Business Software for Together AI

DeepSWE is an innovative and fully open-source coding agent that utilizes the Qwen3-32B foundation model, trained solely through reinforcement learning (RL) without any supervised fine-tuning or reliance on proprietary model distillation. Created with rLLM, which is Agentica’s open-source RL framework for language-based agents, DeepSWE operates as a functional agent within a simulated development environment facilitated by the R2E-Gym framework. This allows it to leverage a variety of tools, including a file editor, search capabilities, shell execution, and submission features, enabling the agent to efficiently navigate codebases, modify multiple files, compile code, run tests, and iteratively create patches or complete complex engineering tasks. Beyond simple code generation, DeepSWE showcases advanced emergent behaviors; when faced with bugs or new feature requests, it thoughtfully reasons through edge cases, searches for existing tests within the codebase, suggests patches, develops additional tests to prevent regressions, and adapts its cognitive approach based on the task at hand. This flexibility and capability make DeepSWE a powerful tool in the realm of software development.

DeepSeek-V4 is an advanced open-source large language model engineered for efficient long-context processing and high-level reasoning tasks. Supporting a massive one million token context window, it enables developers to build applications that handle extensive data and complex workflows without fragmentation. The model is available in two versions: V4-Pro for maximum reasoning power and V4-Flash for faster, cost-efficient performance. DeepSeek-V4-Pro delivers top-tier results in coding, mathematics, and knowledge benchmarks, rivaling leading proprietary models. Its architecture incorporates innovative attention techniques that significantly improve efficiency while maintaining strong performance. The model is optimized for agent-based workflows, allowing seamless integration with tools and automation systems. It also supports dual reasoning modes, enabling users to switch between quick responses and deeper analytical outputs. DeepSeek-V4 is fully open-source, providing flexibility for customization and deployment across various environments. Overall, it offers a powerful and scalable solution for modern AI development.

Qwen3.5 represents a major advancement in open-weight multimodal AI models, engineered to function as a native vision-language agent system. Its flagship model, Qwen3.5-397B-A17B, leverages a hybrid architecture that fuses Gated DeltaNet linear attention with a high-sparsity mixture-of-experts framework, allowing only 17 billion parameters to activate during inference for improved speed and cost efficiency. Despite its sparse activation, the full 397-billion-parameter model achieves competitive performance across reasoning, coding, multilingual benchmarks, and complex agent evaluations. The hosted Qwen3.5-Plus version supports a one-million-token context window and includes built-in tool use for search, code interpretation, and adaptive reasoning. The model significantly expands multilingual coverage to 201 languages and dialects while improving encoding efficiency with a larger vocabulary. Native multimodal training enables strong performance in image understanding, video processing, document analysis, and spatial reasoning tasks. Its infrastructure includes FP8 precision pipelines and heterogeneous parallelism to boost throughput and reduce memory consumption. Reinforcement learning at scale enhances multi-step planning and general agent behavior across text and multimodal environments. Overall, Qwen3.5 positions itself as a high-efficiency foundation for autonomous digital agents capable of reasoning, searching, coding, and interacting with complex environments.

MiniMax M2.7 is a powerful AI model built to drive real-world productivity across coding, search, and office-based workflows. It is trained using reinforcement learning across a wide range of real-world environments, enabling it to execute complex, multi-step tasks with precision and efficiency. The model demonstrates strong problem-solving capabilities by breaking down challenges into structured steps before generating solutions across multiple programming languages. It delivers high-speed performance with rapid token output, ensuring faster completion of demanding tasks. With optimized reasoning, it reduces token usage and execution time, making it more efficient than previous models. M2.7 also achieves state-of-the-art results in software engineering benchmarks, significantly improving response times for technical issues. Its advanced agentic capabilities allow it to work seamlessly with tools and support complex workflows with high skill accuracy. The model is designed to handle professional tasks, including multi-turn interactions and high-quality document editing. It also provides strong support for office productivity, enabling efficient handling of structured data and business tasks. With competitive pricing, it delivers high performance while remaining cost-effective. Overall, it combines speed, intelligence, and versatility to meet the needs of modern professionals and teams.

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.

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.

LLMetrics serves as a comprehensive cost tracking solution for teams involved in the development of AI products, integrating model expenses, token consumption, feature attribution, and usage notifications into a single, interactive dashboard. This powerful tool accommodates over 100 models from various providers, including OpenAI, Anthropic, Google Gemini, Mistral, Cohere, Together AI, and Groq, with pricing information updated on a daily basis. Teams can label each model interaction with details such as feature name, provider, model type, input tokens, and output tokens, enabling them to pinpoint which specific functionalities—be it a chatbot, summarizer, search tool, or lesson creator—are contributing to their expenditures. The platform offers real-time updates and daily trend visualizations, illustrating how costs fluctuate in response to software releases, modifications to prompts, increases in traffic, or transitions between models. Additionally, it includes spend thresholds and spike-detection features that can alert teams via email or Slack when unusual usage patterns are identified, aiding them in preventing runaway loops and unforeseen cost surges prior to receiving the provider invoice. By leveraging these insights, teams can make informed decisions regarding their AI product strategies and budget management.

Cut down on administrative expenses and enhance reimbursement rates, all while ensuring compliance is upheld. Transform your revenue cycle management (RCM) with the innovative capabilities of RapidClaims powered by AI technology. Significantly reduce administrative costs, elevate reimbursement levels, and maintain compliance with minimal effort. Simplify your coding workflow, and either automate tasks or empower your coding staff with tailored solutions that meet your specific needs. Process thousands of charts quickly and accurately while addressing the distinct demands of each client. Our advanced language model adeptly handles unstructured data, crafting a comprehensive patient record by turning notes into organized codes and identifying disease patterns. Avoid repeating past errors by establishing broad coding-related rules in straightforward language, which can be easily implemented across your charts, categorized by specialty, code type, and individual coders. Enhance your insight into code-level trends across various locations and take proactive steps to refine the revenue cycle. Additionally, our platform meticulously reviews charts to uncover claim denial trends, equipping you with the tools to address these challenges effectively and improve overall performance. With these capabilities, you can ensure a more streamlined and efficient coding process that supports your organization's financial health.

AI engineering can be transparent rather than opaque. With a suite of tools for tracing, assessment, prompt management, and more, HoneyHive emerges as a comprehensive platform for AI observability and evaluation, aimed at helping teams create dependable generative AI applications. This platform equips users with resources for model evaluation, testing, and monitoring, promoting effective collaboration among engineers, product managers, and domain specialists. By measuring quality across extensive test suites, teams can pinpoint enhancements and regressions throughout the development process. Furthermore, it allows for the tracking of usage, feedback, and quality on a large scale, which aids in swiftly identifying problems and fostering ongoing improvements. HoneyHive is designed to seamlessly integrate with various model providers and frameworks, offering the necessary flexibility and scalability to accommodate a wide range of organizational requirements. This makes it an ideal solution for teams focused on maintaining the quality and performance of their AI agents, delivering a holistic platform for evaluation, monitoring, and prompt management, ultimately enhancing the overall effectiveness of AI initiatives. As organizations increasingly rely on AI, tools like HoneyHive become essential for ensuring robust performance and reliability.

Nurix AI, located in Bengaluru, focuses on creating customized AI agents that aim to streamline and improve enterprise workflows across a range of industries, such as sales and customer support. Their platform is designed to integrate effortlessly with current enterprise systems, allowing AI agents to perform sophisticated tasks independently, deliver immediate responses, and make smart decisions without ongoing human intervention. One of the most remarkable aspects of their offering is a unique voice-to-voice model, which facilitates fast and natural conversations in various languages, thus enhancing customer engagement. Furthermore, Nurix AI provides specialized AI services for startups, delivering comprehensive solutions to develop and expand AI products while minimizing the need for large internal teams. Their wide-ranging expertise includes large language models, cloud integration, inference, and model training, guaranteeing that clients receive dependable and enterprise-ready AI solutions tailored to their specific needs. By committing to innovation and quality, Nurix AI positions itself as a key player in the AI landscape, supporting businesses in leveraging technology for greater efficiency and success.

Assembly sharpens your entire development perspective, ensuring you begin each day with a clear vision. This innovative platform is set to transform software development by merging understanding, planning, coding, reviewing, and documentation into an integrated framework. Acting as the central hub for development teams, Factory provides customized dashboards that showcase pertinent tasks and optimize workflows, guaranteeing both clarity and productivity from the outset of each day. It supports collaborative design and strategic planning, enabling teams to efficiently create architectures, articulate requirements, and devise technical roadmaps. Furthermore, the codebase Q&A functionality enhances onboarding and knowledge transfer by preserving context and decision-making processes, making it easier to grasp intricate systems. In addition, Factory's AI-enhanced code review mechanism thoroughly analyzes codebases, pinpointing nuanced problems and facilitating effective implementation of feedback for continuous improvement. This comprehensive approach not only elevates individual productivity but also fosters a culture of collaboration and innovation within development teams.

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.

Orq.ai stands out as the leading platform tailored for software teams to effectively manage agentic AI systems on a large scale. It allows you to refine prompts, implement various use cases, and track performance meticulously, ensuring no blind spots and eliminating the need for vibe checks. Users can test different prompts and LLM settings prior to launching them into production. Furthermore, it provides the capability to assess agentic AI systems within offline environments. The platform enables the deployment of GenAI features to designated user groups, all while maintaining robust guardrails, prioritizing data privacy, and utilizing advanced RAG pipelines. It also offers the ability to visualize all agent-triggered events, facilitating rapid debugging. Users gain detailed oversight of costs, latency, and overall performance. Additionally, you can connect with your preferred AI models or even integrate your own. Orq.ai accelerates workflow efficiency with readily available components specifically designed for agentic AI systems. It centralizes the management of essential phases in the LLM application lifecycle within a single platform. With options for self-hosted or hybrid deployment, it ensures compliance with SOC 2 and GDPR standards, thereby providing enterprise-level security. This comprehensive approach not only streamlines operations but also empowers teams to innovate and adapt swiftly in a dynamic technological landscape.

Vertesia serves as a comprehensive, low-code platform for generative AI that empowers enterprise teams to swiftly design, implement, and manage GenAI applications and agents on a large scale. Tailored for both business users and IT professionals, it facilitates a seamless development process, enabling a transition from initial prototype to final production without the need for lengthy timelines or cumbersome infrastructure. The platform accommodates a variety of generative AI models from top inference providers, granting users flexibility and reducing the risk of vendor lock-in. Additionally, Vertesia's agentic retrieval-augmented generation (RAG) pipeline boosts the precision and efficiency of generative AI by automating the content preparation process, which encompasses advanced document processing and semantic chunking techniques. With robust enterprise-level security measures, adherence to SOC2 compliance, and compatibility with major cloud services like AWS, GCP, and Azure, Vertesia guarantees safe and scalable deployment solutions. By simplifying the complexities of AI application development, Vertesia significantly accelerates the path to innovation for organizations looking to harness the power of generative AI.

LFM2 represents an advanced series of on-device foundation models designed to provide a remarkably swift generative-AI experience across a diverse array of devices. By utilizing a novel hybrid architecture, it achieves decoding and pre-filling speeds that are up to twice as fast as those of similar models, while also enhancing training efficiency by as much as three times compared to its predecessor. These models offer a perfect equilibrium of quality, latency, and memory utilization suitable for embedded system deployment, facilitating real-time, on-device AI functionality in smartphones, laptops, vehicles, wearables, and various other platforms, which results in millisecond inference, device durability, and complete data sovereignty. LFM2 is offered in three configurations featuring 0.35 billion, 0.7 billion, and 1.2 billion parameters, showcasing benchmark results that surpass similarly scaled models in areas including knowledge recall, mathematics, multilingual instruction adherence, and conversational dialogue assessments. With these capabilities, LFM2 not only enhances user experience but also sets a new standard for on-device AI performance.

The leading open-source AI assistant. You can create custom autocomplete experiences and chats by connecting any models to any context. Remove the barriers that hinder productivity when developing software to remain in flow. Accelerate your development with a plug and play system that is easy to use and integrates into your entire stack. Set up your code assistant so that it can evolve with new capabilities. Continue autocompletes entire sections of code or single lines in any programming languages as you type. Ask questions about files, functions, the entire codebase and more by attaching code or context. Highlight code sections, then press the keyboard shortcut to convert code into natural language.

gpt-oss-20b is a powerful text-only reasoning model consisting of 20 billion parameters, made available under the Apache 2.0 license and influenced by OpenAI’s gpt-oss usage guidelines, designed to facilitate effortless integration into personalized AI workflows through the Responses API without depending on proprietary systems. It has been specifically trained to excel in instruction following and offers features like adjustable reasoning effort, comprehensive chain-of-thought outputs, and the ability to utilize native tools such as web search and Python execution, resulting in structured and clear responses. Developers are responsible for establishing their own deployment precautions, including input filtering, output monitoring, and adherence to usage policies, to ensure that they align with the protective measures typically found in hosted solutions and to reduce the chance of malicious or unintended actions. Additionally, its open-weight architecture makes it particularly suitable for on-premises or edge deployments, emphasizing the importance of control, customization, and transparency to meet specific user needs. This flexibility allows organizations to tailor the model according to their unique requirements while maintaining a high level of operational integrity.

gpt-oss-120b is a text-only reasoning model with 120 billion parameters, released under the Apache 2.0 license and managed by OpenAI’s usage policy, developed with insights from the open-source community and compatible with the Responses API. It is particularly proficient in following instructions, utilizing tools like web search and Python code execution, and allowing for adjustable reasoning effort, thereby producing comprehensive chain-of-thought and structured outputs that can be integrated into various workflows. While it has been designed to adhere to OpenAI's safety policies, its open-weight characteristics present a risk that skilled individuals might fine-tune it to circumvent these safeguards, necessitating that developers and enterprises apply additional measures to ensure safety comparable to that of hosted models. Evaluations indicate that gpt-oss-120b does not achieve high capability thresholds in areas such as biological, chemical, or cyber domains, even following adversarial fine-tuning. Furthermore, its release is not seen as a significant leap forward in biological capabilities, marking a cautious approach to its deployment. As such, users are encouraged to remain vigilant about the potential implications of its open-weight nature.

Wan 2.6 is a state-of-the-art video generation model developed by Alibaba for high-fidelity multimodal content creation. It enables users to generate short videos directly from text prompts, images, or existing video inputs. The model produces clips up to 15 seconds long while preserving visual coherence and storytelling quality. Built-in audio and visual synchronization ensures that speech, music, and sound effects match the generated visuals seamlessly. Wan 2.6 delivers fluid motion, realistic character animation, and smooth camera transitions. Advanced lip-sync capabilities enhance realism in dialogue-driven scenes. The model supports multiple resolutions, making it suitable for professional and social media use. Users can animate still images into consistent video sequences without losing character identity. Flexible prompt handling supports multiple languages natively. Wan 2.6 streamlines short-form video production with speed and precision.

The Nemotron-3 Super is an innovative member of NVIDIA's Nemotron 3 series of open models, specifically crafted to facilitate sophisticated agentic AI systems that can effectively reason, plan, and carry out multi-step workflows in intricate environments. This model features a unique hybrid Mamba-Transformer Mixture-of-Experts architecture that merges the streamlined efficiency of Mamba layers with the contextual depth provided by transformer attention mechanisms, which allows it to adeptly manage extended sequences and intricate reasoning tasks with impressive accuracy and throughput. By activating only a portion of its parameters for each token, this architecture significantly enhances computational efficiency while preserving robust reasoning capabilities, making it ideal for scalable inference under heavy workloads. The Nemotron-3 Super comprises approximately 120 billion parameters, with around 12 billion being active during inference, which substantially boosts its ability to handle multi-step reasoning and collaborative interactions among agents within extensive contexts. Such advancements make it a powerful tool for tackling diverse challenges in AI applications.

Scribe is an automated knowledge base that operates on a self-hosted platform, utilizing your tools to generate content. It analyzes the Git history, Claude Code and Codex sessions, as well as self-sent URLs and drop files, transforming this information into a well-organized, cross-project wiki formatted in Markdown and stored within Git repositories. By eliminating the need for developers to maintain an additional cognitive framework or to reconstruct context each time an agent session begins anew, Scribe effectively captures critical decisions, fixes, evaluations, and the rationale behind them, enabling agents to reference this accumulated knowledge prior to taking action. Its operational pipeline is scheduled via cron jobs, allowing it to identify projects and sift through low-value data using FTS5 before engaging with an LLM, thus extracting verified facts through structured bounded workflows that run in two passes. The final output is organized into entity-centric pages complete with YAML frontmatter, wikilinks, backlinks, retrieval context, and various typed relationships, including supersedes, contradicts, derived_from, specializes, and extends, ensuring comprehensive documentation and clarity across projects. This systematic approach significantly enhances collaboration and knowledge sharing among teams, streamlining the development process.