Search Results for "memory" - Page 6
Sort By:
Showing 2490 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.
-
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
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. -
2
PicoLM
Run a 1-billion parameter LLM on a $10 board with 256MB RAM
PicoLM is an open-source inference framework designed to run large language models on extremely constrained hardware environments such as inexpensive single-board computers and embedded systems. The project focuses on enabling efficient local inference by optimizing memory usage, computation, and system dependencies so that relatively large models can operate on devices with minimal RAM. It is written primarily in C and designed with a minimalist architecture that removes unnecessary dependencies and external libraries. The runtime is capable of running language models with billions of parameters on devices with only a few hundred megabytes of memory, which is significantly lower than typical LLM infrastructure requirements. ... -
3
NullClaw
Fastest, smallest, and fully autonomous AI assistant infrastructure
...At just 678 KB with ~1 MB peak RAM usage, it boots in under 2 milliseconds and runs on virtually any hardware, including low-cost ARM boards. Despite its size, it delivers a complete AI stack with 22+ model providers, 18+ communication channels, integrated tools, hybrid memory, and sandboxed runtime support. Its architecture is fully modular, using vtable interfaces that allow providers, channels, tools, memory backends, and runtimes to be swapped without code changes. NullClaw is secure by design, enforcing pairing-based authentication, strict sandboxing, encrypted secrets, resource limits, and workspace scoping by default. ... -
4
llmfit
157 models, 30 providers, one command to find what runs on hardware
llmfit is a terminal-based utility that helps developers determine which large language models can realistically run on their local hardware by analyzing system resources and model requirements. The tool automatically detects CPU, RAM, GPU, and VRAM specifications, then ranks available models based on performance factors such as speed, quality, and memory fit. It provides both an interactive terminal user interface and a traditional CLI mode, enabling flexible workflows for different user preferences. llmfit also supports advanced configurations including multi-GPU setups, mixture-of-experts architectures, and dynamic quantization recommendations. By presenting clear performance estimates and compatibility guidance, the project reduces the trial-and-error typically involved in local LLM experimentation. ... -
$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
MimiClaw
Run OpenClaw on a $5 chip
MimiClaw (from the mimiclaw project) is an edge-AI personal assistant that runs directly on extremely low-cost hardware like an ESP32-S3 microcontroller without a full operating system, Node.js, or cloud backend. By running pure C on a bare-metal chip, MimiClaw brings AI interactions and persistent memory to a tiny USB-powered device you can carry in your pocket. You connect the device to Wi-Fi and chat with it using Telegram, making it a convenient always-on assistant for tasks like reminders, quick lookups, or custom AI interactions. Even though it’s running on minimal hardware, MimiClaw maintains local memory that persists across power cycles, enabling context continuity over time without relying on cloud services. ... -
6
Stopwatch Component
Provides a way to profile code
Symfony Stopwatch is a lightweight component designed to measure the time and memory usage of code execution. It helps developers profile their applications by tracking the duration of specific operations and monitoring performance. Stopwatch is ideal for identifying bottlenecks and optimizing performance, especially in complex Symfony applications. It can also be used independently in any PHP project to measure the efficiency of code segments. -
7
MCP Server Qdrant
An official Qdrant Model Context Protocol (MCP) server implementation
The Qdrant MCP Server is an official Model Context Protocol server that integrates with the Qdrant vector search engine. It acts as a semantic memory layer, allowing for the storage and retrieval of vector-based data, enhancing the capabilities of AI applications requiring semantic search functionalities. -
8
JSON-java
A reference implementation of a JSON package in Java
JSON is a light-weight language-independent data interchange format. The JSON-Java package is a reference implementation that demonstrates how to parse JSON documents into Java objects and how to generate new JSON documents from the Java classes. -
9
ncnn
High-performance neural network inference framework for mobile
ncnn is a high-performance neural network inference computing framework designed specifically for mobile platforms. It brings artificial intelligence right at your fingertips with no third-party dependencies, and speeds faster than all other known open source frameworks for mobile phone cpu. ncnn allows developers to easily deploy deep learning algorithm models to the mobile platform and create intelligent APPs. It is cross-platform and supports most commonly used CNN networks, including... -
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.
-
10
Personal AI Infrastructure
Agentic AI Infrastructure for magnifying HUMAN capabilities
...Its architecture supports long-term memory, verification of actions, and ongoing self-improvement, blurring the line between “assistant” and persistent, evolving collaborator. -
11
Claude Cognitive
Persistent context and multi-instance coordination
Claude Cognitive is an advanced memory and context-management extension designed to address the stateless limitations of Claude Code by giving the model a form of persistent “working memory” and multi-instance coordination. It introduces an attention-based context router that prioritizes files and content relevant to the current development discussion — tagging them as HOT, WARM, or COLD based on recency and keyword activation — so Claude Code doesn’t waste token budget rereading irrelevant code. ... -
12
PyOpenCL
OpenCL integration for Python, plus shiny features
...It enables developers to harness the full power of heterogeneous computing directly from Python, combining Python’s ease of use with the performance benefits of OpenCL. PyOpenCL also includes convenient features for managing memory, compiling kernels, and interfacing with NumPy, making it a preferred choice in scientific computing, data analysis, and machine learning workflows that demand acceleration. -
13
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. -
14
data.table
Extends base R’s data for high-performance data manipulation
...Relies only on base R; maintained API, active community; good memory efficiency. Non-equi joins, overlapping range joins, ordered joins, joining with aggregations, etc. -
15
OpenGL Mathematics
Highly Optimized Graphics Math (glm) for C
...Euler angles was implemented in reverse order (extrinsic) it was fixed, now they are intrinsic. Make sure that you have the latest version. vec4 and mat4 variables must be aligned. (There will be unaligned versions later). cglm doesn't alloc any memory on heap. So it doesn't provide any allocator. You should alloc memory for out parameters too if you pass pointer of memory location. -
16
xlswriter
PHP Extension for creating and reader XLSX files
PHPExcel has been unable to work properly for memory reasons at 40,000 and 100000 points, but it can be resolved by modifying the ini configuration, but the time may take longer to complete the work. xlswriter is a PHP C Extension that can be used to write text, numbers, formulas and hyperlinks to multiple worksheets in an Excel 2007+ XLSX file. -
17
Claw Code
AI agent harness for AI coding agents
...It emphasizes harness engineering—how agents are structured, how they interact with tools, and how they maintain context during execution. The system is being actively expanded, with a Rust-based runtime in development to improve performance and memory safety. Overall, Claw Code serves as a research-driven platform for advancing agent-based software development systems. -
18
NanoClaw
A lightweight alternative to Clawdbot / OpenClaw
...The project connects directly to WhatsApp, letting you deploy an assistant that can chat in a familiar interface while still supporting real agent behaviors instead of simple call-and-response prompts. It includes memory so the assistant can retain important context across interactions, enabling more consistent follow-through on ongoing tasks. It also supports scheduled jobs, making it suitable for recurring reminders, periodic automations, and timed workflows without needing an external orchestrator. -
19
bitnet.cpp
Official inference framework for 1-bit LLMs
bitnet.cpp is the official open-source inference framework and ecosystem designed to enable ultra-efficient execution of 1-bit large language models (LLMs), which quantize most model parameters to ternary values (-1, 0, +1) while maintaining competitive performance with full-precision counterparts. At its core is bitnet.cpp, a highly optimized C++ backend that supports fast, low-memory inference on both CPUs and GPUs, enabling models such as BitNet b1.58 to run without requiring enormous compute infrastructure. The project’s focus on extreme quantization dramatically reduces memory footprint and energy consumption compared with traditional 16-bit or 32-bit LLMs, making it practical to deploy advanced language understanding and generation models on everyday machines. ... -
20
parca
Continuous profiling for analysis of CPU and memory usage
Continuous profiling for analysis of CPU, memory usage over time, and down-to-the-line number. Saving infrastructure costs, improving performance, and increasing reliability. A single profiler, using eBPF, automatically discovers targets from Kubernetes or systemd across the entire infrastructure with very low overhead. Supports C, C++, Rust, Go, and more. Both producing pprof formatted profiles with the eBPF-based profiler and ingesting any pprof formatted profiles allowing for wide language adoption and interoperability with existing tooling. ... -
21
AgentScope
Build and run agents you can see, understand and trust
...It provides essential abstractions that evolve with advancing LLM capabilities, emphasizing reasoning, tool use, and flexible orchestration rather than rigid prompt constraints. With built-in support for ReAct agents, memory, planning, human-in-the-loop control, and real-time voice interaction, developers can create powerful agents in minutes. AgentScope integrates seamlessly with tools, long-term memory systems, MCP, A2A (Agent-to-Agent) protocols, and observability frameworks. It also supports reinforcement learning workflows for tuning agents and improving performance across complex tasks. ... -
22
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. -
23
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. ... -
24
BuntDB
Database for Go with custom indexing and geospatial support
BuntDB is an embeddable, in-memory key/value database written in Go, with optional persistence to disk. It is built for scenarios where you want a lightweight, fast store (reads and writes in memory) but also durability (via append-only file format) and transactional semantics (ACID with single-writer, multiple-reader locking). Among its distinguishing features are support for custom indexing (even within JSON values), spatial (geospatial) indexes with support up to 20 dimensions, flexible iteration over keys (ascending, descending, ranges), TTL/expiry eviction, and embeddability. ... -
25
Jimfs
An in-memory file system for Java 8+
Jimfs is an in-memory file system for Java that fully implements the java.nio.file API introduced in Java 7 and enhanced in Java 8 and beyond. Developed by Google, it allows developers to create and manipulate file systems entirely in memory, making it ideal for testing, simulation, and temporary file operations without touching the actual disk. Jimfs supports most standard file operations, including file and directory creation, deletion, copying, symbolic and hard links, as well as stream-based file reading and writing. ...
