Search Results for "active"
Sort By:
Showing 211 open source projects for "active"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Endpoint Management with Remote Control Built InSave 50% on your first year when you switch from your existing RMM to Splashtop AEM. Automate patching, track inventory, and jump directly into 1-click unattended remote sessions without switching tools.
-
1
n8n
Free and source-available fair-code licensed workflow automation tool
n8n is an extendable workflow automation tool. With a fair-code distribution model, n8n will always have visible source code, be available to self-host, and allow you to add your own custom functions, logic and apps. n8n's node-based approach makes it highly versatile, enabling you to connect anything to everything. n8n has 200+ different nodes to automate workflows. -
2
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
GLM-4.5 is a cutting-edge open-source large language model designed by Z.ai for intelligent agent applications. The flagship GLM-4.5 model has 355 billion total parameters with 32 billion active parameters, while the compact GLM-4.5-Air version offers 106 billion total parameters and 12 billion active parameters. Both models unify reasoning, coding, and intelligent agent capabilities, providing two modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for immediate responses. They are released under the MIT license, allowing commercial use and secondary development. ... -
3
Kimi K2
Kimi K2 is the large language model series developed by Moonshot AI
Kimi K2 is Moonshot AI’s advanced open-source large language model built on a scalable Mixture-of-Experts (MoE) architecture that combines a trillion total parameters with a subset of ~32 billion active parameters to deliver powerful and efficient performance on diverse tasks. It was trained on an enormous corpus of over 15.5 trillion tokens to push frontier capabilities in coding, reasoning, and general agentic tasks while addressing training stability through novel optimizer and architecture design strategies. The model family includes variants like a foundational base model that researchers can fine-tune for specific use cases and an instruct-optimized variant primed for general-purpose chat and agent-style interactions, offering flexibility for both experimentation and deployment. ... -
4
FlashInfer
FlashInfer: Kernel Library for LLM Serving
FlashInfer is a kernel library designed to enhance the serving of Large Language Models (LLMs) by optimizing inference performance. It provides a high-performance framework that integrates seamlessly with existing systems, aiming to reduce latency and improve efficiency in LLM deployments. FlashInfer supports various hardware architectures and is built to scale with the demands of production environments. -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
5
Lemonade
Lemonade helps users run local LLMs with the highest performance
...Its README emphasizes real-world adoption across startups, research groups, and large companies, signaling a focus on practical deployments rather than toy demos. The repository highlights easy onboarding with downloads, docs, and a Discord for support, suggesting an active user community. Messaging centers on squeezing maximum throughput/latency from modern accelerators without users having to hand-tune kernels or flags. Releases further reinforce the “server” framing, pointing developers toward a service that can be integrated into apps and tools. -
6
TurboFieldfare
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
...Instead of loading the entire model, it keeps the shared core and KV cache in RAM while streaming only the routed experts required for each token from SSD. This approach reduces active memory use to roughly 2 GB while the installed model occupies about 14.3 GB of storage. The project includes a native Mac application, command-line tools, a streaming installer, a Swift library, and an experimental OpenAI-compatible local server. Quantized weights, custom Metal kernels, chunked prefill, and a bounded expert cache improve efficiency. ... -
7
DeepSeek R1
Open-source, high-performance AI model with advanced reasoning
...DeepSeek R1 offers unrestricted access for both commercial and academic use. The model employs a Mixture of Experts (MoE) architecture, comprising 671 billion total parameters with 37 billion active parameters per token, and supports a context length of up to 128,000 tokens. DeepSeek-R1's training regimen uniquely integrates large-scale reinforcement learning (RL) without relying on supervised fine-tuning, enabling the model to develop advanced reasoning capabilities. This approach has resulted in performance comparable to leading models like OpenAI's o1, while maintaining cost-efficiency. ... -
8
Gemini-API
Reverse-engineered Python API for Google Gemini web app
...While the project offers a powerful integration, users should note that the API is reverse-engineered (not officially supported by Google) and may face changes or rate-limits. The project is licensed under AGPL-3.0, emphasizing the “open” nature but also requiring derivative works to remain open. It has a strong community following and active discussions/issue tracking around model support, error handling, and new features. -
9
SillyTavern
LLM Frontend for Power Users
...SillyTavern is a user interface you can install on your computer (and Android phones) that allows you to interact with text generation AIs and chat/roleplay with characters you or the community create. SillyTavern is a fork of TavernAI 1.2.8 which is under more active development and has added many major features. At this point, they can be thought of as completely independent programs. -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
10
Cybergod
A program that can do anything to earn money without human operators
AGI Computer Control is an experimental autonomous software system designed to operate independently and generate income without human intervention. It aims to simulate artificial general intelligence (AGI) by leveraging evolutionary algorithms, deep active inference, and other advanced AI techniques. The project explores the boundaries of machine autonomy and self-directed behavior in computational environments. -
11
agentsview
Local-first session intelligence and analytics for coding agents
...It tracks token usage, cost, models, projects, tools, and session behavior across different agents. Its web interface adds dashboards, heatmaps, full-text search, and live updates while sessions are active. It can also support team-oriented workflows through optional PostgreSQL sync and DuckDB mirroring. -
12
llama.cpp
Port of Facebook's LLaMA model in C/C++
The llama.cpp project enables the inference of Meta's LLaMA model (and other models) in pure C/C++ without requiring a Python runtime. It is designed for efficient and fast model execution, offering easy integration for applications needing LLM-based capabilities. The repository focuses on providing a highly optimized and portable implementation for running large language models directly within C/C++ environments. -
13
Qwen3-Coder
Qwen3-Coder is the code version of Qwen3
Qwen3-Coder is the latest and most powerful agentic code model developed by the Qwen team at Alibaba Cloud. Its flagship version, Qwen3-Coder-480B-A35B-Instruct, features a massive 480 billion-parameter Mixture-of-Experts architecture with 35 billion active parameters, delivering top-tier performance on coding and agentic tasks. This model sets new state-of-the-art benchmarks among open models for agentic coding, browser-use, and tool-use, matching performance comparable to leading models like Claude Sonnet. Qwen3-Coder supports an exceptionally long context window of 256,000 tokens, extendable to 1 million tokens using Yarn, enabling repository-scale code understanding and generation. ... -
14
Surya
Implementation of the Surya Foundation Model for Heliophysics
...Named after the Sanskrit word for “sun,” Surya is trained on nine years of high‑resolution solar imagery from NASA’s Solar Dynamics Observatory (SDO). It is designed to forecast solar phenomena—such as flares, solar wind, irradiance, and active region behavior—by predicting future solar images with a sophisticated long–short vision transformer architecture, thereby enabling improved space weather forecasting. Foresees solar flares, wind, EUV spectra, and active region formation in advance. Achieves approximately 16% improvement in forecasting accuracy over traditional methods. 366-million‑parameter foundation model capturing general-purpose solar representations. -
15
abtop
Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI
abtop is a terminal monitoring tool for AI coding agents, inspired by system monitors like htop and btop. It gives users a real-time view of active Claude Code, Codex CLI, and OpenCode sessions from local process and file state. The dashboard helps developers track token usage, context window percentage, rate limits, child processes, open ports, and multiple active profiles. It is read-only, so it does not require API keys or authentication and does not control the agents it observes. abtop is especially useful for developers running several agents across projects who need quick visibility into cost, quota pressure, context growth, and orphaned processes. ... -
16
ego (lite)
The fastest browser for AI agents to run web automation
Ego Lite is a macOS browser designed for people and external AI agents to work in parallel. Each agent receives an isolated Space, allowing several browser tasks to run simultaneously without taking over the user's active tabs. Optional Chrome data migration carries over logins, cookies, extensions, and bookmarks so agents can use authenticated sessions with less setup. The ego-browser skill connects tools such as Codex, Claude Code, Cursor, and custom agent CLIs to the browser. Agents interact through JavaScript tools for navigation, snapshots, form entry, clicks, waiting, and captures. ... -
17
PyGAD
Source code of PyGAD, Python 3 library for building genetic algorithms
PyGAD is an open-source easy-to-use Python 3 library for building the genetic algorithm and optimizing machine learning algorithms. It supports Keras and PyTorch. PyGAD supports optimizing both single-objective and multi-objective problems. PyGAD supports different types of crossover, mutation, and parent selection. PyGAD allows different types of problems to be optimized using the genetic algorithm by customizing the fitness function. -
18
SGLang
SGLang is a fast serving framework for large language models
SGLang is a fast serving framework for large language models and vision language models. It makes your interaction with models faster and more controllable by co-designing the backend runtime and frontend language. -
19
Claude Overlay
A floating, screen-aware Claude Code chat for Windows
Claude Overlay is a Windows utility that places a screen-aware Claude Code assistant in a frameless, always-on-top chat window. It captures the active window or every monitor when a message is sent, letting Claude answer questions about visible documents, errors, dashboards, and applications. Because it runs the installed Claude Code CLI through the Agent SDK, it can also read files, execute commands, and edit open work when permissions allow. The interface streams responses, shows tool activity and context use, accepts pasted images, and provides an in-place model switcher. ... -
20
oMLX
LLM inference server with continuous batching & SSD caching
...It serves text models, vision-language models, OCR models, embeddings, and rerankers through OpenAI- and Anthropic-compatible APIs. Continuous batching allows concurrent requests, while a tiered KV cache keeps active data in RAM and moves colder blocks to SSD for reuse. Models can be pinned, unloaded manually, or evicted automatically when memory runs low. A web dashboard provides monitoring, chat, downloads, benchmarks, integrations, and per-model settings. It also supports tool calling, structured output, MCP integration, and experimental multi-Mac inference. -
21
GPT-SoVITS
1 min voice data can also be used to train a good TTS model
GPT‑SoVITS is a state-of-the-art voice conversion and TTS system that enables zero‑shot and few‑shot synthesis based on a short vocal sample (e.g., 5 seconds). It supports cross‑lingual speech synthesis across English, Chinese, Japanese, Korean, Cantonese, and more. It's powered by VITS architecture enhanced for few‑sample adaptation and real‑time usability. -
22
Qwen Code
Qwen Code is a coding agent that lives in the digital world
Qwen Code is a command-line AI workflow tool designed to enhance developer productivity by leveraging the power of Qwen3-Coder models. Adapted from the Google Gemini CLI, it features an enhanced parser optimized specifically for Qwen-Coder models, enabling deep code understanding and manipulation. The tool supports querying and editing large codebases beyond traditional context limits, making it ideal for modern, complex projects. Qwen Code automates various development workflows, including... -
23
LitterBox
A secure sandbox environment for malware developers and red teamers
...The README frames typical use cases: testing evasion, validating detections, analyzing behavior, and keeping sensitive tooling in-house. Repo metadata and author pages highlight an active security-tools ecosystem around the maintainer, with CI and pull-request activity suggesting ongoing development. The project positions itself as a safe proving ground to reduce surprises in the field while minimizing operational risk. For teams exploring MCP integrations, notes mention pairing with LLM agents for assisted analysis. -
24
Handy STT
A free, open source, and extensible speech-to-text application
...Handy allows users to start transcription instantly using a configurable keyboard shortcut—press to record, release to transcribe—and automatically pastes the resulting text into any active text field. Its backend leverages OpenAI’s Whisper models for GPU-accelerated speech recognition and Parakeet V3 for efficient CPU-only transcription with automatic language detection. To further refine accuracy and responsiveness, Handy integrates Silero’s Voice Activity Detection (VAD) for silence filtering, ensuring only speech segments are processed. -
25
GitHub Copilot CLI
GitHub Copilot CLI brings the power of Copilot coding agent
...It brings AI-powered coding assistance directly into your terminal. GitHub Copilot CLI allows you to build, debug, refactor, and understand code via natural language conversations. You can have these conversations within the Active Directory. It integrates tightly with your GitHub context—repositories, issues, pull requests. The Copilot can leverage repository context when making suggestions. The tool is currently in public preview and is evolving. Preview proposed changes before committing or applying them. Extensibility via MCP (Modular Copilot Platform) servers or custom servers.
