Cerebras Integrations

StackAI is an enterprise AI automation platform built to help organizations create end-to-end internal tools and processes with AI agents. Unlike point solutions or one-off chatbots, StackAI provides a single platform where enterprises can design, deploy, and govern AI workflows in a secure, compliant, and fully controlled environment. Using its visual workflow builder, teams can map entire processes — from data intake and enrichment to decision-making, reporting, and audit trails. Enterprise knowledge bases such as SharePoint, Confluence, Notion, Google Drive, and internal databases can be connected directly, with features for version control, citations, and permissioning to keep information reliable and protected. AI agents can be deployed in multiple ways: as a chat assistant embedded in daily workflows, an advanced form for structured document-heavy tasks, or an API endpoint connected into existing tools. StackAI integrates natively with Slack, Teams, Salesforce, HubSpot, ServiceNow, Airtable, and more. Security and compliance are embedded at every layer. The platform supports SSO (Okta, Azure AD, Google), role-based access control, audit logs, data residency, and PII masking. Enterprises can monitor usage, apply cost controls, and test workflows with guardrails and evaluations before production. StackAI also offers flexible model routing, enabling teams to choose between OpenAI, Anthropic, Google, or local LLMs, with advanced settings to fine-tune parameters and ensure consistent, accurate outputs. A growing template library speeds deployment with pre-built solutions for Contract Analysis, Support Desk Automation, RFP Response, Investment Memo Generation, and InfoSec Questionnaires. By replacing fragmented processes with secure, AI-driven workflows, StackAI helps enterprises cut manual work, accelerate decision-making, and empower non-technical teams to build automation that scales across the organization.

MachinesFluent is a versatile AI-powered dictation tool that enables users to voice their thoughts on multiple platforms, both online and offline, transforming their spoken input into raw text, polished documents, summaries, translations, replies, comprehensive notes, or any tailored format they need. This innovative app also allows for voice-activated searches on the web, effortless handling of copied text, image analysis from your clipboard, and transcription of existing audio or video files. Users are granted the ability to dictate offline, enhancing privacy, while still enjoying the ease of cloud-based speech functionalities, as well as options for local and cloud AI solutions. Moreover, it features direct sign-in for OpenAI accounts, customizable prompts, tailored model selections, vocabulary lists, audio snippets of voice, a log of previous commands, adjustable hotkeys, and dictation styles that cater to specific applications or websites. Built for individuals who prioritize fast dictation, value privacy when required, harness AI capabilities when beneficial, and desire the flexibility to customize their workflows, MachinesFluent truly excels in the competitive landscape of dictation software. As a result, it provides a comprehensive suite of tools that accommodate a wide range of user needs, making it an essential application for anyone looking to enhance their dictation experience.

Kimi K3 is Moonshot AI’s most advanced model, designed for high-end reasoning, software engineering, multimodal understanding, knowledge work, and agentic AI applications. The model has 2.8 trillion parameters and is built on Kimi Delta Attention, a hybrid linear attention mechanism created for long-context performance. It also uses Attention Residuals and supports a native context window of up to 1 million tokens. This makes Kimi K3 suitable for tasks involving large codebases, long research materials, enterprise documentation, multi-file analysis, legal documents, technical manuals, and complex workflows. Kimi K3 always has thinking mode enabled, with reasoning effort configured through the reasoning_effort field and maximum effort currently supported as the default. Developers can use the model through an OpenAI-compatible API, making it easier to integrate with existing SDKs, clients, and application infrastructure. The model supports streaming responses with separate reasoning and final-answer deltas, allowing applications to display reasoning progress and final content differently. Kimi K3 also supports strict structured output with JSON Schema, partial mode for continuing from a prefix, custom tool calling, required tool use, and dynamic tool loading through system messages. Its vision capabilities support image and video inputs through base64 or uploaded files, enabling analysis of visual content alongside text. Automatic context caching helps workflows that reuse long prefixes, such as large knowledge bases or persistent system context, without requiring developers to manage cache IDs manually. By combining frontier-scale parameters, long-context processing, visual input, structured outputs, tool orchestration, and developer-friendly API compatibility, Kimi K3 gives teams a strong foundation for advanced AI agents, coding assistants, research systems, enterprise automation, and multimodal applications.

Kimi K2.7 Code is an open-source agentic coding model from Moonshot AI designed for developers, engineering teams, and AI coding workflows that require long-context understanding and multi-step execution. It is built for real-world software engineering tasks, including code generation, code review, debugging, repository navigation, tool use, and long-horizon development work. The model is described by Moonshot AI as a coding-focused agentic model with stronger performance on complex coding tasks than earlier Kimi K2 releases. Kimi K2.7 Code supports a 256K context window, allowing it to process large codebases, technical requirements, logs, documentation, and multi-file development context in a single workflow. It is available through Kimi Code, which provides developer-oriented tools for using the model in coding tasks. The model can also be accessed through Moonshot’s API platform, where Kimi K2.7 Code and Kimi K2.7 Code Highspeed are offered alongside earlier Kimi models. For developers who want more control, Kimi K2.7 Code is listed on Hugging Face with deployment support for inference engines such as vLLM, SGLang, and KTransformers. It uses OpenAI- and Anthropic-compatible API options, helping teams connect it to existing applications, coding tools, and agent systems more easily. Third-party model listings describe it as using a 1T-parameter mixture-of-experts architecture with 32B active parameters, native INT4 quantization, and reduced thinking-token usage compared with Kimi K2.6. The model is designed to improve efficiency by using fewer reasoning tokens while still supporting demanding programming workflows. Kimi K2.7 Code is a strong fit for developers who want an open, long-context, tool-friendly AI model for software engineering automation and AI-assisted development.

Pi is an efficient terminal coding environment that is built to integrate effortlessly with developers' workflows, allowing them to work naturally rather than having to adapt to its framework. It features solid default configurations while remaining lightweight and offering a wide range of customization possibilities, enabling users to expand Pi through various extensions, skills, prompt templates, themes, and shareable packages from npm or git. When teams need particular commands, tools, providers, workflows, or UI changes, they can easily direct Pi to create these elements, make real-time modifications, refresh, and resume their tasks without any delays. Pi's flexibility is evident in its support for various modes including interactive, print/JSON, RPC, and SDK, allowing it to serve as a full-fledged terminal UI, a programmable command interface, a JSON event stream, or a readily embeddable agent. Additionally, it is compatible with over 15 providers and a multitude of models, such as Anthropic, OpenAI, Google, Azure, Bedrock, Mistral, Groq, Cerebras, xAI, Hugging Face, Kimi For Coding, MiniMax, OpenRouter, Ollama, and more, enabling seamless mid-session model switching that enhances both flexibility and user satisfaction. This versatility makes Pi an essential resource for developers aiming to customize their coding environment precisely according to their preferences and requirements, ultimately fostering a more productive and enjoyable programming experience.

SWE-1.7 is a frontier software engineering model from Cognition built for advanced coding agents and long-horizon development workflows. It is designed to deliver strong coding intelligence at a fraction of the cost of some leading frontier alternatives, improving the cost-performance balance for real software engineering work. The model is trained from a Kimi K2.7 base and further improved through Cognition’s reinforcement learning pipeline, showing that additional post-training can still produce major capability gains. SWE-1.7 is optimized for tasks such as bug fixing, feature implementation, code migrations, terminal-based workflows, multilingual software engineering, large codebase navigation, and end-to-end validation. It performs especially well on longer asynchronous tasks where an AI agent needs to gather context, inspect files, test hypotheses, make changes, and verify results over an extended period. Cognition trained the model with infrastructure improvements that preserve entropy, stabilize training, support multi-cluster reinforcement learning, and improve fault tolerance across large distributed runs. The training process also focused heavily on data quality, using automated execution tests, verifier quality checks, reward-hacking prevention, and task filtering to create stronger learning signals. SWE-1.7 includes self-compaction, allowing it to summarize its working state and continue long projects even when tasks exceed the raw context window. It also uses an alternating length penalty to encourage concise reasoning on easier tasks while maintaining deeper exploration when a problem requires it. In practice, the model tends to explore codebases carefully, read relevant files, search for hidden requirements, test edge cases, and experiment before deciding how to implement a fix. Available in Devin across web, desktop, and CLI via Cerebras, SWE-1.7 gives engineering teams a powerful model for running scalable, cost-efficient coding agents.

Kimi K2.6 is a cutting-edge agentic AI model developed by Moonshot AI, designed to improve practical application, programming efficiency, and complex reasoning abilities beyond its forerunners, K2 and K2.5. Utilizing a Mixture-of-Experts framework, this model embodies the multimodal, agent-centric principles of the Kimi series, seamlessly combining language understanding, coding skills, and tool application into a unified system capable of planning and executing sophisticated workflows. It boasts advanced reasoning capabilities and superior agent planning, allowing it to break down tasks, coordinate multiple tools, and address challenges involving numerous files or steps with heightened accuracy and efficiency. Furthermore, it excels in tool-calling functions, ensuring a reliable connection with external platforms like web searches or APIs, while incorporating built-in validation systems to confirm the correctness of execution formats. Significantly, Kimi K2.6 marks a transformative advancement in the AI landscape, establishing new benchmarks for the intricacy and dependability of automated processes, and paving the way for future innovations in the field.

omp (oh my pi) is an open-source AI coding agent and developer platform created to provide a deeply integrated environment for AI-assisted software engineering across local and cloud-based workflows. Rather than functioning as a standalone chatbot, the platform connects AI models directly to code editors, language servers, debuggers, shells, browsers, version control systems, memory stores, and development utilities through a unified toolset. It supports more than 40 AI providers, enabling developers to work with cloud APIs, subscription-based coding models, self-hosted language models, and local AI runtimes from a single interface. The platform includes advanced development features such as structural code editing, AST-based refactoring, integrated debugging through the Debug Adapter Protocol, persistent Python and JavaScript execution environments, browser automation, and semantic code analysis using language server integration. Developers can orchestrate parallel AI subagents, collaborate through encrypted live coding sessions, manage durable project memory, and automate complex engineering workflows without switching between multiple applications. omp introduces specialized technologies such as Hashline content-aware editing, deterministic Snapcompact context compression, time-traveling stream rules, GitHub filesystem integration, workflow orchestration, and intelligent memory management to improve coding quality while reducing AI token consumption. The platform also provides built-in tools for web search, code review, browser control, GitHub operations, image generation, speech synthesis, document handling, and knowledge retrieval within the same development environment. A high-performance native Rust engine powers searching, file operations, syntax analysis, shell execution, image rendering, and workspace management across Windows, macOS, and Linux without relying heavily on external utilities.

MindMac is a cutting-edge macOS application designed to enhance productivity by seamlessly integrating with ChatGPT and various AI models. It supports an extensive range of AI providers, including OpenAI, Azure OpenAI, Google AI with Gemini, Google Gemini Enterprise Agent Platform, Anthropic Claude, OpenRouter, Mistral AI, Cohere, Perplexity, OctoAI, and allows for the use of local LLMs via LMStudio, LocalAI, GPT4All, Ollama, and llama.cpp. The application boasts more than 150 pre-made prompt templates aimed at improving user interaction and offers extensive customization options for OpenAI settings, visual themes, context modes, and keyboard shortcuts. A key feature is its powerful inline mode, which enables users to create content or ask questions directly within any application, thus removing the need for switching between different windows. MindMac also emphasizes user privacy by securely storing API keys within the Mac's Keychain and sending data directly to the AI provider while avoiding intermediary servers. Users can enjoy basic functionalities of the application free of charge, without the need for an account setup. Furthermore, its intuitive interface is designed to be accessible for individuals who may not be familiar with AI technologies, ensuring a smooth experience for all users. This makes MindMac an appealing choice for both seasoned AI enthusiasts and newcomers alike.

Perplexity has introduced an enhanced AI search engine named Sonar, built on the Llama 3.3 70B model. This latest version of Sonar has undergone additional training to increase the precision of information and improve the clarity of responses within Perplexity's standard search functionality. These upgrades aim to offer users answers that are not only accurate but also easier to understand, all while maintaining the platform's well-known speed and efficiency. Moreover, Sonar is equipped with the ability to conduct real-time, extensive web research and provide answers to questions, enabling developers to easily integrate these features into their applications through a lightweight and budget-friendly API. In addition, the Sonar API supports advanced models such as sonar-reasoning-pro and sonar-pro, which are specifically tailored for complex tasks that require deep contextual understanding and retention. These advanced models can provide more detailed answers, resulting in an average of double the citations compared to previous iterations, thereby greatly enhancing the transparency and reliability of the information offered. With these significant advancements, Sonar aims to set a new standard in delivering exceptional search experiences to its users, ensuring they receive the best possible information available.

LiteLLM acts as an all-encompassing platform that streamlines interaction with over 100 Large Language Models (LLMs) through a unified interface. It features a Proxy Server (LLM Gateway) alongside a Python SDK, empowering developers to seamlessly integrate various LLMs into their applications. The Proxy Server adopts a centralized management system that facilitates load balancing, cost monitoring across multiple projects, and guarantees alignment of input/output formats with OpenAI standards. By supporting a diverse array of providers, it enhances operational management through the creation of unique call IDs for each request, which is vital for effective tracking and logging in different systems. Furthermore, developers can take advantage of pre-configured callbacks to log data using various tools, which significantly boosts functionality. For enterprise users, LiteLLM offers an array of advanced features such as Single Sign-On (SSO), extensive user management capabilities, and dedicated support through platforms like Discord and Slack, ensuring businesses have the necessary resources for success. This comprehensive strategy not only heightens operational efficiency but also cultivates a collaborative atmosphere where creativity and innovation can thrive, ultimately leading to better outcomes for all users. Thus, LiteLLM positions itself as a pivotal tool for organizations looking to leverage LLMs effectively in their workflows.

Axolotl is a highly adaptable open-source platform designed to streamline the fine-tuning of various AI models, accommodating a wide range of configurations and architectures. This innovative tool enhances model training by offering support for multiple techniques, including full fine-tuning, LoRA, QLoRA, ReLoRA, and GPTQ. Users can easily customize their settings with simple YAML files or adjustments via the command-line interface, while also having the option to load datasets in numerous formats, whether they are custom-made or pre-tokenized. Axolotl integrates effortlessly with cutting-edge technologies like xFormers, Flash Attention, Liger kernel, RoPE scaling, and multipacking, and it supports both single and multi-GPU setups, utilizing Fully Sharded Data Parallel (FSDP) or DeepSpeed for optimal efficiency. It can function in local environments or cloud setups via Docker, with the added capability to log outcomes and checkpoints across various platforms. Crafted with the end user in mind, Axolotl aims to make the fine-tuning process for AI models not only accessible but also enjoyable and efficient, thereby ensuring that it upholds strong functionality and scalability. Moreover, its focus on user experience cultivates an inviting atmosphere for both developers and researchers, encouraging collaboration and innovation within the community.

Mastra is a developer-friendly TypeScript framework designed to create advanced AI agents that can perform tasks, manage knowledge bases, and persist memory within workflows. By utilizing TypeScript, Mastra offers a robust solution for building scalable AI agents with full control over task execution, user interactions, and data storage. Developers can create intelligent agents that remember past interactions and make informed decisions based on real-time data, making Mastra a perfect tool for building everything from AI assistants to sophisticated automation systems. Its easy setup, scalability, and powerful integration features ensure efficient development cycles for AI-powered solutions.

Vivgrid is a multifaceted development platform designed specifically for AI agents, emphasizing essential features like observability, debugging, safety, and a strong global deployment system. It ensures complete visibility into the activities of agents by meticulously logging prompts, memory accesses, tool interactions, and reasoning steps, which helps developers pinpoint and rectify any potential failures or anomalies in behavior. In addition, the platform supports the rigorous testing and implementation of safety measures, such as refusal protocols and content filters, while promoting human oversight prior to the deployment phase. Moreover, Vivgrid adeptly manages the coordination of multi-agent systems that utilize stateful memory, efficiently assigning tasks across various agent workflows as needed. On the deployment side, it leverages a worldwide distributed inference network to provide low-latency performance, consistently achieving response times below 50 milliseconds, and supplying real-time data on latency, costs, and usage metrics. By combining debugging, evaluation, safety, and deployment into a unified framework, Vivgrid seeks to simplify the delivery of resilient AI systems, eliminating the reliance on various separate components for observability, infrastructure, and orchestration. This integrated strategy not only enhances developer efficiency but also allows teams to concentrate on driving innovation rather than grappling with the challenges of system integration. Ultimately, Vivgrid represents a significant advancement in the development landscape for AI technologies.

Rebolt is an advanced AI platform designed specifically for enterprises, enabling businesses to create customized applications and intelligent agents simply by providing verbal instructions to the AI. It effortlessly integrates with a variety of corporate tools such as OneDrive, SharePoint, Salesforce, and Slack, along with custom APIs, and encompasses vital infrastructure components such as databases, file storage, scheduling options (including cron jobs), audit logs, and distinct environments for staging and production. Users can craft applications and agents without the need for API key programming, simply by expressing their needs in natural language while maintaining strong enterprise security measures, including permissions mapping via systems like Azure groups and role-based access controls. This platform is meticulously developed for building operational workflows, internal tools, and automation that connect seamlessly to the organization's existing data and services, thus enabling non-technical users or low-code teams to swiftly develop solutions that can substitute for spreadsheets, tedious manual tasks, and fragmented SaaS applications. Furthermore, Rebolt's user-friendly interface promotes enhanced collaboration among teams, driving productivity and fostering innovation across the organization. By streamlining processes and bridging gaps between systems, Rebolt not only simplifies the development of new tools but also empowers teams to work more efficiently and creatively.

Zo Computer is a next-generation AI companion that functions as your own private cloud computer. Unlike typical AI apps, Zo actively runs tasks, builds automations, and manages workflows around the clock. It can research the web, organize files, convert documents, manage reminders, and even host servers or applications. Zo brings together AI models, data, and compute in a single environment you fully control. Powered by a Linux-based backend, it allows advanced users to self-host tools while remaining simple enough for non-technical users. You can interact with Zo via text or app, making complex tasks feel effortless. The platform supports multiple leading AI models, including language, image, audio, and video generation. Zo continuously learns from your context to deliver more relevant results over time. It’s designed to replace scattered tools with one unified, intelligent system. Zo turns AI into an always-on builder, not just a chatbot.

Anuma is a cutting-edge AI platform that emphasizes user privacy while bringing together access to both proprietary and open-source AI systems through an intuitive interface that guarantees full ownership and control over personal information. Users can effortlessly interact with a variety of models, such as ChatGPT, Claude, Gemini, Grok, and open-source alternatives like DeepSeek or Qwen, all within one platform, eliminating the hassle of switching tools and retaining contextual continuity, which streamlines workflows across different AI technologies. Central to the platform is a Private Memory Layer that securely holds user preferences, conversation logs, and contextual details in an encrypted format under the user's control, effectively blocking any unauthorized access to sensitive information. This memory feature is designed to be persistent across multiple sessions and various AI models, allowing users to continue from where they left off without needing to repeat previous information, which significantly improves continuity in complex workflows. Anuma also empowers users to compare multiple models side by side, alongside the flexibility to develop custom mini-applications and automate processes without any coding knowledge required. As a result, users can experience heightened efficiency and a more personalized approach to their interactions with AI technologies, making Anuma a valuable tool for anyone seeking to optimize their use of artificial intelligence. Moreover, this platform not only enhances productivity but also fosters creativity by enabling users to tailor their experiences according to their specific needs and preferences.

AI Workers are autonomous agents designed specifically for your organization, functioning as true team members rather than just simple chatbots waiting for commands. Each of these sophisticated AI units possesses a unique professional identity, complete with an email address, phone number, and profiles on communication platforms such as Slack and Teams, showcasing their proactive nature and ability to operate continuously without direct prompts. Rather than requiring exhaustive instructions for their tasks, you only need to outline your goals, allowing them to independently create the necessary workflows to tackle various responsibilities, including generating daily reports, conducting weekly follow-ups, updating CRM systems, managing client relations, performing research, overseeing content production, handling financial duties, coordinating HR tasks, supporting design initiatives, and assisting in development processes. This framework comprises a wide array of specialized AI Workers, each tailored for specific functions in fields such as marketing, development, design, HR, and finance, ensuring practical application in their designated roles. Additionally, they can effortlessly integrate with over 3,000 different tools, including Slack, Microsoft Teams, Gmail, Notion, HubSpot, Salesforce, and many other business applications, making them a seamless addition to your existing operational workflows. Their remarkable versatility and adaptability significantly enhance productivity and streamline processes, making them essential assets in any business setting, and their ongoing development promises even more innovative solutions in the future.

Flo2 acts as both a gateway and a router, linking users to top-tier AI model providers like OpenAI, Anthropic, Groq, Cerebras, and DeepInfra through a single, cohesive API that aligns with OpenAI's standards. By leveraging intelligent routing capabilities, it efficiently identifies the most economical or fastest model for each request. Ensuring reliability, automatic fallback features uphold application performance even during provider outages. The racing mode function allows for the concurrent processing of requests across different providers, significantly boosting efficiency. Users can track costs comprehensively, with detailed breakdowns available for each request, model, and project. Developers can also integrate their own provider keys on flo2.com, and the testing tier from RapidAPI provides free tokens for initial assessments. This streamlined integration is designed to facilitate the development process while optimizing performance and reducing costs, ultimately enhancing user experience. Furthermore, Flo2's capabilities foster innovation by allowing developers to experiment with various models effortlessly.

Mercury 2 signifies a revolutionary leap in reasoning models, particularly tailored for instantaneous voice interactions, as it can promptly respond to incoming calls. In contrast to conventional autoregressive models that often leave callers waiting in silence while they generate responses sequentially, Mercury 2 uses a diffusion large language model architecture that can produce more than 1000 tokens per second on standard NVIDIA GPUs. This extraordinary processing speed enables it to finalize a complete reasoning cycle and start speaking in a timeframe that harmonizes with the natural flow of conversation, effectively reducing the usual wait time from several seconds to around 300 milliseconds. The functionality of Mercury models revolves around converting clear text into noise, after which a traditional Transformer is trained to reverse this process and predict the original text simultaneously across all positions. By adopting a denoising strategy that processes multiple tokens concurrently, the generation process becomes more efficient, achieving speeds comparable to customized silicon on NVIDIA H100s while enhancing responsiveness in voice applications. Consequently, Mercury 2 not only improves user interactions but also establishes a new benchmark for the field of interactive voice technology, paving the way for future advancements. With its innovative design, it promises to revolutionize the way users engage with voice systems.

Our cutting-edge storage solutions are adept at handling millions of small, random files, which is essential for optimizing GPU-based training servers and significantly enhancing the training speed. We offer high-bandwidth and low-latency networking options that ensure smooth connectivity between distributed training servers and facilitate efficient data transfer from storage to those servers. In contrast to other cloud service providers that charge extra for data access—costs that can add up quickly—we aim to be a collaborative partner in your operations. By working together, we help implement scheduling services, provide expert guidance on best practices, and offer outstanding support tailored specifically to your requirements. Understanding that every organization has its own workflow dynamics, Cirrascale is dedicated to delivering the most effective solutions for achieving your goals. Uniquely, we are the sole provider that works intimately with you to customize your cloud instances, thereby boosting performance, removing bottlenecks, and optimizing your processes. Furthermore, our cloud solutions are strategically designed to enhance your training, simulation, and re-simulation efforts, leading to swifter results. By focusing on your specific needs, Cirrascale enables you to maximize both your operational efficiency and effectiveness in cloud environments, ultimately driving greater success in your projects. Our commitment to your success ensures that you are not just another client, but a valued partner in our journey together.

Witsy is a versatile desktop application that provides users with access to a wide variety of generative AI models from top AI providers, serving as a one-stop solution for all generative AI needs. Designed as a BYOK (Bring Your Own Keys) application, Witsy requires users to supply their own API keys for the LLM providers they wish to engage with. Additionally, users can choose to utilize Ollama to run models locally at no charge and seamlessly incorporate them into Witsy. A key aspect of Witsy's design is its commitment to user privacy; it does not collect or process any personal information, ensuring that all data remains securely on the user's device. Furthermore, the application avoids using cookies or any tracking mechanisms, which adds an extra layer of protection for user privacy. All features within Witsy are accessible via convenient keyboard shortcuts, allowing users to easily start chats, use the scratchpad, execute commands, and perform other tasks efficiently. Users also have the ability to customize these shortcuts according to their personal preferences, enhancing their interaction with the application. Another beneficial feature is the capability to engage with the AI model in the scratchpad, which streamlines the document creation process. This unique approach fosters a collaborative environment, enabling users to work with AI as though they are partnering with a colleague, ultimately making Witsy an essential asset for boosting productivity and creativity. As a result, Witsy stands out in the market as a user-friendly tool that adapts to individual workflows and enhances overall efficiency.