Scale Faster with Managed Weaviate: Now in Public Preview on DigitalOcean
Managed Weaviate is now in public preview on DigitalOcean, offering an easy way for developers to run Weaviate in production, at a price that makes sense from day one.
DigitalOcean Blog
@digitalocean-blog
Publisher
100
Posts
Posts by DigitalOcean Blog
Built for Mass Scale: Hard-Won Lessons from Teams Running High Volume Inference Workloads in Production
Learn hard-won lessons on scaling AI inference from industry leaders. Discover insights on infrastructure, latency, and agent governance for production scale.
DigitalOcean Evaluations: Production Model and Router Testing for the Inference Stack
Run LLM-as-a-Judge evaluations directly on your production inference endpoints. Compare models, custom rubrics, and datasets in one integrated platform alongside DigitalOcean Inference.
Run Codex in the cloud – DigitalOcean for Codex is now available
Spin up a persistent, Codex-ready cloud machine in your own DigitalOcean account in one prompt. No manual setup. DigitalOcean for Codex.
Server-Side Tools Are Now Available for DigitalOcean Inference Engine
Learn how Server-Side Tools, now in Public Preview, for DigitalOcean Inference enables web search, knowledge bases, MCP servers, and more.
The Inference Alpha: Maximizing Frontier Models on AMD
Helping millions of developers easily build, test, manage, and scale applications of any size - faster than ever before.
What We Learned Hiring 33 Engineers in Two Weeks
Learn how we replaced the standard interview loop with a three-hour build session and made offers within 24 hours.
Model Evaluations: Prove Your Routing Policy Actually Works
Use DigitalOcean Model Evaluations to benchmark accuracy, latency, and cost across models and routers before changing your production inference stack.
The Team Behind Deploy: Shipping AI, the DigitalOcean Way
Meet three DigitalOcean employees who helped run Deploy 2026 and launch the AI-Native Cloud, from event production to the Inference Router demoed on stage.
Powering the Inference Era: Inside the DigitalOcean Data & Learning Layer
The DigitalOcean Data & Learning layer offers structured, vector, and retrieval layers that work together in the same ecosystem.
Open by Design: How NVIDIA and DigitalOcean Are Building the Stack for the Always-On Agentic Era
At DigitalOcean Deploy 2026, DigitalOcean and NVIDIA discussed industry trends in open-source AI and how developers can run agentic AI.
The Inference Tax: How Prefix-Aware Routing Eliminates the Hidden Cost of LLMs at Scale
vLLM prefix caching and prefix-aware KV cache routing eliminate redundant LLM prefill costs at scale. Learn how DigitalOcean Serverless Inference reduces GPU compute waste by up to 4x on the same hardware.
DigitalOcean Serverless Inference: A Deep Dive
A deep dive into DigitalOcean Serverless Inference—how we built a scalable, API-first AI inference platform and the architecture powering it.
AI Disruptors: How the Next Generation of Business is Being Built
The founders from Andi AI, Higgsfield AI, LawVo, and Probably share what it takes to build in the agentic era: reliability, human oversight, and solving problems that actually matter.
OpenCode Now Supports DigitalOcean Inference Router for Intelligent Model Routing
DigitalOcean Inference Router, now in Public Preview, was built to solve this problem by dynamically routing requests to the right model for the job. As part of DigitalOcean’s AI-Native Cloud, it gives developers a unified way to control, optimize, and evaluate AI inference across models. And as...
Scalable, Cost-Efficient AI: Introducing Unified Batch Inference on DigitalOcean
Process high-volume AI workloads asynchronously with DigitalOcean Batch Inference. Reduce inference costs by up to 50% using OpenAI and Anthropic models through one unified API.
Request-Based Autoscaling Is Now Generally Available on App Platform
Request-based autoscaling on DigitalOcean App Platform is now generally available. Apps can now automatically scale based on live HTTP traffic signals (requests per second and P95 response latency) so your infrastructure reacts in real-time.
How We Built DigitalOcean Inference Router
Inside DigitalOcean's Inference Router—how we use purpose-built models and live metrics to route LLM requests to the right model, fast.
Your Model Doesn't Matter. Your Infrastructure Does.
Learn why your AI infrastructure matters more than your model and how DigitalOcean helps you scale without switching providers.
Powering the Inference Era: Inside the DigitalOcean AI-Native Cloud
This week at Deploy 2026, we launched the DigitalOcean AI-Native Cloud, a purpose-built platform for the inference and agentic era that integrates five layers from silicon to agents into a single open stack.
Introducing DigitalOcean AI-Native Cloud for Production AI Workloads
Today at Deploy 2026, we revealed DigitalOcean’s AI-Native Cloud, a full-stack system for production AI workloads. Our AI-Native Cloud builds on DigitalOcean’s core cloud across compute, storage, networking, and managed services, and extends it with capabilities designed for how AI systems actual...
How we built the most performant DeepSeek V3.2, MiniMax-M2.5 and Qwen 3.5 397B on DigitalOcean Serverless Inference
Today at Deploy, we are announcing the general availability of DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B on DigitalOcean Serverless Inference. On DeepSeek V3.2 and Qwen 3.5 397B, we deliver #1 output speed across all providers Artificial Analysis tested. On DeepSeek V3.2 specifically, that t...
DigitalOcean Dedicated Inference: A Technical Deep Dive
Explore the architecture behind DigitalOcean's Dedicated Inference: managed LLM hosting on dedicated GPUs with VPC endpoints and OpenAI-compatible APIs.
Beyond the Abyss Project Poseidon’s Quest for Zero-Downtime Reliability
Discover how DigitalOcean's Project Poseidon uses ML and GenAI internally to help predict hypervisor failures and evacuate at-risk nodes before they crash.
From Incident Counting to SLIs: How DigitalOcean Rethought Availability
Learn how DigitalOcean replaced incident-based availability tracking with an SLI-driven framework spanning control plane, data plane, and error budgets.
The LLM Inference Trilemma: Throughput, Latency, Cost
Learn how to navigate the three-way tradeoff between throughput, latency, and cost when serving LLMs, with a practical framework for tuning deployments.
Mastering the 600B+ Frontier: Optimizing Large Model Deployments on the Inference Cloud
Learn how high-bandwidth storage helps eliminate the “data tax” on GPU clusters and keeps 600B+ parameter model deployments from stalling on idle silicon.
The Inference Cloud Memory Layer: A Technical Dive into DigitalOcean Managed Databases
DigitalOcean Managed Databases serves as the foundational memory layer for the inference cloud. Learn how offerings from PostgreSQL, MongoDB, and Valkey function as the system of record for today’s stateful AI applications and work with DigitalOcean to support AI applications.
Load Balancing and Scaling LLM Serving
DigitalOcean rethinks load balancing for LLMs with precise prefix cache-aware routing, boosting cache hits, cutting costs, and improving performance at scale.
Building a Robust Documentation Agent with DigitalOcean Gradient AI Platform
Learn how DigitalOcean shipped a production docs agent on Gradient AI Platform using golden datasets, LLM-judged evals, and CI/CD-gated prompt iteration.
Advanced Prompt Caching at Scale
Learn how to scale prompt caching across LLM replicas with session affinity, tiered routing, and prefix-aware load balancing to cut latency and inference costs.
The Hidden Cost of Complex AI Platforms: Why Developer Experience Matters
Discover the hidden costs of complex AI platforms and how poor developer experience slows innovation, increases overhead, and impacts scalability. Learn what to look for instead.
The Glue Problem in Modern AI Development
Learn how fragmented AI infrastructure slows developers, and how a cloud like DigitalOcean reduces complexity and accelerates building apps.
The Agentic Era Demands a New Class of Infrastructure: DigitalOcean Acquires Katanemo Labs
DigitalOcean acquired Katanemo Labs to help developers move AI agents from prototype to production with less infrastructure overhead. By integrating Katanemo Lab’s Plano data plane and observability capabilities, teams can rely on built-in orchestration, execution, and monitoring instead of stitc...
Run Advanced Reasoning on DigitalOcean with Arcee AI's Trinity Large-Thinking
Today, we're announcing that Arcee AI's Trinity Large-Thinking is now available in Public Preview on DigitalOcean's Agentic Inference Cloud, giving developers the ability to run frontier-class reasoning workloads without managing infrastructure or stitching together complex systems.
Now Available: DigitalOcean Cloud Security Posture Management (CSPM)
To help teams operate reliably in production with clear visibility into potential security issues, today we’re launching DigitalOcean Cloud Security Posture Management (CSPM). CSPM provides agentless, in-dashboard visibility into your infrastructure, helping you detect risks, prioritize what matt...
NVIDIA GTC 2026 Confirmed It: The Inference Era Is Here
Reflections on NVIDIA GTC 2026 and how AI has moved beyond the training era and into the era of production inference. GTC made it clear that the industry is moving beyond chips to the broader operating infrastructure architecture required to support AI-native companies.
DigitalOcean India: Inside Our Growing Hub for AI and Cloud Innovation
Explore DigitalOcean India’s rapid growth, AI innovation, and role in building the Agentic Inference Cloud for scalable, developer-first applications.
Enhancing Security with User-Specific Access Keys for DigitalOcean Functions
Introducing user-specific access keys for DigitalOcean Functions. Learn how this new security model improves team management, auditability, and automation.
Meet the New Standard for High-Performance, Low-Cost Inference: NVIDIA Dynamo 1.0 is now available to DigitalOcean Customers
NVIDIA Dynamo 1.0 is now available to DigitalOcean customers to help drive performance enhancements and cost efficiency. NVIDIA Dynamo 1.0 offers a 7x inference performance increase and by pairing it with DigitalOcean’s Agentic Inference Cloud, customers can achieve higher performance at lower co...
Prompt Caching for Anthropic and OpenAI Models: Building Cost-Efficient AI Systems
Learn how prompt caching in Anthropic and OpenAI models cut LLM costs and latency by reusing large, repeated prompt prefixes instead of reprocessing them on every request.
DigitalOcean at NVIDIA GTC 2026: Building the AI Factory for the Agentic Era
Today, at NVIDIA GTC 2026, we are excited to announce a massive expansion of our inference capabilities in partnership with NVIDIA. We are moving beyond basic infrastructure; we are building an AI Factory designed specifically to support AI builders and power the next generation of autonomous age...
Deploy Smarter with AI: Introducing App Platform Skills on DigitalOcean
We're introducing App Platform Skills, a collection of open-source, AI-native playbooks that bridge this gap. Skills inject up-to-date, opinionated DigitalOcean App Platform knowledge directly into an AI assistant's context — turning it from a generic code generator into an infrastructure-aware c...
Scaling Autonomous Site Reliability Engineering: Architecture, Orchestration, and Validation for a 90,000+ Server Fleet
This article covers how to use an AI SRE agent to help customers receive timely, in-depth investigation and troubleshooting for their web applications delivering faster diagnosis and quicker resolution.
Native .NET Buildpack Support is Now Available on App Platform
With native .NET buildpack support on DigitalOcean App Platform, you can deploy your .NET applications directly from a Git repository without writing or maintaining Dockerfiles. App Platform automatically detects your .NET project, installs the correct SDK version, and builds your application for...
How DigitalOcean’s Agentic Inference Cloud powered by NVIDIA GPUs Achieved 67% Lower Inference Costs for Workato
To make agentic workloads production-ready, the Workato AI Research Lab needed an inference stack built for production scale. This technical deep dive explores how DigitalOcean's Agentic Inference Cloud delivered 67% lower inference costs powered by NVIDIA GPUs.
Supabase Template is Now Available on DigitalOcean App Platform
We've introduced native Supabase template support on DigitalOcean App Platform. Deploy a production-ready Supabase backend with one click, complete with managed PostgreSQL, authentication, REST API, file storage, and real-time capabilities.
Zero to Deploy: Launching Your Career at DigitalOcean
What’s it like to build at DigitalOcean? Ship real code, work on AI infrastructure, and gain true ownership. Hear from three early builders who joined full-time.
DigitalOcean Gradient™ AI GPU Droplets Optimized for Inference: Increasing Throughput at Lower the Cost
In this post, we walk through the Inference Optimized Image, a fully pre-configured OS image, available on DigitalOcean's GPU Droplets. We cover the optimization stack, the engineering reasoning behind each layer, and the benchmark methodology and our test results showing these gains.
Expanding our Agentic Inference Cloud: Introducing GPU Droplets Powered by AMD Instinct™ MI350X GPUs
We’re expanding our AI/ML offerings with the introduction of new DigitalOcean Gradient™ AI GPU Droplets, virtual machines powered by AMD Instinct MI350X GPUs. By integrating these GPUs into our Agentic Inference Cloud, we continue to deliver cost-efficient, high-performance solutions for leading...
DigitalOcean Gradient™ AI Platform Now Integrates with LlamaIndex
We're excited to announce that DigitalOcean Gradient™ AI Platform now integrates natively with LlamaIndex - one of the most popular frameworks for building RAG applications.
The Container paradox: Why the Inference Cloud Demands a “Decoupled” Database
Discover why decoupling stateful databases from ephemeral Kubernetes clusters is crucial for reliability. Learn the risks of "Database-in-a-Box" and how to choose the right persistence strategy for your cloud-native apps.
Heroku’s Next Chapter Is Maintenance. Yours Shouldn’t Be
Heroku is entering maintenance mode—migrate to DigitalOcean App Platform with three months free for new workloads and support from our Solutions team.
Now Available: Anthropic Claude Opus 4.6 on DigitalOcean’s Agentic Inference Cloud
Claude Opus 4.6 is now available on the DigitalOcean Gradient™ AI Platform via Serverless Inference—giving teams access to Anthropic’s most capable model on a platform built to run inference reliably at scale.
LLM Inference Benchmarking - Measure What Matters
As inference hardware costs remain high, squeezing maximum performance to improve unit economics is a primary objective for AI teams. This article focuses on the LLM performance domain and analyzes the interplay between latency, throughput, concurrency, and cost.
Run Multiple OpenClaw AI Agents with Elastic Scaling and Safe Defaults — without Managing Infrastructure
Today we’re launching OpenClaw on DigitalOcean App Platform, designed to help teams move from proof of concept to sustained production operation with elastic scaling, safe defaults, and simpler day-to-day operations.
Technical Deep Dive: How we Created a Security-hardened 1-Click Deploy OpenClaw
At DigitalOcean, our 1-Click Deploy OpenClaw through our Marketplace enables us to package the latest and greatest software configured for our Droplet® server, and make it easily available to customers. Creating our 1-Click Deploy OpenClaw was the natural next step in getting this to our customer...
Introducing OpenClaw on DigitalOcean: One-Click Deploy, Security-hardened, Production-Ready Agentic AI
We’re excited to announce 1-Click deployment for OpenClaw on DigitalOcean Droplet® servers, making it faster to run always-on, agentic AI in a security-hardened cloud environment.
Technical Deep Dive: How DigitalOcean and AMD Delivered a 2x Production Inference Performance Increase for Character.ai
Character.ai wanted to optimize GPU performance and achieve lower inference costs for its application. Working closely together, the Character.ai, AMD, and DigitalOcean teams optimized AMD Instinct™ MI300X and MI325X GPU platforms, resulting in a 2x production inference throughput.
Introducing Multiple Registry Support on DigitalOcean Container Registry
DigitalOcean Container Registry now offers support for multiple registries, available for Premium Plan customers.
Building the Inference Cloud, and What Comes Next
2025 was a defining year for DigitalOcean as we solidified our vision about what the next era of cloud and AI will look like. We built out our inference cloud, which gives digital native enterprises and AI-native businesses the power to integrate AI and cloud workflows through one unified platfor...
Unstoppable Velocity: Why 2026 is the Year to Join DigitalOcean
As we kick off 2026, we’re fortifying our teams with people who have deep expertise, a passion for customers, and the hunger to gain hands-on experience with AI and work that is defining history.
Speed Up Your JavaScript Apps: Native Bun Support is Now Available on App Platform
DigitalOcean App Platform now offers native Bun support. Developers can deploy Bun applications directly from their code repository without writing a single line of configuration. App Platform’s Cloud Native Buildpacks automatically detect, build, deploy and run Bun apps.
A More Powerful, Code-First Knowledge Base Experience on the DigitalOcean Gradient™ AI Platform
Enhancements to DigitalOcean Gradient™ AI Knowledge Bases, now in public preview, are designed to solve this problem. Its code-first feature lets developers create, manage, and query knowledge bases entirely from code, giving full control over ingestion, chunking, embedding, and retrieval without...
Introducing DigitalOcean Gradient™ AI Agent Development Kit: Deploy agent code as a real application
The DigitalOcean Gradient™ AI Agent Development Kit (ADK), now available in public preview, is a powerful, code-first SDK that lets you build, test, and deploy sophisticated multi-step agent workflows from within their existing development environments, with built-in support for evaluations, trac...
A Year of Innovation: DigitalOcean Managed Databases in 2025
Read the recap of FY25 for DigitalOcean Managed Databases, and everything we released.
Introducing the Spend by Date Range Billing View
DigitalOcean customers now have access to the new custom date range billing view, a billing insight and cost optimization tool that allows you to evaluate your costs more granularly.
Leveling Up Kubernetes: Key DigitalOcean Managed Kubernetes Releases in 2025
Learn more about what features we release for DigitalOcean Kubernetes in 2025.
Powering the Next Leap in AI: GPU Droplets accelerated by NVIDIA HGX™ B300 are now available on DigitalOcean
We've expanded the availability of our AI/ML offerings by releasing new DigitalOcean Gradient™ AI GPU Droplets (virtual machines) accelerated by NVIDIA HGX B300s. This is a significant step forward in our mission to provide the simplest, most scalable cloud for builders everywhere.
Now Available: Remote MCP for DigitalOcean Services
DigitalOcean now offers support for Remote MCP Server for select DigitalOcean Services.
From User to Trusted Advisor: How Jeff Fan Powers Customer Success at DigitalOcean
Explore how Jeff Fan partners with DigitalOcean’s customers to bridge today’s challenges with tomorrow’s opportunities.
DoTs SDK Development: Automating TypeScript Client Generation
Now, our TypeScript SDK empowers developers to leverage TypeScript's type safety and modern development features, enabling them to manage their DigitalOcean resources. In this blog, we’ll share insights into the making of DoTs and the approach we took to develop it.
Evaluate your AI agents faster and more effectively
We’re updated our agent evaluations experience in the DigitalOcean Gradient™ AI Platform. These improvements make it faster and easier to evaluate your AI agents, understand results, and debug issues.
Streamline Your Workflow: Announcing Environment Support for DigitalOcean App Platform
Helping millions of developers easily build, test, manage, and scale applications of any size - faster than ever before.
Powered by DigitalOcean Hatch: How Ex-human uses GPU Droplets to Build Empathetic AI that Serves Customers
Learn how Ex-human uses DigitalOcean's Hatch program and affordable GPU Droplets to build scalable, empathetic AI characters for businesses while managing costs.
Hacktoberfest 2025 Comes to a Close
A look back at Hacktoberfest 2025, including participation stats, key changes to the program, and what we learned from this year's event.
GPU Observability: Get Deeper Insights into Your Droplets and DOKS Clusters
We’re introducing a new set of basic observability metrics for all GPU Droplets and DOKS clusters, giving you a powerful, simple way to monitor and optimize your AI workloads.
Leading the Cloud With Curiosity : Spotlight on Pranav Nambiar, SVP, AI/ML & PaaS
Discover how Pranav Nambiar is driving innovation in AI/ML and PaaS at DigitalOcean and why he believes DigitalOcean is the place to build meaningful impact.
Helping Startups Build Faster with an AI Startup Ecosystem
DigitalOcean’s new AI Startup Ecosystem brings together established technology partners, vibrant community organizations, AI developer platforms, and university entrepreneurship programs to help founders build, launch and scale faster on DigitalOcean's comprehensive agentic cloud.
Image and audio models from fal now available on DigitalOcean
We’re excited to announce the launch of multimodal AI models from fal on the DigitalOcean Gradient™ AI Platform, now available through Serverless Inference.
OAuth App Based Workload Identity for Droplets
Learn what workload identity federation is and how it can be implemented leveraging DigitalOcean’s OAuth API.
Is DigitalOcean Your Next Career Spot? A 5-Year Insider on Why It Should Be
Akanksha Kapoor shares her five-year journey of growth, collaboration, culture, and why DigitalOcean could be your next career spot.
Announcing GPU Droplets accelerated by NVIDIA HGX H100 in the EU
We’re expanding the availability AI/ML offerings with the introduction of new DigitalOcean Gradient™ AI GPU Droplets, virtual machines accelerated by NVIDIA HGX H100s, in our Amsterdam data center. This is a significant step forward in our mission to provide the simplest, most scalable cloud for...
Introducing the DigitalOcean AI Ecosystem
At its flagship conference in London, UK, DigitalOcean introduced its AI Ecosystem: a network of AI partners that are committed to creating a powerful environment that will help builders create the next generation of AI applications.
Announcing cost-efficient storage with usage-based backups, cold storage, and Network file storage
Optimize data storage and protection with DigitalOcean's new Network File Storage, Spaces cold storage, and usage-based backups.
Announcing per-sec billing, new Droplet plans, BYOIP, and NAT gateway to reduce scaling costs
Scale cloud infrastructure cost-effectively with DigitalOcean's new per-second billing, dedicated Droplet plans, BYOIP, and VPC NAT Gateway.
Introducing DigitalOcean Organizations, a new and comprehensive account layer
DigitalOcean Organizations for Account Management is now available, enabling customers to simplify billing, streamline user management, and completely simplify and centralize their DigitalOcean presence.
Storage that thinks for itself: Introducing Storage autoscaling, the newest feature for Managed Databases
Storage autoscaling is now available for all DigitalOcean Managed Databases.
Build Smarter Agents with Image Generation, Auto-Indexing, VPC Security, and new AI Tools on DigitalOcean Gradient™ AI Platform
Today we’re introducing a new wave of features that expand what you can build with the Gradient AI Platform, give you greater security and control, and accelerate your development workflow.
Hacktoberfest 2025: How to Participate
Learn how you can join thousands of other fans of open source with code, low- or no-code contributions to open-source projects.
Build faster, debug smarter, and make AI safer with new DigitalOcean Gradient™ AI Platform features
The way developers build with AI is changing fast—and so is the DigitalOcean Gradient™ AI Platform. Debugging data, reinventing agents from scratch, or connecting AI to workflows manually takes time and slows you down. The DigitalOcean Gradient™ AI Platform is evolving to tackle these challenges,...
Hacktoberfest 2025: Celebrate All Things Open Source!
Hacktoberfest 2025 is a few days away! Join fellow devs and open-source advocates to celebrate all things open source all October long.
Announcing Gateway API Support for DigitalOcean Kubernetes
The Kubernetes Gateway API, as a managed service, is now pre-installed in all DigitalOcean Kubernetes (DOKS) clusters and ready to use at no additional cost.
Sharks of DigitalOcean: Archana Kamath, Senior Director, IaaS
Discover Archana Kamath’s journey as Senior Director at DigitalOcean, leading our compute and networking teams and driving customer-centric innovation.
What's New on DigitalOcean App Platform
Welcome to What’s New on DigitalOcean App Platform—your regular roundup of the latest updates for App Platform. We’ll share new feature releases, technical tutorials, or video walkthroughs to help you stay ahead of the curve and keep building. Check back regularly for new insights and inspiration...
Single Sign-On is Now Available, Strengthening Security and Simplifying Authentication
Single Sign-On is now available on DigitalOcean, offering seamless login support for customers.
DigitalOcean MCP Server is now available
DigitalOcean is thrilled to offer its support for MCP Server, a new way to leverage AI.
Stop Building SaaS from Scratch: Meet the SeaNotes Starter Kit
SeaNotes is a production-ready SaaS Starter Kit from DigitalOcean’s SeaStack series. It comes with auth, billing, email, storage, AI, and deployment already set up—so you can focus on building your product, not the plumbing.
Announcing OpenAI gpt-oss Models on the DigitalOcean Gradient™ AI Platform
OpenAI’s first open-source GPT models (20b and 120b) are now available on the Gradient AI Platform. This launch brings even more flexibility and choice to developers building AI-powered applications, whether you’re starting with a quick prototype or scaling a production agent.
Introducing langchain-gradient: Seamless LangChain Integration with DigitalOcean Gradient™ AI Platform
We’re excited to introduce langchain-gradient, a new open-source integration that brings the power of LangChain to DigitalOcean Gradient AI Platform. LangChain is a popular framework for building applications powered by large language models (LLMs), with tools for chaining prompts, managing conte...