Search Results for "python language" - Page 34
Sort By:
Showing 1946 open source projects for "python language"
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.
-
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
1
Playwright for .NET
.NET version of the Playwright testing and automation library
...Cross-language. Use the Playwright API in TypeScript, JavaScript, Python, .NET, Java. Test Mobile Web. Native mobile emulation of Google Chrome for Android and Mobile Safari. The same rendering engine works on your Desktop and in the Cloud. Auto-wait. Playwright waits for elements to be actionable prior to performing actions. It also has a rich set of introspection events. -
2
UniMate
UniMate: One Unified Model to Animate Diverse Skeletons
UniMate is a generative motion model that animates rigged 3D assets with different skeletal structures from natural-language prompts. It is designed to handle bipeds, quadrupeds, birds, marine creatures, insects, serpentine rigs, and articulated rigid objects with one unified model. Its topology-aware diffusion transformer conditions generation on skeleton structure rather than requiring a fixed character template. The accompanying UniML3D dataset contains 13,006 text-paired motion sequences... -
3
AI Infra
Understanding of AI Infra: Quantitative Analysis and System Design
AI Infra Book is an open-source technical book and companion repository focused on the infrastructure behind modern large language models. It approaches inference and training through quantitative analysis of hardware limits, data movement, model architecture, and distributed systems. The book contains twelve chapters supported by formulas, diagrams, experiments, and case studies. Companion tools help readers reproduce resource calculations and inspect the assumptions behind system-design... -
4
MSA: Memory Sparse Attention
Trainable latent-memory framework for 100M-token contexts
MSA, or Memory Sparse Attention, is a research framework for scaling language-model memory to extremely long contexts. It replaces full attention over all tokens with sparse selection of compressed latent memory states. Document-wise rotary position encoding and top-k routing keep training and inference close to linear complexity. A tiered KV-cache design stores routing keys on GPU while larger content states can remain on CPU. Its Memory Parallel engine distributes scoring and transfers... -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
5
US Job Market Visualizer
A research tool for visually exploring Bureau of Labor Statistics
US Job Market Visualizer is a research tool for interactively exploring Occupational Outlook Handbook data from the U.S. Bureau of Labor Statistics. It organizes information for 342 occupations into a treemap where area represents employment and color can represent different metrics. Users can compare projected growth, median pay, education requirements, and estimated digital AI exposure. The repository includes tools for scraping BLS pages, converting them to structured data, and building... -
6
jlens
Companion code for the global workspace interpretability paper
Jacobian Lens is Anthropic’s reference implementation for examining what a language model’s internal activations are inclined to produce as text. It transports residual-stream vectors from selected layers and positions into the final-layer basis using an averaged input-output Jacobian. The transformed vectors are decoded through the model’s own unembedding into ranked vocabulary predictions. The package can fit new lenses, load saved ones, apply them to prompts, and merge results from... -
7
DeepSpec
A full-stack codebase for training and evaluating speculative decoding
DeepSpec is a full-stack codebase for training and evaluating draft models used in speculative decoding. It provides the components needed to prepare data, train draft models, and measure acceptance behavior against target models. The workflow starts with data preparation, including prompt download, target answer regeneration, and target cache construction. It then trains a draft model using configuration files for different algorithms and target model setups. The evaluation pipeline... -
8
HRM-Text
1B text generation model based on the HRM architecture
HRM-Text is a one-billion-parameter text generation model and pretraining framework based on the Hierarchical Reasoning Model architecture. It is designed to make foundation model pretraining more accessible by reducing compute and data requirements compared with traditional scaling-heavy approaches. The system combines hierarchical recurrent design, task-completion strengthening, and latent-space reasoning. Its training stack includes PrefixLM sequence packing, FlashAttention 3 kernels,... -
9
GEO Content Writer
Backlog-row-first content production system for teams
GEO Content Writer is an AI-based content generation tool designed to create optimized content tailored for geographic and semantic search contexts. It focuses on producing articles, pages, and structured content that align with both traditional SEO requirements and emerging AI search patterns. The system leverages language models to generate content that is context-aware, location-specific, and optimized for discoverability. It supports automated workflows for generating large volumes of... -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
10
Machine Learning Engineering Open Book
Machine Learning Engineering Open Book
Machine Learning Engineering Open Book is an open “living book” that captures practical methodologies, tooling advice, and operational knowledge for successfully training and deploying large language models and multimodal systems. The repository functions as a field guide compiled from real-world experience, particularly from work on large-scale models such as BLOOM-176B and IDEFICS-80B. It is heavily oriented toward practitioners who need hands-on solutions, including copy-paste commands,... -
11
List of independent blogs in Chinese
List of independent blogs in Chinese
List of independent blogs in Chinese is a curated open repository that aggregates and maintains a large list of independent Chinese-language blogs across technology, design, and personal knowledge domains. The project aims to promote the independent blogging ecosystem by making it easier for readers to discover high-quality personal sites outside major content platforms. It is community-driven, allowing contributors to submit and update blog entries so the directory remains current and... -
12
Claude Code Hooks Mastery
Master Claude Code Hooks
Claude Code Hooks Mastery is a trending community-centric GitHub repository aimed at helping developers master Claude Code hooks — customizable integration points that let users extend, automate, and augment workflows when using Claude Code, an agentic terminal coding assistant. Although the project itself doesn’t include a single coherent application, it functions as a curated collection of advanced hook examples, best practices, and coding patterns that show how to tailor Claude Code to... -
13
Auto-Deep-Research
Your Fully-Automated Personal AI Assistant
Auto-Deep-Research is a system designed to fully automate deep research workflows using language models, retrieval, planning, and multi-stage reasoning to produce structured research artifacts such as surveys, benchmarks, reports, and even prototypes without heavy human intervention. Users provide a research topic or multifaceted goal, and the system autonomously breaks the objective down into subtasks like literature collection, critical summarization, cross-comparison, citation extraction,... -
14
Moondream
Tiny vision language model
Moondream is a creative code project and visual experimentation repository that explores generative graphics, aesthetic patterns, and interactive art through code. The project typically showcases procedural visualizations, algorithmic designs, and artistic experiments that push the boundaries of what can be expressed with programming languages and rendering frameworks. While the exact nature can vary by commit or branch, Moondream’s work often blends geometry, color theory, and motion to... -
15
ValueCell
Community-driven, multi-agent platform for financial applications
ValueCell is a community-driven multi-agent AI platform focused on financial research, analysis, and decision-making that lets users leverage multiple specialized AI agents for tasks like data retrieval, investment research, strategy execution, and market tracking. The system brings together a suite of collaborative agents—such as research agents that gather and interpret fundamentals, strategy agents that implement trading logic, and news agents that deliver personalized updates—to help... -
16
GLM-4.5V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.5V is the preceding iteration in the GLM-V series that laid much of the groundwork for general multimodal reasoning and vision-language understanding. It embodies the design philosophy of mixing visual and textual modalities into a unified model capable of general-purpose reasoning, content understanding, and generation, while already supporting a wide variety of tasks: from image captioning and visual question answering to content recognition, GUI-based agents, video understanding,... -
17
Trae Agent
LLM-based agent for general purpose software engineering tasks
Trae Agent is an open-source, LLM-based agent system also developed by ByteDance, focused primarily on automating software engineering workflows. It provides a command-line interface (CLI) that accepts natural-language instructions (e.g. “refactor this module,” “write a unit test,” “generate a REST API skeleton”), and then orchestrates tool-based workflows — such as file editing, shell/batch commands, code generation, code formatting or refactoring — to carry out complex engineering tasks.... -
18
Linkedin Scraper
A library that scrapes Linkedin for user data
Linkedin Scraper is a library that scrapes Linkedin for user data. Version 2.0.0 and before is called linkedin_user_scraper and can be installed via pip3 install --user linkedin_user_scraper. The reason is that LinkedIn has recently blocked people from viewing certain profiles without having previously signed in. So by setting scrape=False, it doesn't automatically scrape the profile, but Chrome will open the linkedin page anyways. You can login and logout, and the cookie will stay in the... -
19
RAPTOR
The official implementation of RAPTOR
RAPTOR is a retrieval architecture designed to improve retrieval-augmented generation systems by organizing documents into hierarchical structures that enable more effective context retrieval. Traditional RAG systems typically retrieve small text chunks independently, which can limit a model’s ability to understand broader document context. RAPTOR addresses this limitation by recursively embedding, clustering, and summarizing documents to create a tree-structured hierarchy of information.... -
20
LeetCode Book
Comprehensive study guide for coding interviews
LeetCode-Book is a comprehensive study guide for coding interviews that consolidates algorithm patterns, data-structure templates, and worked LeetCode solutions. It organizes problems by topic—arrays, linked lists, stacks/queues, trees/graphs, dynamic programming, greedy, backtracking, and math—so you can study systematically. Explanations are concise but intentional, highlighting why a pattern fits, how to reason about boundary cases, and the time/space trade-offs. Many entries include... -
21
Gemma Translator
Code to run an on-device, fully offline voice translator
...The entire inference workflow can operate offline after the required models are installed. Its React interface is optimized for compact handheld and Raspberry Pi displays, including two-person conversational layouts. A Python backend coordinates speech recognition, text-to-speech, and communication with the local language model. Scripts automate setup, model downloading, development startup, and production deployment as a Raspberry Pi kiosk. The repository also includes systemd configuration and printable enclosure files for building a dedicated translation appliance. -
22
Theia
Cloud & Desktop IDE Platform
Eclipse Theia is an open source extensible platform for developing multi-language Cloud and Desktop IDEs with state-of-the-art web technologies. If you’re not sure if you need a web version or a desktop version or both, Theia is the best solution. It can develop one IDE for both browsers and native desktop applications from a single source. Theia has a highly flexible architecture, allowing extenders and adopters to customize and extend every aspect of it. It supports VS code extensions,... -
23
Browser Agent
AI Browser Agent is an advanced Browser AI tool
Browser Agent Python is an AI-powered browser automation tool developed by Oxylabs that enables users to control web interactions through natural language instead of traditional scripting. The tool allows developers to describe tasks in plain English, such as navigating pages, clicking elements, filling forms, and extracting data, and the system executes those actions as if a human were interacting with the browser. -
24
MLX Engine
LM Studio Apple MLX engine
MLX Engine is the Apple MLX-based inference backend used by LM Studio to run large language models efficiently on Apple Silicon hardware. Built on top of the mlx-lm and mlx-vlm ecosystems, the engine provides a unified architecture capable of supporting both text-only and multimodal models. Its design focuses on high-performance on-device inference, leveraging Apple’s MLX stack to accelerate computation on M-series chips. The project introduces modular VisionAddOn components that allow image... -
25
rust-by-practice
Challenging examples, exercises and projects
rust-by-practice is a hands-on, exercise-oriented learning resource for the Rust programming language that takes users beyond theory into real code challenges and practical patterns. Rather than simply listing Rust syntax or language features, it structures its content around progressively complex problems, each designed to illustrate a core Rust concept such as ownership, borrowing, lifetimes, traits, concurrency, zero-cost abstractions, and safe systems programming idioms. The repository...
