Search Results for "/storage/emulated/0/android/data/net.sourceforge.uiq3.fx603p/files" - Page 65
Sort By:
13336 projects for "/storage/emulated/0/android/data/net.sourceforge.uiq3.fx603p/files" with 1 filter applied:
-
SoftCo: Enterprise Invoice and P2P Automation SoftwareSoftCo Accounts Payable Automation processes all PO and non-PO supplier invoices electronically from capture and matching through to invoice approval and query management. SoftCoAP delivers unparalleled touchless automation by embedding AI across matching, coding, routing, and exception handling to minimize the number of supplier invoices requiring manual intervention. The result is 89% processing savings, supported by a context-aware AI Assistant that helps users understand exceptions, answer questions, and take the right action faster.
-
Data management solutions for confident marketingVerify, deduplicate, manipulate, and assign records automatically to keep your CRM data accurate, complete, and ready for business.
-
1
Lagent
A lightweight framework for building LLM-based agents
...The framework provides tools and abstractions that allow language models to interact with external tools, execute tasks, and perform multi-step reasoning processes. Instead of using LLMs only for text generation, Lagent enables developers to transform models into agents capable of performing actions such as retrieving data, executing code, or interacting with APIs. The system includes modular components that allow developers to connect different models and tools within the same agent architecture. Its design emphasizes simplicity and flexibility so that developers can experiment with different agent workflows without needing a complex infrastructure setup. ... -
2
OmAgent
Build multimodal language agents for fast prototype and production
OmAgent is an open-source Python framework designed to simplify the development of multimodal language agents that can reason, plan, and interact with different types of data sources. The framework provides abstractions and infrastructure for building AI agents that operate on text, images, video, and audio while maintaining a relatively simple interface for developers. Instead of forcing developers to implement complex orchestration logic manually, the system manages task scheduling, worker coordination, and node optimization behind the scenes. ... -
3
vLLM Semantic Router
System Level Intelligent Router for Mixture-of-Models at Cloud
...This approach allows developers to combine multiple models with different strengths, such as lightweight models for simple queries and more advanced reasoning models for complex tasks. The router operates as an intelligent layer between users and model infrastructure, capturing signals from prompts, responses, and contextual data to improve decision-making. It can also integrate safety and monitoring mechanisms that detect issues such as jailbreak attempts, hallucinations, or sensitive information exposure. -
4
ai-cookbook
Examples and tutorials to help developers build AI systems
...The repository contains examples that demonstrate how to build AI workflows using modern tools such as large language models, autonomous agents, and external APIs. Developers can learn how to construct applications like intelligent assistants, automation pipelines, and AI-powered data analysis tools through step-by-step tutorials and ready-to-run scripts. The code examples are designed to emphasize practical architecture patterns that are commonly used in production environments, helping developers understand how to integrate AI services into software products. -
The full-stack observability platform that protects your dataLayer, tags and conversion dataCode-Cube.io detects issues instantly, alerts you in real time and helps you resolve them fast. No manual QA. No unreliable data. Just data you can trust and act on.
-
5
RunAnywhere
Production ready toolkit to run AI locally
...The toolkit allows developers to integrate language models, speech recognition, and voice synthesis capabilities into mobile or desktop applications while keeping all computation local. By running models entirely on device, the platform eliminates network latency and protects user data because information does not leave the device. The SDK supports popular open-source models such as Llama, Mistral, and Qwen, enabling developers to build AI-powered features such as chat interfaces and voice assistants with minimal external dependencies. It also includes integrated pipelines that combine speech-to-text, large language models, and text-to-speech into a complete conversational system. -
6
Ling-V2
Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI
...It introduces highly sparse architectures where only a fraction of the model’s parameters are activated per input token, enabling models like Ling-mini-2.0 to achieve reasoning and instruction-following capabilities on par with much larger dense models while remaining significantly more computationally efficient. Trained on more than 20 trillion tokens of high-quality data and enhanced through multi-stage supervised fine-tuning and reinforcement learning, Ling-V2’s models demonstrate strong general reasoning, mathematical problem-solving, coding understanding, and knowledge-intensive task performance. -
7
Agent SOP
Natural language workflows for AI agents
...It defines reusable SOP templates that agents can instantiate with context-specific parameters, allowing organizations to codify best practices for customer support, data processing, document workflows, or incident response. The framework supports monitoring and state tracking, so external systems can observe progress, intervene if necessary, and log outcomes for compliance or auditing. Integrations with common messaging and task orchestration systems enable SOP agents to interact with email, ticket queues, and databases as part of their workflows. -
8
Gitlogue
A cinematic Git commit replay tool for the terminal
...When you run this tool in the terminal, it visually replays diffs line by line, highlights syntax, and shows changes evolving in a way that feels like watching a code story unfold, which can be entertaining and useful for reviewing history or showcasing progress. It builds on typical Git data but reshapes it into a compelling narrative with visual appeal, making it great for demos, teaching, or just savoring your development journey. The tool is standalone and designed to be easy to install and run, so users don’t need complex setups to enjoy animated commit histories. Gitlogue adds atmosphere and personality to otherwise dry version control logs, and it supports terminal-friendly output that respects your existing workflow. -
9
Jesse
An advanced crypto trading bot written in Python
...It acts as an agent manager where you can define tasks, contexts, and tool integrations so that AI reasoning is reliably connected to deterministic procedures like API calls, data retrieval, and task execution. Jesse emphasizes structured outputs, safety boundaries, and explainable reasoning, helping users design agents that don’t just hallucinate responses but can coordinate steps, validate conditions, and interact with systems predictably. It also includes built-in support for evaluation, logging, and orchestration so developers can monitor, test, and improve agent behavior over time. ... -
The AI-powered unified PSA-RMM platform for modern MSPs.SuperOps.ai is the only PSA-RMM platform powered by intelligent automation and thoughtfully crafted for the new-age MSP. The platform also helps MSPs manage their projects, clients, and IT documents from a single place.
-
10
VibeKit
Run Claude Code, Gemini, Codex in a clean, isolated sandbox
...It provides a set of abstractions and utilities that let developers connect generative models to UI frameworks, sensors, event streams, and external services without having to build plumbing from scratch. Instead of treating AI models as black boxes behind simple prompts, Vibekit encourages developers to define declarative behaviors, reactive rules, and data flows that make the outputs of models part of living application logic. This can include things like dynamic content generation, live adaptation based on user interaction, and connectors to external APIs for enriched grounding. The toolkit also supports testing and local iteration, with utilities that simulate event streams and mock model responses to make development predictable. -
11
Nano Events
Simple and tiny (107 bytes) event emitter library for JavaScript
...Rather than offering many complex features, nanoevents focuses on the core primitives: creating an emitter, subscribing to named events, emitting events with arbitrary data, and unsubscribing. Because of its minimal API surface and implementation, it’s very easy to integrate into frontend or backend JS/TypeScript projects without introducing significant dependencies or weight. The simplicity reduces cognitive load: developers don’t need to read long docs or worry about advanced event semantics. -
12
Underscore.js
JavaScript's utility belt
Underscore.js is a JavaScript utility-library created by Jeremy Ashkenas that provides a broad set of functions for working with arrays, objects, functions, and other data types — essentially a “utility belt” for functional programming in JS. Instead of extending built-in objects or modifying prototypes, Underscore provides its helpers in a single _ namespace, enabling cross-browser support and consistent behaviour across environments. It offers map/filter/reduce, deep-cloning, templating, object traversal, function binding, and more, which makes it easier to write concise, expressive code rather than verbose loops and conditional logic. ... -
13
Google API JavaScript Client
Google APIs Client Library for browser JavaScript, aka gapi
This library (often used via gapi) provides a browser-friendly way to call Google APIs using OAuth 2.0 and generated discovery documents. It abstracts discovery, auth, and HTTP details so developers can focus on domain calls like Drive file operations, Calendar events, or YouTube data. The client can load APIs dynamically at runtime, which keeps bundles small and allows late-binding to specific services and versions. It includes helpers for incremental auth, token refresh, and scopes so apps can request only what they need when they need it. Responses are returned as promise-based calls with typed parameters derived from service definitions, simplifying error handling and pagination. ... -
14
BTree implementation for Go
BTree provides a simple, ordered, in-memory data structure for Go
This package is a high-performance, in-memory B-tree for Go that implements an ordered set/map with efficient insert, delete, and range iteration. It’s parameterized by tree degree so callers can tune cache behavior and memory overhead for their workload. Instead of relying on Go’s built-in maps—which are hash-based and unordered—btree preserves sorted order and provides rich traversal APIs like ascending, descending, and range scans. The implementation favors minimal allocations and... -
15
LangExtract
A Python library for extracting structured information
LangExtract is a Python library developed by Google that leverages large language models (LLMs) to extract structured information from unstructured text—such as clinical notes, research papers, or literary works—based on user-defined instructions. It is designed to transform free-form text into reliable, schema-constrained data while maintaining traceability back to the source material. Each extracted entity is precisely grounded in its original context, allowing visual inspection and validation via automatically generated interactive HTML visualizations. LangExtract supports a wide range of models, including Google Gemini, OpenAI GPT, and local LLMs via Ollama, making it adaptable to different deployment environments and compliance needs. ... -
16
JEPA
PyTorch code and models for V-JEPA self-supervised learning from video
...This makes learning focus on semantics and structure, yielding features that transfer well with simple linear probes and minimal fine-tuning. The repository provides training recipes, data pipelines, and evaluation utilities for image JEPA variants and often includes ablations that illuminate which masking and architectural choices matter. Because the objective is non-autoregressive and operates in embedding space, JEPA tends to be compute-efficient and stable at scale. The approach has become a strong alternative to contrastive or pixel-reconstruction methods for representation learning. -
17
DLRM
An implementation of a deep learning recommendation model (DLRM)
...The implementation is optimized for performance at scale, supporting multi-GPU and multi-node execution, quantization, embedding partitioning, and pipelined I/O to feed huge embeddings efficiently. 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. -
18
Seamless Communication
Foundational Models for State-of-the-Art Speech and Text Translation
...The motivation is to move beyond “text in, text out” and enable direct, live, multi-turn exchange involving language, gesture, gaze, vision, and modality switching without user friction. The system architecture includes a real-time multimodal signal pipeline for audio, video, and sensor data, a dialog manager that can decide when to act (speak, gesture, point) or query, and a cross-modal reasoning layer that fuses perception with semantic context. The research prototype includes components for visual grounding (understanding when a user references something in view), gesture recognition and synthesis, and turn-taking mechanisms that mirror human conversational timing. ... -
19
Animated Drawings
Code to accompany "A Method for Animating Children's Drawings"
...Users can provide rough keyframes or control constraints (pose anchors), and the system fills intermediate frames with fluid animation. The repository includes demonstration apps and notebooks where you can upload or draw shapes and watch animations play. Because the approach is data-driven, it generalizes to new drawings even with varying proportions or stylizations. -
20
DeepEP
DeepEP: an efficient expert-parallel communication library
...Its core role is to implement high-throughput, low-latency all-to-all GPU communication kernels, which handle the dispatching of tokens to different experts (or shards) and then combining expert outputs back into the main data flow. 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. ... -
21
Hanami
A flexible framework for maintainable Ruby apps
Hanami is a modern Ruby web framework that aims to be lightweight, fast, and modular, in contrast to the monolithic design of Rails. It emphasizes separation of concerns, encouraging developers to structure applications into clear layers of controllers, views, entities, and repositories. Each component—like the router, model layer, or view rendering engine—can be used independently, which gives developers flexibility to build lean applications. Hanami promotes immutability, plain old Ruby... -
22
Phoenix LiveView
Rich, real-time user experiences with server-rendered HTML
...You no longer have to split work between client and server, across different toolings, layers, and abstractions. Instead, LiveView enriches the server with a declarative and powerful model while keeping your code closer to your data (and ultimately your source of truth). -
23
Cheshire
Clojure JSON and JSON SMILE (binary json format) encoding/decoding
Cheshire is a high-performance JSON encoding and decoding library for Clojure, built atop Jackson to combine fast parsing/generation with advanced support for types like Dates, UUIDs, Sets, Symbols, and the binary JSON SMILE format. Custom encoding is supported from 2.0.0 and up if you encounter a bug, please open a GitHub issue. From 5.0.0 onwards, custom encoding has been moved to be part of the core namespace (not requiring a namespace change). Custom and Core encoding have been combined... -
24
Ruma
A set of Rust crates for interacting with the Matrix chat network
...It includes all the features you'd expect from a modern chat platform including instant messaging, group chats, audio and video calls, searchable message history, synchronization across all your devices, and end-to-end encryption. Matrix is federated, so no single company controls the system or your data. You can use an existing server you trust or run your own, and the servers synchronize messages seamlessly. Learn more in the Introduction to Matrix. Rust is a systems programming language from Mozilla built with safety, concurrency, and performance in mind. Its novel approach to memory safety and its rich type system make it an excellent choice for writing fast, secure, and reliable programs. -
25
Laravel Echo
Laravel Echo library for beautiful Pusher and Ably integration
In many modern web applications, WebSockets are used to implement realtime, live-updating user interfaces. When some data is updated on the server, a message is typically sent over a WebSocket connection to be handled by the client. This provides a more robust, efficient alternative to continually polling your application for changes. To assist you in building these types of applications, Laravel makes it easy to "broadcast" your events over a WebSocket connection.
