Search Results for "git:/git.code.sf.net/p/docfetcher/code" - Page 31
Sort By:
Showing 1782 open source projects for "git:/git.code.sf.net/p/docfetcher/code"
View related business solutions-
Eurekos LMS - Build a Smarter CustomerEurekos is a purpose-built LMS that engages customers throughout the entire learning journey from pre-sales, to onboarding, and everything after.
-
Composable, Open Source Payments PlatformJuspay's Payments Orchestration Platform offers a comprehensive product suite for businesses, including open-source payment orchestration, global payouts, seamless authentication, payment tokenization, fraud & risk management, end-to-end reconciliation, unified payment analytics & more. The company’s offerings also include end-to-end white label payment gateway solutions & real-time payments infrastructure for banks. These solutions help businesses achieve superior conversion rates, reduce fraud, optimize costs, and deliver seamless customer experiences at scale.
-
1
Grounded Docs
Open-Source Alternative to Context7, Nia, and Ref.Tools
...By acting as an intermediary layer between documentation sources and AI tools, the server enables models to access structured documentation in a consistent and machine-readable format. This makes it easier for AI systems to answer technical questions, generate code examples, or retrieve reference material without requiring developers to manually integrate documentation into prompts. The architecture follows the MCP specification, which allows AI assistants and agent frameworks to connect to external tools through standardized protocols. -
2
how-to-optim-algorithm-in-cuda
How to optimize some algorithm in cuda
how-to-optim-algorithm-in-cuda is an open educational repository focused on teaching developers how to optimize algorithms for high-performance execution on GPUs using 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. ... -
3
Hugging Face Skills
Definitions for AI/ML tasks like dataset creation
...Each skill is a self-contained folder with structured metadata and guidance that tells an agent how to execute tasks such as dataset creation, model training, evaluation, or Hub operations. The project is designed to be interoperable across major agent ecosystems, including Claude Code, OpenAI Codex, Gemini CLI, and Cursor, making it a cross-platform building block for agent automation. By formalizing best practices and workflows, Skills helps transform general-purpose coding agents into domain-aware assistants that can execute complex ML pipelines with less manual prompting. The repository also includes ready-to-use skills for common Hugging Face operations and encourages teams to extend them with custom domain logic. -
4
Playwriter
Chrome extension to let agents control your browser
Playwriter is an open-source project that combines a Chrome extension with a CLI to allow autonomous agents to control a web browser directly using Playwright code in a stateful sandbox environment. The system enables browser automation by running Playwright commands through a persistent session managed by a background extension, allowing agents or scripts to navigate, interact with, and query browser contexts without losing state between commands. This makes it valuable for scenarios where AI agents need to perform complex web automation tasks—like multi-step navigation, form interaction, or content extraction—without reinitializing context or state every time. ... -
Curtain LogTrace File Activity MonitoringCurtain LogTrace File Activity Monitoring is an enterprise file activity monitoring solution. It tracks user actions: create, copy, move, delete, rename, print, open, close, save. Includes source/destination paths and disk type. Perfect for monitoring user file activities.
-
5
Z80-μLM
Z80-μLM is a 2-bit quantized language model
...A key deliverable is producing CP/M-compatible .COM binaries, enabling a genuinely vintage “chat with your computer” experience on real hardware or accurate emulators. The project sits at the intersection of machine learning and systems constraints, showing how model architecture, quantization, and inference code generation can be adapted to extreme memory and compute limits. It also functions as an educational reference for how to reduce inference to operations that fit an old-school instruction set and runtime environment. -
6
GetProfile
User profile and long-term memory for your AI agent
...It then extracts structured traits and “memories” from those conversations, stores them, and injects the most relevant profile context back into future prompts so responses stay consistent and personalised over time. The goal is to make “memory” and user understanding an infrastructure concern rather than an app-by-app feature, so teams can add continuity with minimal code changes. Because it behaves like an OpenAI-compatible gateway, it can work with multiple providers and tools that already speak that API shape. -
7
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. ... -
8
MCPHub
A unified hub for centralized management and dynamic organization
MCPHub is a unified hub that organizes many MCP servers behind clean Streamable HTTP (SSE) endpoints so clients can connect to “all tools,” a specific server, or logical groups. It’s designed to simplify multi-server operations: one process can multiplex several named STDIO servers and re-expose them over HTTP for IDEs and services. The README ships in multiple languages and includes deployment and routing guidance, signaling an intention to reach a broad user base. The project publishes to... -
9
SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it
...We accomplish our results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, and view, edit, and execute code files. We call this an Agent-Computer Interface (ACI). -
Award-winning proxy networks, AI-powered web scrapers, and business-ready datasets for download.Bright Data is a leading data collection platform, enabling businesses to collect crucial structured and unstructured data from millions of websites through our proprietary technology. Our proxy networks give you access to sophisticated target sites using precise geo-targeting. You can also use our tools to unblock tough target sites, accomplish SERP-specific data collection tasks, manage and optimize your proxy performance as well as automating all of your data collection needs.
-
10
Spark NLP
State of the Art Natural Language Processing
Experience the power of large language models like never before, unleashing the full potential of Natural Language Processing (NLP) with Spark NLP, the open source library that delivers scalable LLMs. The full code base is open under the Apache 2.0 license, including pre-trained models and pipelines. The only NLP library built natively on Apache Spark. The most widely used NLP library in the enterprise. Spark ML provides a set of machine learning applications that can be built using two main components, estimators and transformers. The estimators have a method that secures and trains a piece of data to such an application. ... -
11
DataFrame
C++ DataFrame for statistical, Financial, and ML analysis
This is a C++ analytical library designed for data analysis similar to libraries in Python and R. For example, you would compare this to Pandas, R data.frame, or Polars. You can slice the data in many different ways. You can join, merge, and group-by the data. You can run various statistical, summarization, financial, and ML algorithms on the data. You can add your custom algorithms easily. You can multi-column sort, custom pick, and delete the data. DataFrame also includes a large... -
12
Mosec
A high-performance ML model serving framework, offers dynamic batching
Mosec is a high-performance and flexible model-serving framework for building ML model-enabled backend and microservices. It bridges the gap between any machine learning models you just trained and the efficient online service API. -
13
OxidizeBot
High performance Twitch bot in Rust
...From a song request system to groundbreaking game modes where your viewers can interact directly with you and your game. It's written in Rust, providing an unparalleled level of reliability and performance. OxidizeBot doesn't cost you anything, and its source code is available on GitHub for anyone to tinker with! Plays music moderates your chat, plays games, you name it! You own your data. It uses your internet for the best possible latency. It's light on system resources*. And running locally means it can perform rich interactions with your games like Chaos%. -
14
ArrayFire
ArrayFire, a general purpose GPU library
...The community of ArrayFire developers invites you to build with us if you're interested and able to write top performing tensor functions. Together we can fulfill The ArrayFire Mission under an excellent Code of Conduct that promotes a respectful and friendly building experience. Rigorous benchmarks and tests ensuring top performance and numerical accuracy. Cross-platform compatibility with support for CUDA, OpenCL, and native CPU on Windows, Mac, and Linux. Built-in visualization functions through Forge. -
15
scikit-image
Image processing in Python
scikit-image is a collection of algorithms for image processing. It is available free of charge and free of restriction. We pride ourselves on high-quality, peer-reviewed code, written by an active community of volunteers. scikit-image builds on scipy.ndimage to provide a versatile set of image processing routines in Python. This library is developed by its community, and contributions are most welcome! Read about our mission, vision, and values and how we govern the project. Major proposals to the project are documented in SKIPs. ... -
16
MLJAR Studio
Python package for AutoML on Tabular Data with Feature Engineering
We are working on new way for visual programming. We developed a desktop application called MLJAR Studio. It is a notebook-based development environment with interactive code recipes and a managed Python environment. All running locally on your machine. We are waiting for your feedback. The mljar-supervised is an Automated Machine Learning Python package that works with tabular data. It is designed to save time for a data scientist. It abstracts the common way to preprocess the data, construct the machine learning models, and perform hyper-parameter tuning to find the best model. ... -
17
DeepDetect
Deep Learning API and Server in C++14 support for Caffe, PyTorch
...While the Open Source Deep Learning Server is the core element, with REST API, and multi-platform support that allows training & inference everywhere, the Deep Learning Platform allows higher level management for training neural network models and using them as if they were simple code snippets. Ready for applications of image tagging, object detection, segmentation, OCR, Audio, Video, Text classification, CSV for tabular data and time series. Neural network templates for the most effective architectures for GPU, CPU, and Embedded devices. Training in a few hours and with small data thanks to 25+ pre-trained models. ... -
18
FlowGram
Extensible workflow development framework
...Instead of shipping as a ready-made product, it provides the building blocks — a canvas for wiring together nodes, a form engine for configuring node parameters, a variable-scope and type-inference engine, and a set of “materials” (pre-built node types such as code execution, conditional logic, LLM calls, etc.) that can be composed into larger workflows. This makes FlowGram highly flexible: you can prototype data-processing pipelines, AI-agent flows, automation scripts, or even business process automation without writing all the plumbing yourself. The framework supports both free-layout canvases (for free-form graphs) and fixed-layout canvases (for more structured flowcharts, including loops, branches, compound nodes), giving you visual freedom depending on your use-case. -
19
Llama Cookbook
Solve end to end problems using Llama model family
The Llama Cookbook is the official Meta LLaMA guide for inference, fine‑tuning, RAG, and multi-step use-cases. It offers recipes, code samples, and integration examples across provider platforms (WhatsApp, SQL, long context workflows), enabling developers to quickly harness LLaMA models -
20
Simple MCP
A simple TypeScript library for creating MCP servers
simple-mcp is a TypeScript library designed to facilitate the creation of Model Context Protocol (MCP) servers. It offers a straightforward API, enabling developers to set up MCP servers with minimal code. The library emphasizes type safety through full TypeScript integration and incorporates parameter validation using Zod. It fully implements the MCP, ensuring compatibility with MCP clients. -
21
Liger Kernel
Efficient Triton Kernels for LLM Training
Liger Kernel is a unified kernel developed by LinkedIn to streamline data science and machine learning workflows across different languages and tools. It provides a consistent interface for running code in various languages (such as Python, R, SQL) within a single Jupyter-like environment, enhancing productivity and collaboration for data scientists working in mixed-language projects. -
22
embedchain
Framework to easily create LLM powered bots over any dataset
Embedchain is a framework to easily create LLM-powered bots over any dataset. If you want a javascript version, check out embedchain-js. Embedchain empowers you to create chatbot models similar to ChatGPT, using your own evolving dataset. Start building LLM powered bots under 30 seconds. -
23
Monoio
Rust async runtime based on io-uring
...Its design philosophy centers on a “thread-per-core” model where each core runs its own event loop, minimizing cross-thread synchronization needs, avoiding the overhead and complexity of task scheduling, and letting developers write efficient, low-overhead asynchronous networking or I/O code. Because tasks do not need to be Send or Sync and can make use of thread-local data safely, Monoio simplifies certain concurrency paradigms while delivering performance benefits for workloads like high-throughput network servers, proxies, or real-time services. The runtime includes abstractions for async sockets, readers/writers, TCP/UDP networking, and compatibility layers (macros, crates) to ease adoption. -
24
mlforecast
Scalable machine learning for time series forecasting
...It lets you apply any regressor that follows the typical scikit-learn API, for example, gradient-boosted trees or linear models, to time-series data by automating much of the messy feature engineering and data preparation. Instead of writing custom code to build lagged features, rolling statistics, and date-based predictors, mlforecast generates those automatically based on a simple configuration. It supports multi-series forecasting, meaning you can train one model that forecasts many time series at once (common in retail, demand forecasting, etc.), rather than one model per series. ... -
25
Insanely Fast Whisper
An opinionated CLI to transcribe Audio files w/ Whisper on-device
...It is specifically engineered for environments with CUDA-enabled GPUs or Apple Silicon devices, allowing users to process hours of audio in minutes or even seconds depending on hardware capabilities. The tool provides a streamlined CLI interface, making it easy to run transcription tasks on local files or URLs without needing to write custom code. It supports multiple Whisper model variants, including distilled versions for faster inference with minimal accuracy loss.
