Cerebras Integrations

StackAI is an enterprise AI automation platform to build end-to-end internal tools and processes with AI agents in a fully compliant and secure way. Designed for large organizations, it enables teams to automate complex workflows across operations, compliance, finance, IT, and support without heavy engineering. With StackAI you can: • Connect knowledge bases (SharePoint, Confluence, Notion, Google Drive, databases) with versioning, citations, and access controls. • Deploy AI agents as chat assistants, advanced forms, or APIs integrated into Slack, Teams, Salesforce, HubSpot, or ServiceNow. • Govern usage with enterprise security: SSO (Okta, Azure AD, Google), RBAC, audit logs, PII masking, data residency, and cost controls. • Route across OpenAI, Anthropic, Google, or local LLMs with guardrails, evaluations, and testing. • Start fast with templates for Contract Analyzer, Support Desk, RFP Response, Investment Memo Generator, and more.

SweKit let’s you build PR agents to review code, suggest improvements, enforce coding standards, identify potential issues, automate merge approvals, and provide feedback on best practices, streamlining the review process and enhancing code quality. Automate writing new features, debug complex issues, create and run tests, optimize code for performance, refactor for maintainability, and ensure best practices across the codebase, accelerating development and efficiency. Use highly optimized code analysis, advanced code indexing, and intelligent file navigation tools to explore and interact with large codebases effortlessly. Ask questions, trace dependencies, uncover logic flows, and gain instant insights, enabling seamless communication with complex code structures. Keep your documentation in sync with your code. Automatically update Mintlify documentation whenever changes are made to the codebase, ensuring that your docs stay accurate, up-to-date, and ready for your team and users.

MindMac is a native macOS application designed to enhance productivity by integrating seamlessly with ChatGPT and other AI models. It supports multiple AI providers, including OpenAI, Azure OpenAI, Google AI with Gemini, Google Cloud Vertex AI with Gemini, Anthropic Claude, OpenRouter, Mistral AI, Cohere, Perplexity, OctoAI, and local LLMs via LMStudio, LocalAI, GPT4All, Ollama, and llama.cpp. MindMac offers over 150 built-in prompt templates to facilitate user interaction and allows for extensive customization of OpenAI parameters, appearance, context modes, and keyboard shortcuts. The application features a powerful inline mode, enabling users to generate content or ask questions within any application without switching windows. MindMac ensures privacy by storing API keys securely in the Mac's Keychain and sending data directly to the AI provider without intermediary servers. The app is free to use with basic features, requiring no account for setup.

Perplexity has recently introduced an enhanced version of its AI search engine, named Sonar. Built upon the Llama 3.3 70B model, Sonar has undergone additional training to improve the factual accuracy and readability of responses in Perplexity's default search mode. This advancement aims to deliver users more precise and comprehensible answers while maintaining the platform's characteristic efficiency and speed. Sonar also provides real-time, web-wide research and Q&A capabilities, allowing developers to integrate these features into their products through a lightweight, cost-effective, and user-friendly API. The Sonar API supports advanced models like sonar-reasoning-pro and sonar-pro, designed for complex tasks requiring deep understanding and context retention. These models offer detailed answers with an average of twice as many citations as previous versions, enhancing the transparency and reliability of the information provided.

​LiteLLM is a versatile platform designed to streamline interactions with over 100 Large Language Models (LLMs) through a unified interface. It offers both a Proxy Server (LLM Gateway) and a Python SDK, enabling developers to integrate various LLMs seamlessly into their applications. The Proxy Server facilitates centralized management, allowing for load balancing, cost tracking across projects, and consistent input/output formatting compatible with OpenAI standards. This setup supports multiple providers. It ensures robust observability by generating unique call IDs for each request, aiding in precise tracking and logging across systems. Developers can leverage pre-defined callbacks to log data using various tools. For enterprise users, LiteLLM offers advanced features like Single Sign-On (SSO), user management, and professional support through dedicated channels like Discord and Slack.

​Axolotl is an open source tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures. It enables users to train models, supporting methods like full fine-tuning, LoRA, QLoRA, ReLoRA, and GPTQ. Users can customize configurations using simple YAML files or command-line interface overrides, and load different dataset formats, including custom or pre-tokenized datasets. Axolotl integrates with technologies like xFormers, Flash Attention, Liger kernel, RoPE scaling, and multipacking, and works with single or multiple GPUs via Fully Sharded Data Parallel (FSDP) or DeepSpeed. It can be run locally or on the cloud using Docker and supports logging results and checkpoints to several platforms. It is designed to make fine-tuning AI models friendly, fast, and fun, without sacrificing functionality or scale.

Mastra is a powerful TypeScript framework for building intelligent AI agents that can execute tasks, access knowledge bases, and maintain memory persistently within workflows. This framework simplifies the process of creating and deploying AI-powered agents by leveraging TypeScript’s capabilities to streamline development. With features like customizable agent instructions, memory, and task orchestration, Mastra provides developers with the tools to build and scale AI agents for various applications, from personal assistants to specialized domain experts.

Vivgrid is a development platform for AI agents that emphasizes observability, debugging, safety, and global deployment infrastructure. It gives you full visibility into agent behavior, logging prompts, memory fetches, tool usage, and reasoning chains, letting developers trace where things break or deviate. You can test, evaluate, and enforce safety policies (like refusal rules or filters), and incorporate human-in-the-loop checks before going live. Vivgrid supports the orchestration of multi-agent systems with stateful memory, routing tasks dynamically across agent workflows. On the deployment side, it operates a globally distributed inference network to ensure low-latency (sub-50 ms) execution and exposes metrics like latency, cost, and usage in real time. It aims to simplify shipping resilient AI systems by combining debugging, evaluation, safety, and deployment into one stack, so you're not stitching together observability, infrastructure, and orchestration.

Rebolt is an enterprise-grade AI platform that empowers companies to build custom applications and intelligent agents simply by speaking with AI. The platform integrates seamlessly with corporate tools such as OneDrive, SharePoint, Salesforce, Slack, and custom APIs, offering built-in infrastructure like databases, file storage, scheduling (cron jobs), audit logs, and distinct staging and production environments for deployment. Users can create apps and agents without writing API key code by simply describing what they need in natural language, while maintaining enterprise-class security, permissions mapping (e.g., via Azure groups), and role-based access. Rebolt is designed for building operational workflows, internal tools, and automation that connect to existing company data and services, enabling non-technical users (or low-code teams) to rapidly assemble solutions and replace spreadsheets, manual processes, and fragmented SaaS stacks.

AI Crypto-Kit empowers developers to build crypto agents by seamlessly integrating leading Web3 platforms like Coinbase, OpenSea, and more to automate real-world crypto/DeFi workflows. Developers can build AI-powered crypto automation in minutes, including applications such as trading agents, community reward systems, Coinbase wallet management, portfolio tracking, market analysis, and yield farming. The platform offers capabilities engineered for crypto agents, including fully managed agent authentication with support for OAuth, API keys, JWT, and automatic token refresh; optimization for LLM function calling to ensure enterprise-grade reliability; support for over 20 agentic frameworks like Pippin, LangChain, and LlamaIndex; integration with more than 30 Web3 platforms, including Binance, Aave, OpenSea, and Chainlink; and SDKs and APIs for agentic app interactions, available in Python and TypeScript.

Our high-throughput storage systems can serve millions of small, random files to GPU-based training servers accelerating overall training times. We offer high-bandwidth, low-latency networks for connecting distributed training servers as well as transporting data between storage and servers. Other cloud providers squeeze you with extra fees and charges to get your data out of their storage clouds, and those can add up fast. We consider ourselves an extension of your team. We work with you to set up scheduling services, help with best practices, and provide superior support. Workflows can vary from company to company. Cirrascale works to ensure you get the right solution for your needs to get you the best results. Cirrascale is the only provider that works with you to tailor your cloud instances to increase performance, remove bottlenecks, and optimize your workflow. Cloud-based solutions to accelerate your training, simulation, and re-simulation time.

Witsy is a desktop application that provides access to all generative AI models from top AI providers. It is a one-stop solution for all your generative AI needs. Witsy is a BYOK (Bring Your Own Keys) AI application, meaning you need to have API keys for the LLM providers you want to use. Alternatively, you can use Ollama to run models locally on your machine for free and use them in Witsy. Witsy itself does not collect or process any personal data. All your data is kept on your computer and never leaves it. Witsy does not use cookies or any other tracking mechanisms. All features of Witsy are accessible through keyboard shortcuts. You can trigger the chat or scratchpad, execute commands, and more. You can also customize the shortcuts to fit your needs. You can also talk to the AI model in the scratchpad for the ultimate document creation experience. Work with Witsy as if you were collaborating with a peer.