Search Results for "memory" - Page 6
Sort By:
Showing 498 open source projects for "memory"
View related business solutions-
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.
-
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
1
OpenSRE
Build your own AI SRE agents. The open source toolkit for the AI era
...When an alert is triggered, the system autonomously analyzes correlated signals, identifies anomalies, and generates structured investigation reports with probable causes and recommended actions. Its multi-agent architecture allows parallel reasoning across systems, mimicking how experienced SRE teams debug complex issues. The platform also incorporates memory and knowledge graph capabilities to learn from past incidents and improve future investigations. It is designed to run locally within an organization’s infrastructure, ensuring data privacy and compliance. -
2
Claw Compactor
14-stage Fusion Pipeline for LLM token compression
...It is especially useful in autonomous workflows where agents accumulate large volumes of interaction history over time. The project aligns with broader strategies in AI systems that balance memory retention with computational constraints. Overall, claw-compactor functions as an infrastructure component that enhances scalability and stability in persistent AI agent environments. -
3
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. -
4
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. -
$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.
-
5
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. ... -
6
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. ... -
7
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. -
8
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. -
9
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. ... -
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.
-
10
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. -
11
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. -
12
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. ... -
13
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... -
14
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. ... -
15
redis-py
Redis Python client
redis-py is the official Python client for interacting with Redis, the in-memory data structure store. It supports all Redis commands and data types, making it easy to build caching, messaging, or real-time analytics features in Python applications. With both synchronous and asyncio support, redis-py is suited for modern Python projects and integrates smoothly into web frameworks, task queues, and backend services. -
16
SageAttention
NeurIPS2025 Spotlight] Quantized Attention
...The system achieves this by using low-precision numerical formats such as INT4, FP8, or INT8 to represent key matrices within the attention computation. These optimizations allow models to perform matrix operations faster and consume less memory during inference. SageAttention is designed to function as a plug-and-play replacement for standard attention implementations, enabling developers to accelerate existing models without modifying their architecture. -
17
Triton
Development repository for the Triton language and compiler
...It aims to bridge the gap between low-level GPU programming, such as CUDA, and higher-level abstractions by providing a more productive and flexible environment for developers. Triton enables users to write optimized kernels for machine learning workloads while maintaining readability and control over performance-critical aspects like memory access patterns and parallel execution. The project leverages LLVM and MLIR to compile code into efficient GPU instructions, supporting both NVIDIA and AMD hardware. It is widely used in research and production environments where custom tensor operations are required, offering both high performance and developer-friendly syntax. -
18
Whisper-WebUI
A Web UI for easy subtitle using whisper model
...Built with Gradio, it allows users to upload audio or video files, process them locally, and generate accurate text outputs without relying on command-line tools. The platform integrates optimized implementations such as faster-whisper, significantly improving transcription speed and reducing memory usage compared to standard models. It supports multiple input sources including local files, YouTube content, and microphone input, making it versatile for different workflows. Whisper WebUI also includes advanced preprocessing and postprocessing features such as voice activity detection, background music separation, and speaker diarization, enabling more accurate and structured outputs. -
19
Torrra
A Python tool that lets you search and download torrents
...The core of Torrra is built with modern asynchronous I/O and efficient resource handling, allowing it to manage multiple active torrents, peer connections, and swarm interactions without wasting CPU or memory. Users can add, pause, prioritize, and remove torrents dynamically, while the client intelligently manages piece selection, peer discovery, and bandwidth allocation to optimize download throughput. Torrra also includes hooks for event monitoring and status reporting, enabling third-party tools to visualize torrent progress or integrate with home automation dashboards. -
20
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. -
21
Spring AI Alibaba Examples
Spring AI Alibaba examples for building and testing AI apps
...Each module focuses on a specific use case such as chat, image processing, audio handling, graph workflows, and retrieval-augmented generation. The examples highlight how to integrate AI models, manage prompts, handle memory, and build multi-model or multi-agent workflows. Developers can explore individual project folders for detailed instructions and implementation guidance. Spring AI Alibaba Examples also supports experimentation through playground modules and encourages contributions to expand real-world AI use cases and improve development practices. -
22
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. -
23
Continuous Claude v3
Context management for Claude Code. Hooks maintain state via ledgers
Continuous Claude v3 is a persistent, multi-agent development environment built around the Claude Code CLI that aims to overcome the limitations of standard LLM context windows. Rather than relying on a single session’s context, Continuous Claude uses mechanisms like ledgers, YAML handoffs, and a memory system to preserve and recall state across multiple sessions, ensuring that learned insights and plans are not lost when context compaction occurs. The project orchestrates many specialized agents and skills—109 skills and 32 agents—so that complex coding tasks can be broken down, analyzed, and executed collaboratively by different components. ... -
24
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. -
25
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.
