DigitalOcean Release Notes
260 release notes curated from 34 sources by the Releasebot Team. Last updated: Nov 19, 2026
DigitalOcean Products
- Nov 18, 2026
- Date parsed from source:Nov 18, 2026
- First seen by Releasebot:Nov 19, 2026
Now Available: GPT-6.2 Astra and GPT-6.2 Sol from OpenAI
DigitalOcean adds OpenAI’s GPT-6.2 Astra and Sol to Serverless Inference, billed through existing accounts.
GPT-6.2 Astra and GPT-6.2 Sol from OpenAI are now available through DigitalOcean Serverless Inference. OpenAI reports Astra, its frontier model for the hardest projects, sets new highs on OpenAI’s evals across professional work and scientific research at less than a third of GPT-6 Astra’s cost per task (OpenAI eval data; not a per-token price). Sol is OpenAI’s efficient model for everyday work and multistep agentic workflows. Both are available on your existing DigitalOcean account and billed on your DigitalOcean invoice. Access the models now ->
Original source - Nov 18, 2026
- Date parsed from source:Nov 18, 2026
- First seen by Releasebot:Nov 19, 2026
18 November
DigitalOcean adds version pinning and changelogs for Action Gateway tools, interactive stdin for Harness Runtime sandbox commands, and GPT-6.2 Astra and Sol for serverless inference.
■ Action Gateway now lets you pin a tool to a released version and keep calling it after newer versions are released. List a tool’s versions with a changelog that marks breaking changes, and see the latest version in _meta.latest_version when a call uses an older one. For more information, see Tool Versions. ■ Interactive stdin for DigitalOcean Harness Runtime sandbox commands is enabled per team. Start a command with keep_stdin_open on an event stream, then write base64 chunks to /v2/harness-runtime/sessions/{session_id}/sandbox/exec/{exec_id}/stdin while stdout and stderr continue to stream. Use this to drive a REPL, answer a prompt, or feed a long-running process. For more information, see How to Send Interactive Stdin to a Sandbox Command. ■ The following OpenAI models are now available on DigitalOcean Inference for serverless inference: ■ GPT-6.2 Astra ■ GPT-6.2 Sol For more information, see the Available Models page.
Original source All of your release notes in one feed
Join Releasebot and get updates from DigitalOcean and hundreds of other software products.
- Nov 17, 2026
- Date parsed from source:Nov 17, 2026
- First seen by Releasebot:Nov 18, 2026
- Modified by Releasebot:Nov 18, 2026
17 November
DigitalOcean makes MicroVMs generally available in MKC1, with flexible settings, scoped access, file transfers, outbound controls, and monitoring.
- DigitalOcean MicroVMs are now in general availability in MKC1. With general availability, you can change a MicroVM’s settings without recreating it, create access tokens that reach only one MicroVM, add URLs for additional ports, and upload and download files. You can also restrict a MicroVM’s outbound traffic to the destinations you allow and attach credentials that the platform adds to outbound requests, open a console from the Control Panel, and monitor MicroVMs with metrics, platform logs, and traces in DigitalOcean Insights.
- Nov 10, 2026
- Date parsed from source:Nov 10, 2026
- First seen by Releasebot:Nov 11, 2026
Now Available: Claude Fable 5.2
DigitalOcean adds Anthropic’s Claude Fable 5.2 to Serverless Inference, Inference Router preview, model synthesis, and Evaluations for eligible customers in supported regions, with reported faster output and lower token pricing than Fable 5.1.
Claude Fable 5.2, which Anthropic calls its most capable generally available model for technical work, is now available through Serverless Inference, Inference Router (Public Preview - no SLA; may change), model synthesis, and Evaluations to eligible customers in supported regions. Anthropic reports that, in its own testing as of November 2026, it generates output up to 30% faster than Claude Fable 5.1, at $8 / $40 per million input / output tokens, lower than Fable 5.1’s $10 / $50 (USD, excluding taxes subject to change), actual results vary by workload and configuration. It runs on the same DigitalOcean account, API, and invoice you already use for serverless inference billed by DigitalOcean.
Anthropic and Claude are trademarks of Anthropic, PBC. DigitalOcean is not affiliated with, and this announcement is not endorsed by, Anthropic.
Access the model now ->
Original source - Nov 10, 2026
- Date parsed from source:Nov 10, 2026
- First seen by Releasebot:Nov 11, 2026
QM, Y Combinator's Open-Source Agent Harness, Now Deploys in One Click on DigitalOcean
DigitalOcean launches the first one-click QM deployment in its Marketplace, bringing together compute, Managed Agents sandboxes, inference, database and storage so teams can run open-source agents on infrastructure they control.
Y Combinator built QM, a multiplayer agent harness for Slack and the web, to run agents across its own teams, from accounting and legal to engineering. In July, YC open-sourced it so any startup could do the same. Starting today, DigitalOcean offers the first one-click deployment for QM from the DigitalOcean Marketplace.
“We made QM open source so companies can own the agents that run their business. DigitalOcean makes it easy to get started. In one click, a team has QM running with sandboxes, inference, data and storage already in place, and the time they’d have spent on setup goes into building their company,” said Joshua France, Head of YC Labs, Y Combinator.
What one click sets up
Running QM has meant assembling a stack across providers. The DigitalOcean Marketplace deployment sets up all of it at once, on one bill:
- A Droplet for QM’s core service
- Managed Agents for isolated sandboxes
- Serverless Inference, with no extra API key
- Managed PostgreSQL for sessions, memory and the job queue
- Spaces for files and snapshots
Open by design
QM lets each team choose its harness and model (e.g. Pi, OpenCode, Codex, or Claude Code), and it runs in a range of environments. DigitalOcean contributed Managed Agents to QM as a built-in sandbox option available to QM users on supported versions.
“Y Combinator and DigitalOcean are working together to bring open intelligence to YC founders. With QM on DigitalOcean, startups can begin on one complete, open platform, choosing their models, harnesses, and data and running them on infrastructure they control,” said Paddy Srinivasan, CEO of DigitalOcean. “We want DigitalOcean to be the easiest place to run QM, and we’re investing in YC founders so they can get the most out of it.”
Get started
Deploy QM from the DigitalOcean Marketplace at do.co/qm, and read the QM docs.
Forward-looking statements. This post contains forward-looking statements about DigitalOcean’s plans for QM and YC founders. They reflect our current plans, are subject to change without notice, and are not a commitment to deliver any material, feature, or functionality. Managed Agents is offered as a public preview, and DigitalOcean does not guarantee that public preview services perform for production-level workloads.
Original source Similar to DigitalOcean with recent updates:
- Obsidian release notes125 release notes · Latest Nov 12, 2026
- Perplexity release notes33 release notes · Latest Nov 6, 2026
- OpenClaw release notes481 release notes · Latest Nov 19, 2026
- xAI release notes313 release notes · Latest Nov 17, 2026
- Ubiquiti release notes1162 release notes · Latest Nov 18, 2026
- 1Password release notes248 release notes · Latest Nov 17, 2026
- Nov 10, 2026
- Date parsed from source:Nov 10, 2026
- First seen by Releasebot:Nov 11, 2026
10 November
DigitalOcean is deprecating five open-source models on Serverless Inference, while keeping them available on Dedicated Inference. Users can migrate to recommended replacement models to avoid service disruption.
The following open-source models are deprecated from DigitalOcean Serverless Inference as of 10 November 2026:
- DeepSeek V4 Flash
- Llama 4 Maverick 17B 128E Instruct
- Qwen 3.5 397B A17B
- Gemma 4
- gpt-oss-20b
These models remain available on Dedicated Inference.
For serverless inference, migrate DeepSeek V4 Flash to DeepSeek V4.1 Flash 1017 (deepseek-v4.1-flash-1017), Llama 4 Maverick 17B 128E Instruct to DeepSeek V4.1 Flash (deepseek-v4.1-flash), Qwen 3.5 397B A17B to Qwen3.8-Max (qwen3.8-max), Gemma 4 to GLM-5.3 Flash (glm-5.3-flash), and gpt-oss-20b to gpt-oss-120b (openai-gpt-oss-120b) to avoid service disruption. For information on our model deprecation policy and recommended replacement models, see Model Support Policy.
Original source - Nov 9, 2026
- Date parsed from source:Nov 9, 2026
- First seen by Releasebot:Nov 11, 2026
9 November
DigitalOcean adds Anthropic’s Claude Fable 5.2 to Inference for serverless inference.
The following Anthropic model is now available on DigitalOcean Inference for serverless inference:
- Claude Fable 5.2
For more information, see the Available Models page.
Original source - Nov 7, 2026
- Date parsed from source:Nov 7, 2026
- First seen by Releasebot:Nov 13, 2026
7 November
DigitalOcean brings High Performance Block Storage to private preview in six datacenters, offering network-attached NVMe volumes with up to 60,000 IOPS and 1,200 MB/s per volume. Preview volumes are free and require at least 128 GiB.
High Performance Block Storage
High Performance Block Storage is now available in private preview in the NYC2, SFO3, ATL1, RIC1, MKC1, and MEM1 datacenters. High Performance volumes use network-attached NVMe storage over NVMe/TCP and deliver up to 60,000 IOPS and 1,200 MB/s per volume, regardless of Droplet type.
You can create High Performance volumes in the Control Panel or through the API by setting performance_class to b2. Volumes require a minimum size of 128 GiB and are free during the preview.
To request access, contact your Technical Account Manager (TAM). For more information, see How to Create High Performance Block Storage Volumes.
Original source - Nov 6, 2026
- Date parsed from source:Nov 6, 2026
- First seen by Releasebot:Nov 7, 2026
Introducing: Cuttlefish, build agents from anywhere
DigitalOcean brings Cuttlefish to iPhone, letting users monitor agent sessions, approve tool calls, steer runs, and review results.
From your iPhone, Cuttlefish lets you follow live agent sessions, approve or deny tool calls with the full command or diff in view, steer or stop a run mid-flight, and review what your agent built. It works with whichever agent you run on Managed Agents, including Claude Code, Codex CLI, OpenCode, OpenHands, Hermes, LangGraph, and CrewAI.
Download the app now ->
Original source - Nov 5, 2026
- Date parsed from source:Nov 5, 2026
- First seen by Releasebot:Nov 6, 2026
Now Available: Kimi K3.1 Pro from Moonshot AI
DigitalOcean now offers Moonshot AI’s Kimi K3.1 Pro on its Inference Engine, with a 1M-token context window and serverless access without a separate Moonshot AI account. The post-trained model also reports improved results on selected benchmarks.
Moonshot AI's Kimi K3.1 Pro is now available on DigitalOcean Inference Engine, a post-trained upgrade to Kimi K3 that Moonshot reports scores 65.7% on Terminal-Bench 4.0 and cuts the claim-level hallucination rate on its internal Kimi Hallu Bench Hard stress test from 23.4% (Kimi K3) to 8.3%; that benchmark is a stress test rather than an everyday error rate, and results vary by configuration and workload. It has a 1M-token context window and runs on Serverless Inference with no separate Moonshot AI account.
Access the model now ->
Moonshot AI, Kimi and Terminal-Bench are trademarks of their respective owners; no affiliation or endorsement is implied.
Original source - Nov 5, 2026
- Date parsed from source:Nov 5, 2026
- First seen by Releasebot:Nov 5, 2026
Introducing DigitalOcean Cuttlefish: Get more done with agents on the go
DigitalOcean releases Cuttlefish, a native iPhone app for Managed Agents that lets users monitor sessions, approve tool calls, steer work, and review results from anywhere. It also introduces Box Mount in private preview, syncing Box files with agent workspaces.
Your agent has been refactoring for two hours. It’s deep in the codebase, making real progress, and then it stops: “Can I run this migration?”
Nothing happens until you answer. And you’re not at your desk. You’re in line at the grocery store, or waiting at school pickup.
DigitalOcean Managed Agents, in Public Preview, already moved your agents off your laptop and into the cloud. Each session runs in its own isolated sandbox, so the work keeps going after you close the lid. Now the person in the loop can be anywhere too.
Today we’re introducing Cuttlefish, a native iPhone app for Managed Agents. From your phone, you can review what an agent found, add the context only you have, approve the next step, or start new work. Then you put your phone away and get on with your day.
Keep up with agents that never clock out
Agents run for minutes, hours, or overnight, and they stop to ask for permission along the way. Cuttlefish is built for those moments:
- Follow live sessions: Watch replies, reasoning, and tool calls stream in, and get notified when a run needs approval, finishes, or fails.
- Approve or deny tool calls: See the full command, file path, or diff, rather than a summary, and unblock your agent from wherever you are. Requests classified as high risk require Face ID or your passcode.
- Steer mid-run: Send a correction, pause, resume, or stop a session when it’s heading the wrong way. Messages you send while the agent works get queued, so you can line up the next task without waiting.
- Work with the results: View what your agent built, including websites and documents, right in the app. Cuttlefish attaches to running servers and presents the content in a format suited to quick viewing. You can also browse workspace files, create checkpoints, and fork or roll back.
Built on three principles: choice, control, and collaboration
We built Managed Agents around three principles: choice, control, and collaboration. Choice means you pick the right tool for each job, so Managed Agents runs the harness your team already uses, from Claude Code and Codex CLI to OpenCode, OpenHands, Hermes, LangGraph, and CrewAI, with the models and 20,000+ tools that fit the work. Cuttlefish supervises all of them, so the app in your pocket isn’t tied to a single vendor’s agent.
Control and collaboration are what make it safer to let those agents keep running. You decide which actions an agent can take on its own, and which are off limits, so you stay in control without watching every step. Sessions run in DigitalOcean-hosted microVMs that persist independently of anyone’s device, so a run doesn’t depend on your laptop, and a teammate can join or take over when you’re away. Cuttlefish puts both on your phone, so you can approve, steer, or stop a run and see who’s in a session, wherever you are.
Point your agent at your Box files
Collaboration doesn’t stop at sessions. With this release, we’re bringing the filesystem for AI and Managed Agents together in a single, unified mobile experience. Box is launching Box Mount, now in private preview, which syncs a Box folder into your Managed Agents environment, so agents work on the same files your team already uses, under Box’s permissions, version history, and audit trail.
In Cuttlefish, open Customize > Tools > Box, sign in, and pick a folder. The agent works on plain files in its workspace. Its edits upload to Box, and changes made in Box show up in the workspace. Each person syncs with their own Box account. The agent can edit and delete files in the synced folder, and deletions sync back to Box.
For example, a fictional legal team keeps its vendor contracts in a Box folder, and an agent working on that folder stops to ask permission before writing a summary. On their way to a trial, a lawyer approves from their phone, and the summary lands back in the Box folder, where any colleague with access can see it right away. No one has to email a file or ask who has the latest copy.
Getting Started
Your agents are already doing the work. With Cuttlefish, the next time one stops to ask permission, you can answer from your phone instead of coming back to a stalled run.
- If you don’t have a DigitalOcean account, create one.
- Download Cuttlefish from the App Store.
- Sign in with your DigitalOcean account.
- Start a session by choosing your coding agent, including Claude Code, OpenCode, and Codex CLI.
Why “Cuttlefish”?
Most product names describe what the product does. We wanted one that says something more.
The cuttlefish is one of the most dynamic camouflaging animals in the ocean. It adapts to its environment, changing its color, pattern, and texture to match whatever is around it. We think that’s a good metaphor for an agent, which has to adapt to the harness, tools, and models around it. The name points at what the app is about: choice, control, and collaboration, from wherever you are.
Claude Code, Codex CLI, OpenCode, OpenHands, Hermes, Box, App Store, and Face ID are trademarks of their respective owners. Their use here is for identification only and does not imply any affiliation with or endorsement by those owners.
Original source - Nov 5, 2026
- Date parsed from source:Nov 5, 2026
- First seen by Releasebot:Nov 5, 2026
- Modified by Releasebot:Nov 10, 2026
5 November
DigitalOcean adds regional Droplet snapshot copy removal, expands documentation search with its unauthenticated MCP server, and brings the Cuttlefish iOS app for Harness Runtime sessions to public preview. Several NVIDIA models are also scheduled for Serverless Inference deprecation.
- You can now remove a Droplet snapshot’s copy from a single region without deleting the snapshot or its copies in other regions, using the DigitalOcean API or the Control Panel. Read How to Add or Remove Droplet Snapshots in Other Regions to learn how to remove a regional copy.
- The DigitalOcean Documentation MCP server searches the full documentation site index, and each search result includes an excerpt from the page body. You can restrict docs-search results to one product with the Product parameter, and read long pages in sections with the StartIndex and MaxLength parameters of docs-get-page. The server does not require authentication or a DigitalOcean account. To add it to Claude, Claude Desktop, Claude Code, Cursor, Visual Studio Code, or Codex, see Connect the Documentation MCP Server.
- Cuttlefish, an iOS app for DigitalOcean Harness Runtime, is available in public preview on the App Store. Follow and steer sessions, approve or deny tool calls, and work with workspace files and checkpoints from your iPhone. To get started, see How to Steer and Approve Harness Runtime Sessions from the Cuttlefish iOS App.
- The following NVIDIA models are deprecated from DigitalOcean Serverless Inference as of 5 November 2026:
- Nemotron 3 Diarization
- Nemotron 3 Ultra
- Nemotron 3 Nano Omni
- Nemotron Nano 12B v2 VL
These models remain available on Dedicated Inference. Migrate serverless workloads to NVIDIA Nemotron 3.5 Super VL (nemotron-3.5-super-vl) to avoid service disruption. For information on our model deprecation policy and recommended replacement models, see Model Support Policy.
Original source - Nov 4, 2026
- Date parsed from source:Nov 4, 2026
- First seen by Releasebot:Nov 5, 2026
Now Generally Available: Microsoft Entra ID SSO for Teams
DigitalOcean now supports Microsoft Entra ID for team SSO, letting organizations use existing workforce credentials and managed directory access.
Team single sign-on (SSO) now supports Microsoft Entra ID, alongside Okta. If your organization runs workforce identity in Entra, your team signs in with the credentials they already use, and access follows the directory your IT team already manages.
Set up Entra ID SSO today->
Original source - Nov 4, 2026
- Date parsed from source:Nov 4, 2026
- First seen by Releasebot:Jun 23, 2026
- Modified by Releasebot:Nov 4, 2026
4 November
DigitalOcean adds Moonshot AI’s Kimi K3.1 Pro to serverless and dedicated inference.
The following Moonshot AI model is now available on DigitalOcean Inference for serverless inference and dedicated inference:
- Kimi K3.1 Pro
For more information, see the Available Models page.
Original source - Nov 3, 2026
- Date parsed from source:Nov 3, 2026
- First seen by Releasebot:Nov 4, 2026
Now in Public Preview: Secrets Manager
DigitalOcean adds secure application secret management through its Cloud Console, API, and CLI, with IAM access controls and audit logging.
Create, store, and manage application secrets — including API keys, database credentials, OAuth tokens, and certificates — directly from the Cloud Console, API, or CLI. Access is governed by DigitalOcean IAM, and secret activity is logged for audit without exposing secret values.
Get started->
Original source
Curated by the Releasebot team
Releasebot is an aggregator of official release notes from hundreds of software vendors and thousands of sources.
Our editorial process involves the manual review and audit of release notes procured with the help of automated systems.