Search Results for "memory" - Page 19
Sort By:
Showing 3196 open source projects for "memory"
View related business solutions-
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
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.
-
1
Open-LLM-VTuber
Open source AI VTuber platform with voice chat and Live2D avatars
Open-LLM-VTuber is an open source platform designed to create AI-powered VTuber characters that can interact with users through voice and animated avatars. It enables hands-free conversations with large language models by combining speech recognition, language processing, and text-to-speech synthesis into a single system. Users can speak directly to the AI character, and the system can respond with a generated voice while animating a Live2D avatar to simulate a talking virtual personality.... -
2
verl-agent
Designed for training LLM/VLM agents via RL
...This step-wise interaction model makes it possible to train agents to operate in long-horizon scenarios where decisions depend on cumulative context and previous outcomes. Developers can configure memory modules that determine how historical information is stored and incorporated into each step of the reasoning process. -
3
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. -
4
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. -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
5
AI Agents From Scratch
Demystify AI agents by building them yourself. Local LLMs
...The project walks through the process of constructing agents step by step, beginning with simple prompt-based interactions and gradually introducing more advanced capabilities such as planning, tool use, and memory. The repository provides example implementations that demonstrate how language models can interact with external systems, perform reasoning tasks, and execute structured workflows. It focuses on explaining the architecture of agent systems rather than simply providing finished code, making it useful for developers who want to understand how AI agents actually work internally. ... -
6
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. -
7
NagaAgent
A simple yet powerful agent framework for personal assistants
...It provides abstractions for representing goals, context, and state so that agents can plan sequences of actions, evaluate outcomes, and adjust behavior over time. The project includes mechanisms for semantic memory, reasoning pipelines, and integration points with external data sources and language models so that agents can interpret natural language instructions and produce coherent multi-step outputs. Rather than being a simple chatbot, NagaAgent emphasizes persistent thought cycles, context retention, and the ability to decompose complex tasks into smaller executable units, earning it a place in research explorations of agent design. ... -
8
MongoDB Rust Driver
The official MongoDB Rust Driver
The MongoDB Rust Driver is a native, idiomatic Rust client for MongoDB that gives systems software and back-end services the ability to interact with MongoDB from safe, performant Rust code. It makes extensive use of Rust’s ownership and type systems to ensure memory safety, thread safety, and predictable performance without garbage collection overhead. The driver supports common MongoDB features like CRUD operations, indexing, aggregations, change streams, and transactions, enabling full use of the database’s capabilities from Rust applications. Because it’s asynchronous by design, it works well with Rust async runtimes like Tokio and async-std, letting developers build highly concurrent networked services that efficiently use modern multicore hardware. ... -
9
Android Interview Questions
Your Cheat Sheet For Android Interview
...Modern practices are addressed as well—Kotlin language features, coroutines, Jetpack components, MVVM/MVI architecture, dependency injection, and testing strategies. Performance and reliability topics receive attention, such as memory management, threading, WorkManager, networking, and offline storage patterns. The content favors concise, practical answers that interviewers expect, helping candidates rehearse concepts and trade-offs rather than memorize trivia. It’s equally useful for brushing up before an interview and for leveling up day-to-day Android engineering knowledge. -
$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
FastbuildAI
An open-source AI framework for developers and entrepreneurs
...It emphasizes fast iteration: you describe tasks declaratively, wire up tools with typed schemas, and let the runtime handle planning, retries, and result aggregation. The project leans into reproducibility with run records, seed control, and structured traces so you can compare behaviors across versions and inputs. Prompt and memory management are treated as first-class concerns, enabling short-lived scratchpads for reasoning as well as long-horizon state when an agent operates over multiple sessions. The codebase favors small, composable pieces—executors, routers, guards—so teams can adopt just what they need instead of buying into a monolith. It is equally comfortable running locally for development or behind a simple API for production bots and automation workflows. -
11
Atheris
A Coverage-Guided, Native Python Fuzzer
...It hooks into Python’s interpreter to collect fine-grained coverage and uses that signal to evolve inputs, pushing programs into previously unexplored code paths. Because many Python libraries are thin wrappers over C/C++ code, Atheris is equally adept at surfacing memory safety issues in extension modules compiled with sanitizers. The tool integrates smoothly with Python’s packaging and unit-test ecosystems, so you can wrap existing tests as fuzz targets and keep results understandable. It supports structured input strategies and custom mutators, which is especially helpful for text and data formats common in Python workloads. ... -
12
Honggfuzz
Security oriented software fuzzer
honggfuzz is a general-purpose, high-performance fuzzer that mixes coverage feedback with practical crash triage to uncover memory-safety and logic bugs. It supports multiple fuzzing modes—stdin, file, and networking—so targets can be exercised the same way they run in production. Instrumentation via compiler hooks or hardware/perf counters guides mutations toward previously unseen edges, while persistent mode keeps the target process alive to amortize startup costs. -
13
Wuffs
Wrangling Untrusted File Formats Safely
Wuffs is a memory-safe, zero-dependency library and domain-specific language for writing high-performance image codecs and related parsers. Instead of trusting ad-hoc C, Wuffs code is compiled to C with strong bounds, integer, and state checks inserted by construction, aiming to eliminate whole classes of security bugs without a heavy runtime. The design prioritizes predictable performance: decoders avoid dynamic allocation by default, return explicit “short read” signals, and run well in streaming or sandbox-free environments. ... -
14
DLRM
An implementation of a deep learning recommendation model (DLRM)
...It includes data loaders for standard benchmarks (like Criteo), training scripts, evaluation tools, and capabilities like mixed precision, gradient compression, and memory fusion to maximize throughput. -
15
DeepEP
DeepEP: an efficient expert-parallel communication library
...Because MoE architectures require routing inputs to different experts, communication overhead can become a bottleneck — DeepEP addresses that by providing optimized GPU kernels and efficient dispatch/combining logic. The library also supports low-precision operations (such as FP8) to reduce memory and bandwidth usage during communication. DeepEP is aimed at large-scale model inference or training systems where expert parallelism is used to scale model capacity without replicating entire networks. -
16
OSS-Fuzz
OSS-Fuzz - continuous fuzzing for open source software
OSS-Fuzz is a large-scale fuzz testing platform developed by Google to improve the security and reliability of widely used open source software. Fuzz testing is a proven method for uncovering programming errors such as buffer overflows and memory leaks, which can lead to severe security vulnerabilities. By leveraging guided in-process fuzzing, Google has already identified thousands of issues in projects like Chrome, and this initiative extends the same capabilities to the broader open source community. OSS-Fuzz integrates modern fuzzing engines with sanitizers and runs them at scale in a distributed environment, providing automated testing and continuous monitoring. ... -
17
Ring
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI
...Its architectures and training approaches are tuned to enable efficient and capable reasoning performance. Reasoning-optimized model with reinforcement learning enhancements. Efficient architecture and memory design for large-scale reasoning. If you are located in mainland China, we also provide the model on ModelScope.cn to speed up the download process. -
18
rCore-Tutorial-Book-v3
A book about how to write OS kernels in Rust easily
...It is written in Markdown and powered by mdBook, making it easy to read, navigate, and contribute to. The book combines theoretical explanations with practical exercises, allowing students and enthusiasts to understand core OS concepts like bootstrapping, memory management, and process scheduling through hands-on implementation. -
19
Mem0
The Memory layer for AI Agents
Mem0 is a self-improving memory layer designed for Large Language Model (LLM) applications, enabling personalized AI experiences that save costs and delight users. It remembers user preferences, adapts to individual needs, and continuously improves over time. Key features include enhancing future conversations by building smarter AI that learns from every interaction, reducing LLM costs by up to 80% through intelligent data filtering, delivering more accurate and personalized AI outputs by leveraging historical context, and offering easy integration compatible with platforms like OpenAI and Claude. ... -
20
Async.MQTT5
A C++17 MQTT client based on Boost.Asio
Async.MQTT5 is a professional, industrial-grade C++17 client built on Boost.Asio. This Client is designed for publishing or receiving messages from an MQTT 5.0 compatible Broker. Async.MQTT5 represents a comprehensive implementation of the MQTT 5.0 protocol standard, offering full support for publishing or receiving messages with QoS 0, 1, and 2. The MQTT protocol is widely utilised for communication in various real-world scenarios, primarily serving as a reliable communication protocol for... -
21
Chronicle Wire
Low Garbage Java Serialisation Library that supports multiple formats
Chronicle Wire is a Wire Format abstraction library. Chronicle Wire uses Chronicle Bytes for bytes manipulation, and Chronicle Core for low-level JVM access. Configuration includes aliased type information. This supports easy extension by adding new classes/versions, and cross-platform using type aliasing. By supporting types, a configuration file can bootstrap itself. You control how the configuration file is decoded. See example Queue Enterprise config. To send the configuration of a... -
22
jQuery contextMenu plugin & polyfill
jQuery contextMenu plugin & polyfill
...Once a menu is registered, it cannot be altered. That means no commands can be added or removed from the menu. This allows contextMenu to keep a single definition in memory, which enables it to work with hundreds of trigger objects. contextMenu knows the two callbacks show and hide which can be used to update the state of commands within the menu. -
23
OpenFold
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction
OpenFold carefully reproduces (almost) all of the features of the original open source inference code (v2.0.1). The sole exception is model ensembling, which fared poorly in DeepMind's own ablation testing and is being phased out in future DeepMind experiments. It is omitted here for the sake of reducing clutter. In cases where the Nature paper differs from the source, we always defer to the latter. OpenFold is trainable in full precision, half precision, or bfloat16 with or without... -
24
Colossal-AI
Making large AI models cheaper, faster and more accessible
The Transformer architecture has improved the performance of deep learning models in domains such as Computer Vision and Natural Language Processing. Together with better performance come larger model sizes. This imposes challenges to the memory wall of the current accelerator hardware such as GPU. It is never ideal to train large models such as Vision Transformer, BERT, and GPT on a single GPU or a single machine. There is an urgent demand to train models in a distributed environment. However, distributed training, especially model parallelism, often requires domain expertise in computer systems and architecture. ... -
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.
