Search Results for "memory" - Page 17
Sort By:
Showing 3192 open source projects for "memory"
View related business solutions-
$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.
-
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.
-
1
Clawbolt
The AI Assistant that actually does things for the trades
...The platform allows users to interact with an AI assistant through iMessage, SMS, RCS, Telegram, and related messaging channels to handle tasks such as estimates, invoices, scheduling, reminders, and client communication. Clawbolt combines large language model orchestration with memory systems, file storage integrations, and tool-calling workflows to create an assistant capable of managing real operational tasks instead of only answering prompts. The project supports integrations with QuickBooks Online, Google Calendar, Dropbox, and Google Drive, enabling automated business workflows tied directly to conversations. ... -
2
Fast JSON
Fast JSON parser and validator for Go
Fast JSON is a high-performance JSON parser and generator written in Go, designed for speed and efficiency in handling large volumes of structured data. It avoids unnecessary memory allocations and reflection, enabling significantly faster parsing compared to standard libraries. The project provides a low-level API that allows developers to work directly with JSON structures without converting them into intermediate representations. Its design prioritizes minimal overhead and maximum throughput, making it suitable for performance-critical applications such as APIs, data pipelines, and real-time systems. fastjson also supports both parsing and serialization, offering flexibility in data handling. ... -
3
LangChainGo
LangChain for Go, the easiest way to write LLM-based programs in Go
LangChainGo is a Go-based implementation of the LangChain framework, designed to help developers build applications powered by large language models using the Go programming language. It provides a modular architecture that allows developers to combine components such as language models, chains, agents, memory systems, and vector stores into flexible workflows. The framework emphasizes composability, making it easy to create complex pipelines that integrate LLMs with external data sources, APIs, and tools. It supports multiple providers including OpenAI, Anthropic, Google, and local models, offering a unified interface for interacting with different backends. ... -
4
GenericAgent
Self-evolving autonomous agent framework
The GenericAgent project is a flexible framework for building autonomous AI agents that can operate across diverse tasks and environments. It is designed around modularity, allowing developers to define agents with interchangeable components such as tools, memory systems, and reasoning strategies. The architecture emphasizes generality, enabling the same agent framework to be adapted for different domains including coding, research, and task automation. It integrates with modern language models to provide planning, execution, and iterative reasoning capabilities, making it suitable for complex workflows. ... -
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
Bloom
An open source, agentic Loom alternative
...It allows users to record sessions locally while simultaneously preparing those recordings to be processed, indexed, and analyzed by AI systems, effectively turning simple screen captures into structured, queryable data. The project is part of the broader VideoDB ecosystem, which focuses on giving AI agents perception and memory through video, enabling them to understand and act upon visual information. Bloom supports the concept of “agentic video,” where recordings are not just passive media files but interactive assets that can be searched, summarized, and transformed into workflows or insights. This makes it particularly useful for use cases such as debugging AI agents, documenting processes, training models, or creating automated video-based reports. -
6
BigQuery Emulator
BigQuery emulator server implemented in Go
...The emulator supports a large portion of the BigQuery API surface, including dataset management, query execution, and data ingestion, allowing applications to interact with it as if it were the real service. It uses SQLite as its underlying storage engine, with options for in-memory or persistent file-based databases depending on the use case. The system also implements many features of Google Standard SQL, including hundreds of functions and advanced query constructs, enabling realistic query testing. -
7
Team9
Team9 is a collaborative workspace for AI agents
...It builds on agent frameworks like OpenClaw and introduces a managed environment where agents can be assigned roles, share context, and execute tasks collaboratively. The system emphasizes a “local-first” architecture, allowing agents to run on user-controlled infrastructure while maintaining persistent memory and data privacy. It includes orchestration mechanisms that allow agents to operate continuously through scheduled tasks, event-driven triggers, and long-running processes. The platform also integrates messaging gateways and communication channels, enabling agents to interact with users and systems in real time. Its design reflects a shift toward treating AI agents as operational units within organizations rather than isolated tools. -
8
AI Agent Deep Dive
AI Agent Source Code Deep Research Report
AI Agent Deep Dive is a comprehensive educational repository designed to provide a deep and structured understanding of how modern AI agents work, focusing on architecture, workflows, and real-world implementation patterns. It breaks down complex concepts such as planning, tool usage, memory management, and multi-step reasoning into digestible explanations and practical examples. The project is organized as a learning resource rather than a standalone framework, making it particularly useful for developers who want to move beyond surface-level prompt engineering into full agent system design. It explores how agents interact with environments, execute tasks, and maintain context over time, highlighting both strengths and limitations of current approaches. ... -
9
Rust Training Books
Beginner, advanced, expert level Rust training material
...The material emphasizes hands-on learning, encouraging users to actively write and experiment with code rather than passively reading documentation. It reflects Rust’s core philosophy of safety and performance, helping developers understand how to write efficient and memory-safe applications. The repository is organized in a modular way, allowing learners to progress step by step while reinforcing concepts through exercises and real-world scenarios. It is suitable for both beginners transitioning from other languages and experienced developers seeking deeper understanding of Rust’s unique paradigms. -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
10
OP Vault
Give ChatGPT long-term memory using the OP Stack
OP Vault is an open-source system designed to give large language models long-term memory by enabling them to interact with a custom knowledge base built from user-provided documents. It combines a backend written in Go with a React frontend, allowing users to upload files such as PDFs, text documents, and books to create a searchable repository of information. The system uses vector databases like Pinecone alongside OpenAI models to index and retrieve relevant content, enabling precise question-answering grounded in the uploaded materials. ... -
11
CubeCL
Multi-platform high-performance compute language extension for Rust
...It provides an abstraction layer that allows developers to write portable, hardware-efficient compute kernels without directly dealing with complex GPU APIs such as CUDA or OpenCL. CubeCL focuses on delivering predictable performance and composability by exposing explicit control over memory layouts, parallelism, and execution patterns while still maintaining a developer-friendly syntax. The framework is built to integrate tightly with modern ML stacks, enabling efficient tensor operations and custom kernel development that can outperform generic libraries in specialized workloads. By combining compiler optimizations with a domain-specific language, CubeCL allows developers to generate highly optimized code for different hardware backends while maintaining a single source of truth. -
12
Numba CUDA Target
The CUDA target for Numba
...This approach significantly lowers the barrier to entry for GPU programming by eliminating the need to write CUDA C++ while still delivering high performance. The project supports the SIMT programming model, allowing developers to control threads, blocks, and memory hierarchies similarly to native CUDA programming. It is also used as a foundation for accelerating higher-level libraries such as RAPIDS, where custom user-defined GPU functions are required. The repository represents the continuation of CUDA support after its deprecation in core Numba, ensuring ongoing development and optimization under NVIDIA’s ecosystem. -
13
TypeAgent Python
Structured RAG: ingest, index, query
...The repository is intended primarily as a research prototype and sample code rather than a production-ready framework, allowing developers to experiment with building AI agents that maintain structured memory and perform tasks through defined actions. -
14
Kodezi Chronos
Kodezi Chronos is a debugging-first language model
...The project introduces architectural techniques such as Adaptive Graph-Guided Retrieval, which allows the system to navigate large repositories and retrieve relevant debugging information from multiple sources. Another component, Persistent Debug Memory, allows the system to learn patterns from past debugging sessions and apply that knowledge to future problems. The repository mainly contains research documentation, evaluation benchmarks, and experimental frameworks rather than the full proprietary model implementation. -
15
Gollama
Go manage your Ollama models
...Beyond standard model management, Gollama can display metadata such as size, quantization level, model family, and modification date, which helps users compare models quickly. One of its more distinctive capabilities is a VRAM estimation system that can calculate memory requirements, estimate context limits, and help users choose quantization settings that fit available hardware. -
16
LLM-Finetuning
LLM Finetuning with peft
...These tutorials show how developers can adapt pretrained models for tasks such as chatbots, classification, and instruction following. The project also illustrates how low-precision training techniques and adapter-based methods reduce memory requirements while maintaining strong model performance. -
17
Cloudflare Agents
Build and deploy AI Agents on Cloudflare
...The project includes SDKs, templates, and deployment tooling that simplify the process of connecting agents to external APIs, storage systems, and workflows. Its architecture emphasizes persistent memory, enabling agents to maintain context across sessions and interactions. Developers can orchestrate complex behaviors using workflows and durable objects, making it suitable for production-grade autonomous systems. Overall, Cloudflare Agents aims to streamline the development of scalable AI automation that operates close to users for improved performance. -
18
SkillKit
Supercharge AI coding agents with portable skills
SkillKit is a developer-centric toolkit for constructing modular, reusable AI agent skills and integrating them into workflows, platforms, and applications with minimal overhead. It provides a set of abstractions, templates, helper utilities, and patterns that help developers define intents, actions, context handling, memory management, and multi-step logic so that skills can be built once and reused everywhere. Instead of reinventing the wheel every time a new conversational or automation feature is needed, SkillKit encourages engineers to encapsulate logic into coherent skill units that can be registered, tested, and composed together. It supports integration with common agent runtimes and toolkits, allowing skills to be plugged into existing architectures without requiring deep infrastructure rewrites. ... -
19
claude-reflect
A self-learning system for Claude Code that captures corrections
...It watches what you correct Claude about — such as preferring a particular model, style, or workflow — and automatically queues those learnings, then lets you review and sync them back into configuration files like CLAUDE.md and agent definitions so Claude remembers them across sessions. Over time, this creates a personalized memory that helps the AI align more closely with your conventions, avoiding repeated misunderstandings and reducing friction in long-running or recurring tasks. In addition to capturing corrections, claude-reflect analyzes session history to identify repeated patterns and propose reusable commands or workflows, which can be converted into skills that accelerate productivity. -
20
ngraph.path
Path finding in a graph
...It can be integrated with visualization libraries like VivaGraphJS to animate or highlight computed paths in a rendered graph, enabling interactive routing features. Its data structures and algorithm choices are optimized for performance and memory efficiency, so even large meshes or road networks can be navigated interactively. With its standalone design, ngraph.path can be used in browser apps, server-side Node.js services. -
21
lilliput
Resize images and animated GIFs in Go
Lilliput is a lightweight image codec and processing library tailored for environments where performance, portability, and resource efficiency are critical, such as gaming clients, real-time applications, or systems with constrained memory budgets. Designed to support fast decoding and manipulation of common image formats like PNG, JPEG, WebP, and BMP, Lilliput is engineered to minimize dependencies and be easily integrated into a variety of C/C++-based projects without pulling in heavy external libraries. The library provides APIs for scaling, resizing, color conversions, and basic image operations that are crucial for performance-sensitive applications that need to display or transform images on the fly. ... -
22
php-file-iterator
FilterIterator implementation that filters files
...Exclusion lists help you skip vendor directories, VCS folders, or generated artifacts that would otherwise slow down tools. The iterator interface means results are streamed rather than loaded at once, which keeps memory usage modest on large codebases. It also plays nicely with glob patterns and SPL iterators, so you can combine it with other filesystem utilities. As part of the PHPUnit tooling suite, it’s optimized for speed and predictable behavior across platforms. -
23
Counter
Web Analytics made simple
...The backend is designed to be resource-light while still providing the essential metrics teams care about, such as page views, referrers, and basic geography. Rather than storing everything in a monolithic database, it combines a fast in-memory store for hot data with archival to a traditional SQL store for long-term retention. The client snippet is tiny and cookieless, which helps reduce layout shift and keeps page performance high. Because it’s a small Go service with a straightforward architecture, it can be self-hosted easily and integrated into existing stacks. The philosophy is to deliver “just enough” analytics for dashboards and reporting without the overhead or tracking footprint of big-box platforms. -
24
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. ... -
25
Servo
Embed web technologies in applications
Servo is an experimental, highly parallel, and embeddable browser rendering engine written in Rust. It leverages Rust’s memory-safety and concurrency strengths, supports modern GPU-powered rendering (WebGL/WebGPU), and serves as a research-forward alternative to traditional browser engines. Servo is a prototype web browser engine written in the Rust language. It is currently developed on 64-bit macOS, 64-bit Linux, 64-bit Windows, 64-bit OpenHarmony, and Android.