations. UCX facilitates rapid development by providing a high-level API, masking the low-level details, while maintaining high-performance and scalability. UCX implements best practices for transfer of messages of all sizes, based on accumulated experience gained from applications running on the world’s largest datacenters and supercomputers. -
20
Pycord
Pycord is a modern, easy to use, feature-rich, and async ready API
...The project supports Discord application APIs, slash commands, user commands, traditional commands, voice options, and performance-focused optional packages. It includes proper rate limit handling and is optimized for both speed and memory usage. Pycord supports current Python versions and offers documentation, guides, examples, and community resources for new bot developers. It is a strong fit for Python developers who want a maintained Discord framework with practical command support and approachable syntax. -
21
DAW JSON Link v3
Fast, convenient JSON serialization and parsing in C++
...The DAW JSON Link library is a high-performance, no allocation, C++ JSON Library. Direct parsing of JSON to your own data structures via simple declarative mappings. Earlier error reporting of unexpected data and errors. Low memory requirement, parser requires a small amount of stack but does not allocate itself. Optimizations based on data types. Does not require owning the mapped types and is not intrusive. -
22
Tendis
Tendis is a high-performance distributed storage system
A high-performance, persistent key-value store developed by Tencent, combining features of Redis with LSM-tree storage for durability. -
23
Node Archiver
a streaming interface for archive generation
Archiver is a Node.js library that provides a streaming interface for creating archive files in various formats, such as ZIP and TAR, supporting multiple compression methods. -
24
Wink-NLP
Developer friendly Natural Language Processing
Wink-NLP is a lightweight and fast natural language processing library for JavaScript, optimized for browser and Node.js environments. -
25
Pyreft
ReFT: Representation Finetuning for Language Models
PyreFT is a tool by Stanford NLP for fine-tuning transformer models with an emphasis on efficient, resource-conserving training and customizability for NLP tasks.