Search Results for "memory"
Sort By:
Showing 53 open source projects for "memory"
View related business solutions-
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
1
SimpleMem
SimpleMem: Efficient Lifelong Memory for LLM Agents
SimpleMem is a lightweight memory-augmented model framework that helps developers build AI applications that retain long-term context and recall relevant information without overloading model context windows. It provides easy-to-use APIs for storing structured memory entries, querying those memories using semantic search, and retrieving context to augment prompt inputs for downstream processing. -
2
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model
ChatGLM-6B is an open bilingual (Chinese + English) conversational language model based on the GLM architecture, with approximately 6.2 billion parameters. The project provides inference code, demos (command line, web, API), quantization support for lower memory deployment, and tools for finetuning (e.g., via P-Tuning v2). It is optimized for dialogue and question answering with a balance between performance and deployability in consumer hardware settings. Support for quantized inference (INT4, INT8) to reduce GPU memory requirements. Automatic mode switching between precision/memory tradeoffs (full/quantized). -
3
MemoryOS
MemoryOS is designed to provide a memory operating system
MemoryOS is an open-source framework designed to provide a structured memory management system for AI agents and large language model applications. The project addresses one of the major limitations of modern language models: their inability to maintain long-term context beyond the limits of their prompt window. MemoryOS introduces a hierarchical memory architecture inspired by operating system memory management principles, allowing agents to store, update, retrieve, and generate information from multiple layers of memory. -
4
AirLLM
AirLLM 70B inference with single 4GB GPU
AirLLM is an open source Python library that enables extremely large language models to run on consumer hardware with very limited GPU memory. The project addresses one of the main barriers to local LLM experimentation by introducing a memory-efficient inference technique that loads model layers sequentially rather than storing the entire model in GPU memory. This layer-wise inference approach allows models with tens of billions of parameters to run on devices with only a few gigabytes of VRAM. ... -
$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.
-
5
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch
bitsandbytes is an open-source library designed to make training and inference of large neural networks more efficient by dramatically reducing memory usage. Built primarily for the PyTorch ecosystem, the library introduces advanced quantization techniques that allow models to operate using reduced numerical precision while maintaining high accuracy. These optimizations enable large language models and other deep learning architectures to run on hardware with limited memory resources, including consumer-grade GPUs. ... -
6
vLLM
A high-throughput and memory-efficient inference and serving engine
vLLM is a fast and easy-to-use library for LLM inference and serving. High-throughput serving with various decoding algorithms, including parallel sampling, beam search, and more. -
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
xLSTM
Neural Network architecture based on ideas of the original LSTM
xLSTM is an open-source machine learning architecture that reimagines the classic Long Short-Term Memory (LSTM) network for modern large-scale language modeling and sequence processing tasks. The project introduces a new recurrent neural network design that incorporates exponential gating mechanisms and enhanced memory structures to overcome limitations of traditional LSTM models. By introducing innovations such as matrix-based memory and improved normalization techniques, xLSTM improves the ability of recurrent networks to capture long-range dependencies in sequential data. ... -
9
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. -
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
R-KV
Redundancy-aware KV Cache Compression for Reasoning Models
...Modern transformer models rely heavily on KV caches during autoregressive decoding, which store intermediate attention states to accelerate generation. However, these caches can consume large amounts of memory, especially in reasoning-oriented models with long context windows. R-KV introduces a method for compressing the KV cache during decoding, allowing models to maintain reasoning performance while reducing memory consumption and computational overhead. The approach focuses on identifying which attention heads and cache components are most important for maintaining reasoning quality, allowing less critical information to be compressed or discarded. ... -
11
claude-obsidian
Claude + Obsidian knowledge companion
...The system follows the LLM Wiki pattern, where information is stored as persistent markdown files that grow richer over time through cross-referencing and synthesis. It includes features such as contradiction detection, orphaned note identification, and automatic indexing. A persistent memory layer ensures continuity across sessions, eliminating the need for repeated context. It also performs autonomous research to fill knowledge gaps and expand the knowledge base. Overall, it turns note-taking into an active, compounding intelligence system. -
12
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. ... -
13
CodeGeeX2
CodeGeeX2: A More Powerful Multilingual Code Generation Model
...With improved inference efficiency, quantization options, and multi-query/flash attention, CodeGeeX2 achieves faster generation speeds and lightweight deployment, requiring as little as 6GB GPU memory at INT4 precision. Its backend powers the CodeGeeX IDE plugins for VS Code, JetBrains, and other editors, offering developers interactive AI assistance with features like infilling and cross-file completion. -
14
LLM Telegram Bot
A Telegram bot for Large Language Models
...The project is designed to provide a customizable AI assistant that can operate within Telegram conversations, supporting dynamic responses based on user input and configurable parameters. It includes features such as conversation memory, allowing the bot to maintain context across multiple messages and provide more coherent responses. The system supports multiple modes or personas, enabling users to switch between different conversational styles or use cases. It also allows fine-tuning of generation parameters such as temperature and token limits, giving users control over response behavior. ... -
15
PEFT
State-of-the-art Parameter-Efficient Fine-Tuning
Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of pre-trained language models (PLMs) to various downstream applications without fine-tuning all the model's parameters. Fine-tuning large-scale PLMs is often prohibitively costly. In this regard, PEFT methods only fine-tune a small number of (extra) model parameters, thereby greatly decreasing the computational and storage costs. Recent State-of-the-Art PEFT techniques achieve performance comparable to that of full... -
16
METATRON
AI-powered penetration testing assistant using local LLM on linux
...It provides a structured system for task delegation, communication, and collaboration between agents. The framework emphasizes scalability, allowing multiple agents to work together on large or complex problems. It includes mechanisms for managing context, memory, and execution flow across tasks. METATRON is particularly useful for building advanced AI systems that require coordination rather than isolated responses. Its architecture supports modular expansion and integration with different models. Overall, it enables the creation of collaborative AI ecosystems. -
17
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. -
18
Context Engineering
A frontier, first-principles handbook
...Moving beyond traditional prompt engineering, this repository defines and explores how to craft and provide complete context payloads — not just single prompts — to large language models so they can perform tasks more reliably and intelligently. It takes inspiration from thought leaders like Andrej Karpathy and bridges theory with practical examples, offering structured guidance on context orchestration, memory, retrieval, and state control within AI workflows. With extensive materials drawn from research, surveys, and visual explanations, the project acts as both a learning resource and a reference for practitioners looking to improve model behavior by engineering richer inputs. -
19
llm.c
LLM training in simple, raw C/CUDA
llm.c is a minimalist, systems-level implementation of a small transformer-based language model in C that prioritizes clarity and educational value. By stripping away heavy frameworks, it exposes the core math and memory flows of embeddings, attention, and feed-forward layers. The code illustrates how to wire forward passes, losses, and simple training or inference loops with direct control over arrays and buffers. Its compact design makes it easy to trace execution, profile hotspots, and understand the cost of each operation. Portability is a goal: it aims to compile with common toolchains and run on modest hardware for small experiments. ... -
20
Ludwig AI
Low-code framework for building custom LLMs, neural networks
...Comprehensive config validation detects invalid parameter combinations and prevents runtime failures. Automatic batch size selection, distributed training (DDP, DeepSpeed), parameter efficient fine-tuning (PEFT), 4-bit quantization (QLoRA), and larger-than-memory datasets. Retain full control of your models down to the activation functions. Support for hyperparameter optimization, explainability, and rich metric visualizations. Experiment with different model architectures, tasks, features, and modalities with just a few parameter changes in the config. Think building blocks for deep learning. -
21
how-to-optim-algorithm-in-cuda
How to optimize some algorithm in cuda
...The project combines technical notes, code examples, and practical experiments that demonstrate how common computational kernels can be optimized to improve speed and memory efficiency. Instead of presenting only theoretical explanations, the repository includes hand-written CUDA implementations of fundamental operations such as reductions, element-wise computations, softmax, and attention mechanisms. These examples show how different optimization techniques influence performance on modern GPU hardware and allow readers to experiment with real implementations. ... -
22
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. -
23
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. -
24
LLM Vision
Visual intelligence for your home.
LLM Vision is an open-source integration for Home Assistant that adds multimodal large language model capabilities to smart home environments. The project enables Home Assistant to analyze images, video files, and live camera feeds using vision-capable AI models. Instead of relying only on traditional object detection pipelines, it allows users to send prompts about visual content and receive contextual descriptions or answers about what is happening in camera footage. The system can process... -
25
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.
