Search Results for "active"
Sort By:
98 projects for "active" with 2 filters applied:
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
1
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. ... -
2
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. ... -
3
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. ... -
4
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. ... -
$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.
-
5
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. -
6
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. -
7
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. -
8
SimpleEnglish
Agent skill: make LLMs write docs in ASD-STE100
SimpleEnglish is a portable agent skill that makes language models write technical documentation in ASD-STE100 Simplified Technical English. It replaces vague, promotional, and overly complex AI prose with short, direct, testable statements. The instructions enforce controlled practices such as active voice, simple tenses, consistent terminology, limited sentence length, and one instruction per sentence. It is designed for documentation, error messages, runbooks, incident reports, release notes, prompts, and translation preparation rather than marketing copy. The repository includes a complete skill, reusable system prompts, examples, evaluations, and a compact version for limited context budgets. ... -
9
KeepChatGPT
Browser userscript that enhances ChatGPT reliability and usability
...It focuses on solving common problems experienced during AI conversations, such as session timeouts, network errors, message failures, and interruptions during long chats. By automating session refresh and maintaining active connections, KeepChatGPT reduces the need for repeated manual steps when recovering from errors or expired sessions. KeepChatGPT also introduces a variety of enhancements that improve the overall interface and user experience, including page cleanup, expanded display layouts, conversation cloning, and detailed chat information. -
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
GPU Hot
Real-time NVIDIA GPU dashboard
...The project offers a self-hosted web interface that streams hardware metrics directly from GPU servers, enabling developers, ML engineers, and system administrators to observe GPU utilization and system behavior in real time through a browser. The dashboard collects and displays a wide range of performance metrics including temperature, memory usage, power consumption, clock speeds, fan speed, and active processes. It can scale from monitoring a single GPU workstation to large distributed environments with dozens or even hundreds of GPUs by running lightweight containers on each node and aggregating the data centrally. -
11
TencentDB Agent Memory
TencentDB Agent Memory delivers fully local long-term memory for AI
TencentDB Agent Memory is a local long-term memory system for AI agents. It uses symbolic short-term memory and layered long-term memory instead of storing everything as flat vector fragments. For active tasks, it offloads heavy logs into external files and keeps a compact Mermaid canvas in the agent context. For personalization, it organizes memory from raw conversations into atoms, scenarios, and persona-level knowledge. The design keeps high-level memory inspectable while preserving a drill-down path back to raw evidence. It is built for OpenClaw and Hermes-style agent workflows that need lower token usage, better continuity, and no external API dependency. -
12
Stop Slop
A skill file for removing AI tells from prose
Stop Slop is a writing skill file designed to remove the obvious tells of AI-generated prose. It gives an assistant concrete editing rules for making text sound more direct, human, specific, and trustworthy. The project targets common AI habits such as filler openings, overused contrasts, unnecessary adverbs, vague language, passive phrasing, and metronomic sentence rhythm. It also includes a scoring rubric that rates drafts across dimensions such as directness, rhythm, trust, authenticity,... -
13
No AI slop
Removes 20+ patterns of AI slop from any piece of writing
...It targets formulaic contrasts, throat-clearing openings, false insight setups, dramatic fragments, vague attribution, inflated importance, and other recognizable habits. The skill improves clarity, grammar, sentence structure, active voice, and the use of concrete details without flattening the writer’s personal voice. It can also analyze a passage for these patterns without claiming to determine whether AI created it. When editing, it makes the minimum effective changes and returns the revised draft with a brief explanation. A built-in evaluation file provides pass-or-fail checks that the skill applies to its own work. ... -
14
claude-obsidian
Claude + Obsidian knowledge companion
...A persistent memory layer ensures continuity across sessions, eliminating the need for repeated context. It also performs autonomous research to fill knowledge gaps and expand the knowledge base. Overall, it turns note-taking into an active, compounding intelligence system. -
15
AgentHub
GitHub is for humans. AgentHub is for agents
...Rather than focusing solely on human collaboration, the system is designed around an “agent-first” paradigm where AI agents can contribute code, discuss changes, and coordinate problem solving. The platform treats code repositories not just as storage for files but as active environments where agents can propose modifications, review changes, and exchange structured messages. This approach reflects emerging research in multi-agent software development where groups of AI systems collaborate on complex engineering problems. -
16
Minigrid
Simple and easily configurable grid world environments
Minigrid is a lightweight, minimalistic grid-world environment library for reinforcement learning (RL) research. It provides a suite of simple 2D grid-based tasks (e.g., navigating mazes, unlocking doors, carrying keys) where an agent moves in discrete steps and interacts with objects. The design emphasizes speed (agents can run thousands of steps per second), low dependency overhead, and high customizability — making it easy to define new maps, new tasks, or wrappers. It supports the... -
17
Qwen3.6
Qwen3.6 is the large language model series developed by Qwen team
The Qwen3.6 project is an open-source large language model series developed by Alibaba’s Qwen team, designed to deliver high-performance AI capabilities with a strong emphasis on real-world usability and developer productivity. It builds upon the advancements introduced in Qwen3.5, focusing on improving stability, responsiveness, and practical application in coding and agent-based workflows. The repository serves as a central hub for documentation, community discussion, and access to the... -
18
esp32-ai
Running a 28.9M parameter LLM on an $8 microcontroller
...The quantized model occupies about 14.9 MB and generates text without sending data to a server. Most parameters remain in flash through a Per-Layer Embeddings design, while active computation uses SRAM and PSRAM. This memory layout allows the device to retrieve only the embedding rows required for each token. The implementation reaches roughly 9.5 tokens per second and can display generated words on a connected screen. Trained on TinyStories, the model produces short, simple stories rather than answering questions, following instructions, or providing factual knowledge. ... -
19
firerpa LAMDA
The most powerful Android RPA agent framework
...The project emphasizes low-friction setup and powerful control primitives so teams can move from interactive validation to repeatable automation. A public wiki, releases, and issue tracker show active development across areas like connectivity, instrumentation compatibility, and robustness under detection. Together with companion projects (e.g., a device hub), lamda is positioned as a next-generation mobile automation stack rather than a single tool. Its focus on remote control plus RPA primitives makes it useful for QA, operations, and large-scale device orchestration. -
20
MaxKB
Open-source platform for building enterprise-grade agents
...The system exposes flexible tool-use (including MCP), supports multi-model backends, and provides dashboards for dataset management and evaluation. It’s backed by an active org that also builds adjacent ops tooling, and there’s a dedicated documentation repo for configuration and contribution. Community posts describe “self-host your ChatGPT-style assistant” positioning, with integrations and workflows to move from demo to production. Security advisories are tracked publicly, with upgrade guidance when issues arise. -
21
XHS-Downloader
GUI/CLI tool for downloading Xiaohongshu
...Recent releases add format support like JPEG and HEIC, clipboard-listening mode improvements, author-based archiving, SOCKS/HTTP proxy options, and the ability to set the file’s modification time to the post’s publish time for cleaner library organization. There is an active issues/discussions area with community tips, including approaches that use Selenium to acquire cookies and user agents for more reliable downloads. -
22
Browser MCP
Browser MCP is a Model Context Provider (MCP) server
...Because it runs against the user’s primary browser, it’s well-suited to repetitive web tasks, authenticated dashboards, and debugging workflows inside MCP-capable IDEs. A public website and extension streamline installation and connect the local server to clients like Claude, Cursor, VS Code, and Windsurf. The repository shows active development and a growing star count, reflecting rapid adoption across agent tooling. -
23
ReMe
Memory Management Kit for Agents
...It is designed to support long-running agent workflows where context matters and working memory alone isn’t enough, helping agents remember user preferences, task histories, and relevant past observations. The toolkit provides APIs to offload large, ephemeral outputs to external storage and reload them on demand, which reduces memory bloat and keeps active context concise. By combining embeddings, vector search, and summarization workflows, ReMe lets developers build agent systems that can recall and apply past knowledge in future reasoning tasks. The project fits into the broader agent-oriented programming ecosystem by supplying a standardized memory layer that integrates with agent frameworks. -
24
HunyuanImage-3.0
A Powerful Native Multimodal Model for Image Generation
HunyuanImage-3.0 is a powerful, native multimodal text-to-image generation model released by Tencent’s Hunyuan team. It unifies multimodal understanding and generation in a single autoregressive framework, combining text and image modalities seamlessly rather than relying on separate image-only diffusion components. It uses a Mixture-of-Experts (MoE) architecture with many expert subnetworks to scale efficiently, deploying only a subset of experts per token, which allows large parameter... -
25
Sprix SAGE Router
State-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks
Sprix SAGE Router is an open-source routing layer for coordinating agents in Agent2Agent networks. It decides whether an active agent should continue alone, recruit collaborators, or hand a task to another specialist. Routing decisions account for current progress, capability coverage, context-transfer costs, permissions, budgets, and deadlines. The system assigns remaining requirements to agents through task dependency graphs and estimates execution schedules.
