Business Software for Ollama

Qwen3.5-35B-A3B is a member of the Qwen3.5 "Medium" model series, meticulously crafted as an effective multimodal foundation model that strikes a balance between robust reasoning capabilities and practical application needs. Utilizing a Mixture-of-Experts (MoE) architecture, it boasts a total of 35 billion parameters, yet activates only around 3 billion for each token, enabling it to achieve performance levels similar to much larger models while significantly cutting down on computational expenses. The model employs a hybrid attention mechanism that merges linear attention with traditional attention layers, which enhances its ability to handle extensive context and boosts scalability for intricate tasks. As an inherently vision-language model, it processes both textual and visual data, catering to a variety of applications, including multimodal reasoning, programming, and automated workflows. Furthermore, it is engineered to operate as a versatile "AI agent," proficient in planning, utilizing tools, and systematically solving problems, extending its functionality beyond mere conversational interactions. This capability positions it as a valuable asset across diverse domains, where advanced AI-driven solutions are increasingly required.

HiClaw is a multi-agent operating system that is open source and operates on the Matrix framework, allowing various AI agents to work together within Matrix rooms, where their activities are fully accessible to humans in real-time. The system features a Manager Agent that oversees multiple Worker Agents, efficiently breaking down complex tasks and facilitating simultaneous execution, which enhances the management of these intricate operations. Designed with a focus on enterprise-level security and collaborative capabilities, HiClaw utilizes the open Matrix instant messaging protocol, ensuring that all communications between agents are transparent, easily auditable, and fit for distributed systems and federated environments. Humans have the ability to join any Matrix room whenever they wish, which allows them to monitor agent discussions, intervene as necessary, or adjust agent actions in real-time, thereby safeguarding oversight and control. This structured two-tier system, consisting of Manager and Worker Agents, delineates clear responsibilities for each agent, simplifying the process of integrating custom Worker Agents tailored for various applications, while also promoting adaptability within the architecture. Consequently, the design of HiClaw not only enhances operational efficiency but also paves the way for innovative uses of AI collaboration across diverse scenarios.

PyGPT is a versatile open-source AI assistant designed for personal use on desktop systems such as Linux, Windows, and Mac, and it is developed using Python. It operates in a manner akin to ChatGPT but functions locally on your computer, providing features like chat, image and video generation, vision capabilities, voice control, and more. Supporting a variety of models, PyGPT includes options like OpenAI's GPT-5, GPT-4, o1, o3, o4, Google Gemini, Anthropic Claude, xAI Grok, Perplexity Sonar, DeepSeek, Mistral AI, alongside models from Ollama and LlamaIndex. Users can choose from 12 operational modes, including chatting with files, real-time audio interactions, research, completion tasks, and various imaging capabilities. With integrated LlamaIndex support, users can engage with their personal files and data seamlessly. Additionally, PyGPT features built-in vector database capabilities, automated embedding of files and data, and maintains full conversation context alongside both short- and long-term memory. The assistant is equipped with internet access through platforms like Google, Microsoft Bing, and DuckDuckGo, enhancing its functionality, which also includes speech synthesis and recognition, making it a comprehensive tool for productivity. Overall, PyGPT stands out as an innovative solution for those seeking a powerful local AI assistant.

OllaCoder serves as a private AI coding assistant tailored for VS Code, catering specifically to developers who prefer not to upload their source code to external servers. Operating locally, it utilizes your personal Ollama models and integrates features such as agent mode, inline edits, codebase chat, intelligent autocomplete, MCP servers, and a local-first runtime all within a single editor interface. The core philosophy behind OllaCoder emphasizes the notion that software development is a personal endeavor, asserting that your code should remain under your control while providing an AI assistant that is robust, transparent, and unobtrusive. It primarily communicates with your local Ollama instance, ensuring that prompts, completions, and modifications remain on your device; cloud services are optional, with API keys securely stored in the OS keychain. OllaCoder's agent mode is capable of planning tasks, modifying files, executing terminal commands, and confirming the accuracy of its work, allowing users to approve, reject, or revert any action taken. Additionally, the inline edits feature enables users to select a function, specify the desired change, and examine a real diff change by change, enhancing the coding experience. Overall, OllaCoder represents a significant step forward in maintaining code privacy while providing powerful AI-assisted development tools.

Dock serves as a collaborative AI workspace designed for you, your team, and the various agents you deploy. It enables both humans and AI agents to share a unified cloud environment, allowing everyone to access and modify the same information in real-time, rather than navigating through disjointed chats, files, and isolated outputs. The platform is structured around tables with defined columns, rich-text documents, and recognizes agents as primary entities, each equipped with their own API keys, permissions, and audit trails, eliminating the need for delegated human tokens. Teams can leverage Dock for a multitude of tasks, including planning, researching, decision-making, and executing projects, all within a shared interface that accommodates both human and AI contributions. Use cases for Dock span various domains, including engineering, go-to-market strategies, research, operations, individual projects, and agency tasks. Engineering teams can utilize Dock to facilitate sprint planning, create specification documents, and respond to incidents efficiently; marketing teams can streamline content calendars, manage sales pipelines, and enhance customer success initiatives; research teams can effectively document interviews, identify themes, and analyze competitive intelligence; and operations teams can oversee runbooks, manage recruitment processes, ensure compliance, and coordinate onboarding efforts. In essence, Dock fosters a seamless collaboration environment that enhances productivity and innovation across all team functions.

Laguna XS.2 represents Poolside’s innovative open-weight coding model, distinguished as the lightest and quickest member of the Laguna series. This model features a total of 33 billion parameters in a Mixture of Experts setup, with 3 billion parameters activated, and has been meticulously trained in-house using 30 trillion tokens. As the latest generation model accessible to the public, it embodies a second-generation architecture and marks Poolside’s inaugural open-weight offering, drawing from insights gained during the training of Laguna M.1 with synthetic data and reinforcement learning techniques. Specifically designed to enhance agentic coding workflows, Laguna XS.2 excels in coding, acting, and rapidly iterating, particularly within Poolside’s coding agent environment. This model is particularly advantageous for developers and teams seeking a lightweight, efficient coding solution rather than a more cumbersome frontier system. Released under the permissive Apache 2.0 license, it empowers the community to assess, fine-tune, quantize, and build upon its weights, fostering a collaborative development atmosphere. In essence, Laguna XS.2 not only provides a robust platform for agentic coding but also encourages innovation and experimentation among its users.

Laguna M.1 stands out as Poolside's most proficient model for agentic coding, meticulously developed in-house specifically for enhancing software development workflows. This model features a total of 225 billion parameters, utilizing a Mixture of Experts architecture with 23 billion activated parameters, and has been trained entirely within the organization on a dataset consisting of 30 trillion tokens, leveraging the power of 6,144 interconnected NVIDIA H200 GPUs. Poolside undertook the task of training Laguna M.1 from the ground up, employing its proprietary data, dedicated training codebase, and an asynchronous on-policy reinforcement learning approach within its agent framework, all tailored for agentic coding applications. The design of the model ensures optimal performance within Poolside's coding agent, enabling it to effectively reason through software tasks, interact with various tools, edit code, execute tests, and facilitate extended autonomous development sessions. Specifically crafted for developers and teams tackling intricate coding challenges, Laguna M.1 offers enhanced capabilities in reasoning, architectural comprehension, terminal operations, and multi-step execution, surpassing what lighter models can achieve. Ultimately, its robust feature set positions it as an essential asset for those engaged in demanding software projects.

AI Workers are independent agents crafted specifically for your organization; these advanced AI entities function like genuine colleagues rather than mere chatbots awaiting instructions. Each comes equipped with its own professional identity, including an email, phone number, and presence on platforms like Slack and Teams, demonstrating initiative and the capacity to operate around the clock without needing prompts. Rather than dictating every detail of their tasks, you simply define the objectives, and they autonomously develop the necessary workflows, accommodating a variety of tasks such as generating daily reports, conducting weekly follow-ups, managing CRM updates, handling client interactions, performing research, overseeing content creation, executing finance responsibilities, coordinating HR activities, supporting design projects, and assisting with development operations. This system includes a diverse range of specialized AI Workers tailored for functions in marketing, development, design, HR, finance, and more, with each worker crafted for a specific role and practical applications. Furthermore, AI Workers can integrate seamlessly with over 3,000 tools, such as Slack, Microsoft Teams, Gmail, Notion, HubSpot, Salesforce, and various other business applications, ensuring they fit effortlessly into your existing workflows. Their versatility and adaptability make them an invaluable asset for enhancing productivity and streamlining processes in any business environment.

OpenWorker serves as an open-source, locally-focused AI assistant designed to complete various daily tasks from initiation to conclusion rather than merely providing answers. Users can request specific results like a renewal brief, incident report, follow-up message, calendar update, sprint summary, or finalized document, and OpenWorker seamlessly operates across multiple platforms where the relevant data is stored. It offers integration with a range of services including Slack, Gmail, Outlook, Google Calendar, Notion, HubSpot, GitHub, Attio, Google Drive, Jira, Linear, Asana, Dropbox, Box, and an array of other applications through both one-click and manual connections. The platform accommodates cloud, open-weight, and fully local models, supporting providers such as OpenAI, Anthropic, Google, xAI, Mistral, DeepSeek, Kimi, Qwen, and Ollama, allowing users the flexibility to switch models based on task requirements. OpenWorker excels at researching, gathering necessary context, executing multi-step tasks, and generating refined outputs in various formats like chat, Slack, Markdown, PDF, images, or files, all while ensuring to check in prior to making significant decisions. This comprehensive suite of functionalities empowers users to streamline their workflows and enhances overall productivity.

FluentDB is an advanced database client designed specifically for Apple Silicon Macs, emphasizing an AI-centric approach by integrating a schema-aware assistant, a contemporary SQL editor, a user-friendly keyboard navigator, efficient data tables, and essential safety measures within a singular, streamlined interface. It offers seamless connectivity to various databases, including PostgreSQL, MySQL, SQLite, and Microsoft SQL Server, allowing users to pose inquiries in plain English and receive accurately generated SQL statements tailored to their actual tables and columns. The AI prioritizes schema interpretation over row data, refrains from executing any statements autonomously, and seeks user consent prior to executing any write queries, ensuring a high level of control. Features like read-only connections, local query history, server-side cancellation for unresponsive queries, and transparent SQL execution empower users to maintain oversight of their operations. The editor enhances productivity with schema-aware autocomplete, formatting options, saved queries, instant previews, and the ability to effortlessly toggle between manual SQL and AI-driven modes without any loss of context. Users can access a comprehensive range of database components—such as tables, views, functions, sequences, types, and extensions—by using Command + P, while the intuitive native grid allows for smooth scrolling, editing, sorting, copying, and exporting of data, enhancing the overall user experience. This innovative tool is designed to elevate database management by merging advanced AI capabilities with user-friendly functionality.

Introducing the next iteration of our open-source large language model, this version features model weights along with initial code for the pretrained and fine-tuned Llama language models, which span from 7 billion to 70 billion parameters. The Llama 2 pretrained models have been developed using an impressive 2 trillion tokens and offer double the context length compared to their predecessor, Llama 1. Furthermore, the fine-tuned models have been enhanced through the analysis of over 1 million human annotations. Llama 2 demonstrates superior performance against various other open-source language models across multiple external benchmarks, excelling in areas such as reasoning, coding capabilities, proficiency, and knowledge assessments. For its training, Llama 2 utilized publicly accessible online data sources, while the fine-tuned variant, Llama-2-chat, incorporates publicly available instruction datasets along with the aforementioned extensive human annotations. Our initiative enjoys strong support from a diverse array of global stakeholders who are enthusiastic about our open approach to AI, including companies that have provided valuable early feedback and are eager to collaborate using Llama 2. The excitement surrounding Llama 2 signifies a pivotal shift in how AI can be developed and utilized collectively.

Code Llama is an advanced language model designed to generate code through text prompts, distinguishing itself as a leading tool among publicly accessible models for coding tasks. This innovative model not only streamlines workflows for existing developers but also aids beginners in overcoming challenges associated with learning to code. Its versatility positions Code Llama as both a valuable productivity enhancer and an educational resource, assisting programmers in creating more robust and well-documented software solutions. Additionally, users can generate both code and natural language explanations by providing either type of prompt, making it an adaptable tool for various programming needs. Available for free for both research and commercial applications, Code Llama is built upon Llama 2 architecture and comes in three distinct versions: the foundational Code Llama model, Code Llama - Python which is tailored specifically for Python programming, and Code Llama - Instruct, optimized for comprehending and executing natural language directives effectively.

GPT Pilot is an innovative open-source AI application designed to function as a comprehensive AI developer, generating fully operational applications with very little human intervention. In contrast to basic code autocompletion utilities, GPT Pilot is capable of creating entire features, troubleshooting code, discussing problems, and even soliciting code reviews. This tool seeks to expand the horizons of AI-driven software development by managing as much as 95% of coding responsibilities, reserving the remaining 5% for human developers. Additionally, it is designed to work seamlessly with platforms such as VS Code, allowing for real-time collaboration between developers and AI. By facilitating this partnership, GPT Pilot empowers developers to focus on more complex tasks while the AI handles routine coding challenges.

Created by LM-SYS, RouteLLM is a publicly available toolkit that enables users to direct tasks among various large language models to enhance resource management and efficiency. It features strategy-driven routing, which assists developers in optimizing speed, precision, and expenses by dynamically choosing the most suitable model for each specific input. This innovative approach not only streamlines workflows but also enhances the overall performance of language model applications.

Airtool is a powerful low-code platform designed to simplify enterprise application development and data management. With features like real-time dashboards, customizable forms, and integrated analytics, businesses can streamline workflows, improve operational reporting, and gain actionable insights into their performance. Airtool's flexibility allows for quick development, with the ability to integrate various data sources and AI-powered tools for enhanced decision-making. Whether you're optimizing data handling or creating custom applications, Airtool provides a scalable, secure, and efficient solution for modern businesses.

AppFit offers a comprehensive suite of tools to take your concepts from inception to launch, ensuring your web and mobile application development is a success. With AI support integrated throughout the entire development journey, you can effortlessly build full-stack applications while generating code, designing intuitive interfaces, and troubleshooting challenges more efficiently than ever. Leverage AI-driven market insights and analytics to validate your app ideas, helping you quickly identify the right product-market fit. Gain a deep understanding of your target audience and competitive landscape even before the first line of code is written. Our gamified no-code editor facilitates learning as you create, offering engaging, bite-sized lessons akin to how Duolingo teaches languages. With AppFit, you can seamlessly develop responsive web applications and mobile apps that feel native, all from a single codebase. This approach not only conserves time and resources but also broadens your reach to users across a multitude of devices, enhancing your application's accessibility and impact. Additionally, our platform empowers you to innovate and iterate rapidly, ensuring your app remains relevant in an ever-changing market.

Introducing Gemma 3n, our cutting-edge open multimodal model designed specifically for optimal on-device performance and efficiency. With a focus on responsive and low-footprint local inference, Gemma 3n paves the way for a new generation of intelligent applications that can be utilized on the move. It has the capability to analyze and respond to a blend of images and text, with plans to incorporate video and audio functionalities in the near future. Developers can create smart, interactive features that prioritize user privacy and function seamlessly without an internet connection. The model boasts a mobile-first architecture, significantly minimizing memory usage. Co-developed by Google's mobile hardware teams alongside industry experts, it maintains a 4B active memory footprint while also offering the flexibility to create submodels for optimizing quality and latency. Notably, Gemma 3n represents our inaugural open model built on this revolutionary shared architecture, enabling developers to start experimenting with this advanced technology today in its early preview. As technology evolves, we anticipate even more innovative applications to emerge from this robust framework.

Elestio is a comprehensive DevOps platform that allows users to launch over 350 open source software applications on dedicated virtual machines in less than three minutes. This service manages crucial tasks such as installation, configuration, encryption, backups, and both software and OS updates, enabling users to concentrate on maximizing the software's capabilities. Elestio is versatile in deployment options, supporting a variety of cloud providers like DigitalOcean, AWS, VULTR, Hetzner, Linode, and Scaleway, as well as on-premise setups, thereby providing flexibility and minimizing the risk of vendor lock-in. All offerings are powered by dedicated hardware, ensuring users have full access to resources and enhanced kernel-level security. The platform guarantees data protection by encrypting all connections between the user's device, the dashboard, and the services through end-to-end TLS encryption. Additionally, Elestio features a fully managed CI/CD system that integrates seamlessly with GitHub, GitLab, and Docker registries while remaining compatible with any Linux technology stack. This makes it an ideal choice for developers looking for a reliable and secure deployment environment.

The GLM-5V-Turbo is an advanced multimodal coding foundation model specifically tailored for tasks that require visual inputs, capable of handling various formats such as images, videos, texts, and files to generate text-based outputs. This model is particularly refined for agent workflows, which allows it to effectively understand environments, plan appropriate actions, and carry out tasks, while also ensuring compatibility with agent frameworks like Claude Code and OpenClaw. Its ability to manage long-context interactions is noteworthy, boasting a context capacity of 200K tokens and an output limit of up to 128K tokens, making it ideal for intricate, long-term projects. Furthermore, it provides a variety of thinking modes suited for diverse scenarios, exhibits robust visual comprehension for both images and videos, and streams output in real-time to enhance user engagement. Additionally, it features sophisticated function-calling abilities that facilitate the integration of external tools, and its context caching capability significantly boosts performance during prolonged conversations. In practical applications, the model can adeptly transform design mockups into fully functional frontend projects, showcasing its versatility and depth in real-world coding scenarios. This versatility ensures that users can tackle a wide range of complex tasks with confidence and efficiency.

Qwen3.6 is an advanced AI model from Alibaba that builds on previous Qwen releases with a focus on real-world utility and performance. It is designed as a multimodal large language model capable of understanding and generating text while also processing visual and structured data. The model is optimized for coding tasks, enabling developers to handle complex, repository-level programming workflows. Qwen3.6 uses a mixture-of-experts (MoE) architecture, which activates only a portion of its parameters during inference to improve efficiency. This design allows it to deliver strong performance while reducing computational costs. It is available in both proprietary and open-weight versions, giving developers flexibility in deployment. The model supports integration into enterprise systems and cloud platforms, particularly within Alibaba’s ecosystem. Qwen3.6 also introduces stronger agentic capabilities, allowing it to perform multi-step reasoning and more autonomous task execution. It is designed to handle complex workflows, including engineering, analysis, and decision-making tasks. The model emphasizes stability and responsiveness based on developer feedback. Overall, Qwen3.6 provides a scalable and efficient AI solution for coding, automation, and multimodal applications.

Osaurus is an innovative AI platform designed for macOS, enabling users to operate open models directly on their Mac while also providing the option to access cloud models for enhanced performance and share memory seamlessly between them. Developed using Swift specifically for Apple Silicon, it allows for complete offline functionality with local models through interfaces like Ollama, MLX, or LM Studio, ensuring that conversations, code, files, settings, agents, skills, and provider keys remain stored on the device unless the user opts for a cloud service. A convenient system-wide chat overlay grants users quick access to the AI from any application, and users can establish distinct agents tailored for various tasks such as coding, research, and file management, with each agent maintaining its own prompt, history, and memory. Osaurus intelligently synthesizes previous conversations into pertinent information, loads necessary skills for specific tasks, and provides agents with targeted access to relevant folders, file search capabilities, Git, and other essential tools. Additionally, agents operate within a secure sandbox environment, can delegate tasks to subagents, adhere to scheduled operations, react to changes in folders, utilize voice commands, and even create images, showcasing the platform's versatility and robust feature set. This comprehensive approach not only enhances productivity but also empowers users to customize their workflows efficiently.

Lightweight, fast, portable, and powered by Rust, our solution is designed to be compatible with OpenAI. We collaborate with cloud providers, particularly those specializing in edge cloud and CDN compute, to facilitate microservices tailored for web applications. Our solutions cater to a wide array of use cases, ranging from AI inference and database interactions to CRM systems, ecommerce, workflow management, and server-side rendering. Additionally, we integrate with streaming frameworks and databases to enable embedded serverless functions aimed at data filtering and analytics. These serverless functions can serve as database user-defined functions (UDFs) or be integrated into data ingestion processes and query result streams. With a focus on maximizing GPU utilization, our platform allows you to write once and deploy anywhere. In just five minutes, you can start utilizing the Llama 2 series of models directly on your device. One of the prominent methodologies for constructing AI agents with access to external knowledge bases is retrieval-augmented generation (RAG). Furthermore, you can easily create an HTTP microservice dedicated to image classification that operates YOLO and Mediapipe models at optimal GPU performance, showcasing our commitment to delivering efficient and powerful computing solutions. This capability opens the door for innovative applications in fields such as security, healthcare, and automatic content moderation.

Gemma represents a collection of cutting-edge, lightweight open models that are built upon the same research and technology underlying the Gemini models. Created by Google DeepMind alongside various teams at Google, the inspiration for Gemma comes from the Latin word "gemma," which translates to "precious stone." In addition to providing our model weights, we are also offering tools aimed at promoting developer creativity, encouraging collaboration, and ensuring the ethical application of Gemma models. Sharing key technical and infrastructural elements with Gemini, which stands as our most advanced AI model currently accessible, Gemma 2B and 7B excel in performance within their weight categories when compared to other open models. Furthermore, these models can conveniently operate on a developer's laptop or desktop, demonstrating their versatility. Impressively, Gemma not only outperforms significantly larger models on crucial benchmarks but also maintains our strict criteria for delivering safe and responsible outputs, making it a valuable asset for developers.

Discover a user-friendly yet thorough evaluation platform designed to continuously enhance your AI-powered products. By optimizing the LLMOps workflow, you can foster trust and secure a competitive advantage. EvalsOne serves as your comprehensive toolkit for refining your application evaluation process. Picture it as a versatile Swiss Army knife for AI, ready to handle any evaluation challenge you encounter. It is ideal for developing LLM prompts, fine-tuning RAG methods, and assessing AI agents. You can select between rule-based or LLM-driven strategies for automating evaluations. Moreover, EvalsOne allows for the seamless integration of human evaluations, harnessing expert insights for more accurate outcomes. It is applicable throughout all phases of LLMOps, from initial development to final production stages. With an intuitive interface, EvalsOne empowers teams across the entire AI spectrum, including developers, researchers, and industry specialists. You can easily initiate evaluation runs and categorize them by levels. Furthermore, the platform enables quick iterations and detailed analyses through forked runs, ensuring that your evaluation process remains efficient and effective. EvalsOne is designed to adapt to the evolving needs of AI development, making it a valuable asset for any team striving for excellence.

The Gemma family consists of advanced, lightweight models developed using the same innovative research and technology as the Gemini models. These cutting-edge models are equipped with robust security features that promote responsible and trustworthy AI applications, achieved through carefully curated data sets and thorough refinements. Notably, Gemma models excel in their various sizes—2B, 7B, 9B, and 27B—often exceeding the performance of some larger open models. With the introduction of Keras 3.0, users can experience effortless integration with JAX, TensorFlow, and PyTorch, providing flexibility in framework selection based on specific tasks. Designed for peak performance and remarkable efficiency, Gemma 2 is specifically optimized for rapid inference across a range of hardware platforms. Furthermore, the Gemma family includes diverse models that cater to distinct use cases, ensuring they adapt effectively to user requirements. These lightweight language models feature a decoder and have been trained on an extensive array of textual data, programming code, and mathematical concepts, which enhances their versatility and utility in various applications.