# Heroku AI Heroku AI is an AI platform as a service for building, deploying, and scaling AI-powered applications, with managed inference, agents, and MCP support. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Heroku AI adds a flexible standard plan and expands its managed model catalog DevFeed: [Heroku AI adds a flexible standard plan and expands its managed model catalog]() Original publisher: [Read original article]() Author: Anush DSouza Published: 2026-02-19T17:08:20Z Content type: release Language: en Sources: [Heroku]() Topics: [Heroku AI](), [Heroku](), [model-deployment](), [Claude](), [deepseek](), [cohere]() Tags: [claude](), [cohere](), [deepseek](), [deployment](), [heroku](), [heroku-ai](), [inference](), [managed-inference-and-agents](), [models](), [news](), [updates]() ### AI overview Heroku introduces a standard plan for Managed Inference and Agents that lets developers access supported models through one add-on and API key, while adding Claude 4.6, new open-weight models, and Cohere Embed V4. ### Source excerpt Heroku is introducing significant updates to Managed Inference and Agents. These changes focus on reducing developer friction, expanding model catalogue, and streamlining deployment workflows. More flexibility with the new standard plan Until now, Heroku's model-based plans required developers to provision a specific add-on for a specific model. This created significant operational overhead. If you wanted [...] The post Whats New in Heroku AI: New Models and a Flexible Standard Plan appeared first on Heroku. ## Heroku Introduces New Innovations to Expand the Capabilities of Every Salesforce Org DevFeed: [Heroku Introduces New Innovations to Expand the Capabilities of Every Salesforce Org]() Original publisher: [Read original article]() Author: Betty Junod Published: 2025-10-14T15:05:55Z Content type: release Language: en Sources: [Heroku]() Topics: [Heroku](), [Heroku AI](), [Cloud](), [Artificial Intelligence](), [Development](), [Automation](), [Security]() Tags: [ai](), [announcement](), [applink](), [cloud](), [cloud-native](), [deployment](), [developers](), [heroku](), [heroku-ai](), [news](), [salesforce](), [security](), [services](), [work]() ### AI overview Heroku announces new innovations for its AI PaaS at Dreamforce, covering expanded pro-code and elastic compute, data foundation enhancements, and AI-assisted application building. The announcement also details AppLink improvements including JWT authentication, higher invocation throughput, and OpenAPI-based automation. ### Source excerpt Today's businesses face a tremendous amount of complexity in tools, data silos, and systems that teams need to navigate to deliver unique and engaging experiences to their customers. Meanwhile developers are only able to spend a fraction of their time coding due to the cognitive load of technology complexity, constant context switching, and figuring out how to adopt AI effectively into their daily work. The Heroku AI PaaS is the Cloud Native Application Platform from Salesforce to seamlessly build and scale any custom service for greenfield app development, modernizing existing apps, and as part of a Salesforce cloud implementation. At Dreamforce, we are excited to introduce new innovations to our AI PaaS that expand the capabilities of every Salesforce org and empower new builders. Today's announcement includes innovations in three key areas: Expanding the capabilities of every Salesforce org with the flexibility of more pro-code and elastic compute with enterprise performance, scale and security enhancements. Enhancing and expanding the data foundation to empower our customers' modern and AI app strategies. Delivering new vibes using AI to make the process of building new applications as accessible as sending a text message. The post Heroku Introduces New Innovations to Expand the Capabilities of Every Salesforce Org appeared first on Heroku. ## Heroku AI Studio for Managed Inference and Agents DevFeed: [Heroku AI Studio for Managed Inference and Agents]() Original publisher: [Read original article]() Author: Anush DSouza Published: 2025-09-17T15:00:12Z Content type: release Language: en Sources: [Heroku]() Topics: [Heroku AI](), [AI Development](), [Heroku](), [Generative AI](), [Inference]() Tags: [ai](), [ai-studio](), [generative-ai](), [heroku](), [heroku-ai](), [managed-inference-and-agents](), [news](), [product-features]() ### AI overview Heroku introduces AI Studio, an interactive workspace for its Managed Inference and Agents add-on. It lets developers experiment with provisioned models and tools, refine prompts, and use code-integration guidance. ### Source excerpt Ever found yourself in the endless loop of tweaking a prompt, running your code, and waiting to see if you finally got the output you wanted? That slow, frustrating feedback cycle is a common headache for AI developers. What if you could speed that up and get back to what you do best? Let's focus on building amazing applications. We're excited to introduce Heroku AI Studio, a new set of tools designed to streamline your generative AI development from prompt to production. We've focused on creating a more intuitive and efficient workflow, so you can focus on innovation instead of wrestling with your development environment. When using the Heroku Managed Inference and Agents add-on, this new tool is about to become an essential part of your workflow. The post Heroku AI Studio is Your Workspace for Smarter, Faster AI Apps appeared first on Heroku. ## Heroku AI PaaS capabilities and customer examples featured at Dreamforce 2025 DevFeed: [Heroku AI PaaS capabilities and customer examples featured at Dreamforce 2025]() Original publisher: [Read original article]() Author: Lauren Groccia Published: 2025-09-04T15:00:12Z Content type: article Language: en Sources: [Heroku]() Topics: [Heroku](), [Heroku AI](), [Artificial Intelligence](), [MCP](), [Automation](), [Model Context Protocol (MCP)]() Tags: [2025](), [agentforce](), [ai](), [applink](), [automation](), [development](), [events](), [heroku](), [heroku-ai](), [managed-inference-and-agents](), [mcp-on-heroku](), [news](), [platform-updates]() ### AI overview This promotional Dreamforce 2025 guide presents Heroku's evolution from a traditional PaaS to an AI PaaS. It highlights AppLink, Managed Inference and Agents, and MCP on Heroku, along with customer examples involving automation, support, lead delivery, Slack apps, and DevOps. ### Source excerpt The AI revolution presents a critical challenge: moving from experimentation to production. This year, Heroku has evolved beyond a traditional PaaS to become an AI PaaS, a fully managed platform designed to solve this problem and accelerate the delivery of AI-powered apps. With new capabilities like AppLink, Managed Inference and Agents, and MCP on Heroku, Heroku now provides a fully managed platform designed for the AI era. This evolution accelerates the delivery of AI-powered apps and intelligent agents, bringing a new level of speed and simplicity to your development process. Dreamforce 2025 is your chance to see firsthand how the Heroku AI PaaS is delivering business value faster and with less complexity. The post Discover How Heroku's AI PaaS Delivers Real-World Results at Dreamforce appeared first on Heroku. ## Heroku AI Expands Model Offering with OpenAI's gpt-oss-120b DevFeed: [Heroku AI Expands Model Offering with OpenAI's gpt-oss-120b]() Original publisher: [Read original article]() Author: Anush DSouza Published: 2025-08-20T15:00:14Z Content type: release Language: en Sources: [Heroku]() Topics: [Heroku AI](), [gpt-oss](), [OpenAI](), [Heroku](), [API](), [Mixture of Experts (MoE)](), [SDKs](), [Open Source Models & Datasets]() Tags: [agents](), [ai](), [ai-infrastructure](), [ai-machine-learning](), [api](), [deploy](), [engineering](), [function-calling](), [gpt-oss](), [heroku](), [heroku-ai](), [managed-inference-and-agents](), [mixture-of-experts-moe](), [open-source](), [openai](), [python](), [sdk]() ### AI overview Heroku announces that OpenAI's open-weight gpt-oss-120b model is available through Heroku Managed Inference and Agents. Developers can access it through an OpenAI-compatible chat completions API and use it to build and deploy AI applications and agentic workflows. ### Source excerpt Start building with OpenAI's new open-weight model, gpt-oss-120b, now available on Heroku Managed Inference and Agents. This gives developers a powerful, transparent, and flexible way to build and deploy AI applications on the platform they already trust. Access gpt-oss-120b with our OpenAI-compatible chat completions API, which you can drop into any OpenAI-compatible SDK or framework. [...] The post Heroku AI Expands Model Offering with OpenAI's gpt-oss-120b appeared first on Heroku. ## Introducing the Heroku AI Platform as a Service (AI PaaS) DevFeed: [Introducing the Heroku AI Platform as a Service (AI PaaS)]() Original publisher: [Read original article]() Author: Betty Junod Published: 2025-06-26T15:00:05Z Content type: release Language: en Sources: [Heroku]() Topics: [Heroku AI](), [Heroku](), [AI Platform](), [Artificial Intelligence](), [MCP](), [cursor](), [Large Language Model]() Tags: [agents](), [ai](), [claude-code](), [cursor](), [heroku](), [heroku-ai](), [llms](), [managed-inference-and-agents](), [mcp](), [mcp-on-heroku](), [mcp-server](), [news](), [partners](), [platform](), [platform-updates]() ### AI overview Heroku announces its evolution into an AI Platform as a Service, adding AI capabilities to its cloud platform. The announcement describes Heroku AppLink, integrations with Cursor, Windsurf, and Claude Code, and tools for building and running MCP servers. ### Source excerpt Today, we are pleased to announce the evolution of Heroku to an AI Platform as a Service (AI PaaS). GenAI has changed how we build software (vibe coding), the kind of technology we use (Cursor, LLMs), the type of software we make (agents), and redefined what it means to be a developer in this new [...] The post Introducing the Heroku AI Platform as a Service (AI PaaS) appeared first on Heroku. ## Heroku AI: Heroku Remote MCP Server DevFeed: [Heroku AI: Heroku Remote MCP Server]() Original publisher: [Read original article]() Author: Anush DSouza Published: 2025-06-24T22:47:09Z Content type: release Language: en Sources: [Heroku]() Topics: [Heroku](), [MCP Server](), [Heroku AI](), [Model Context Protocol (MCP)](), [OAuth 2.0](), [Authentication](), [Claude](), [cursor](), [Visual Studio Code]() Tags: [agentforce](), [ai](), [authentication](), [claude](), [cursor](), [developer-tools](), [heroku](), [heroku-ai](), [mcp](), [mcp-on-heroku](), [mcp-server](), [news](), [oauth](), [oauth-2-0](), [remote-mcp-server](), [visual-studio-code]() ### AI overview Heroku introduces the Heroku Remote MCP Server, extending its earlier stdio-based server with remote access and OAuth 2.0 authentication. The article explains how agents and clients such as Claude, Agentforce, Cursor, and Visual Studio Code can connect to Heroku and use platform tools. ### Source excerpt Developers can easily scale how autonomous agents interact with infrastructure using the Heroku Remote MCP Server at https://mcp.heroku.com/mcp. This new remote server expands our earlier stdio-based MCP server and comes with secure OAuth authentication. It's provides a secure, scalable, and incredibly simple way for agents to interact with the Heroku platform and use tools to [...] The post Heroku AI: Heroku Remote MCP Server appeared first on Heroku. ## Heroku AI: Managed Inference and Agents is now Generally Available DevFeed: [Heroku AI: Managed Inference and Agents is now Generally Available]() Original publisher: [Read original article]() Author: Anush DSouza Published: 2025-05-15T16:00:48Z Content type: release Language: en Sources: [Heroku]() Topics: [Heroku AI](), [Heroku](), [Inference](), [AI Infrastructure](), [Model Context Protocol]() Tags: [agents](), [ai](), [ai-infrastructure](), [developer-tools](), [heroku-ai](), [inference](), [managed-inference-and-agents](), [mcp-on-heroku](), [model-context-protocol](), [news]() ### AI overview Heroku AI: Managed Inference and Agents is generally available. The release provides ready-to-use access to curated AI models and primitives for building agents that can reason, act, call tools, and support AI-powered features in Heroku applications. ### Source excerpt Many of the most exciting experiences we're beginning to rely on every day are powered by AI; whether it's conversational assistants, personalized recommendations or code generation, these experiences are powered by inference systems and intelligent agents. Behind the scenes, developers offload complex decisions, automate tasks, and compose intelligent applications using large language models and tool [...] The post Heroku AI: Managed Inference and Agents is now Generally Available appeared first on Heroku. ## How I Improved My Productivity with Cursor and the Heroku MCP Server DevFeed: [How I Improved My Productivity with Cursor and the Heroku MCP Server]() Original publisher: [Read original article]() Author: Julián Duque Published: 2025-05-05T08:00:12Z Content type: tutorial Language: en Sources: [Heroku]() Topics: [cursor](), [Model Context Protocol (MCP)](), [Heroku](), [Heroku AI](), [JavaScript](), [Front end](), [Back end]() Tags: [ai](), [backend](), [coding](), [cursor](), [developer-tools](), [engineering](), [front-end](), [heroku](), [heroku-ai](), [javascript](), [mcp-on-heroku](), [model-context-protocol](), [model-context-protocol-mcp]() ### AI overview The article describes how the author uses Cursor with the Heroku MCP Server to deploy and scale applications from within the code editor. It explains MCP's client-server model and how it connects AI assistants to external tools and data sources. ### Source excerpt Generative AI has been one incredible tool to improve my productivity not only for work but for personal projects too. I use it every day, from generating stories and images for my online role playing games to solving code and engineering problems and building awesome demos. Lately I've leaned into Cursor as my go-to AI [...] The post How I Improved My Productivity with Cursor and the Heroku MCP Server appeared first on Heroku.