# Docker Sandboxes

Docker Sandboxes provides disposable, microVM-isolated environments for safely running AI coding agents.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Meet the New Docker: Built to Run on Trust

DevFeed: [Meet the New Docker: Built to Run on Trust](<https://devfeed.tech/articles/meet-the-new-docker-built-to-run-on-trust-144458.md>)

Original publisher: [Read original article](<https://www.docker.com/blog/meet-the-new-docker-built-to-run-on-trust/>)

Author: Jin Kim

Published: 2026-11-19T17:00:00Z

Content type: release

Language: en

Sources: [Docker](<https://devfeed.tech/sources/docker.md>)

Topics: [trust](<https://devfeed.tech/topics/trust.md>), [Docker](<https://devfeed.tech/topics/docker.md>), [Docker AI Governance](<https://devfeed.tech/topics/docker-ai-governance.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [brand](<https://devfeed.tech/tags/brand.md>), [community](<https://devfeed.tech/tags/community.md>), [company](<https://devfeed.tech/tags/company.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-ai-governance](<https://devfeed.tech/tags/docker-ai-governance.md>), [moby](<https://devfeed.tech/tags/moby.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

Docker presents its rebrand as an expansion of its role for the AI-agent era, while retaining its developer-first approach, openness, simplicity and container work. It argues that containers isolate workloads, but agents act autonomously by choosing what to run, access and change, so organizations need purpose-built isolation and governance to give them autonomy while maintaining control. Docker frames its next chapter around a trusted supply chain, an agent runtime and an ecosystem intended to cover governance and risk across enterprises, including third-party layers without vendor lock-in. It points readers to Docker Sandboxes and Docker AI Governance as ways to explore the approach, but provides no implementation details or comparative evidence for those products.

### Source excerpt

Docker launches a new brand built on trust. Learn why Docker is evolving for AI agents, what stays the same, and how to run agents securely with Docker.

## Readie: Low-Latency Code Sandboxes for AI Agents

DevFeed: [Readie: Low-Latency Code Sandboxes for AI Agents](<https://devfeed.tech/articles/readie-low-latency-code-sandboxes-for-ai-agents-139599.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22171>)

Author: Arjun Sivaraman, Zhaoheng Li, Alan Shi, Sanjay Malisetty, Eugene Wu, Yongjoo Park

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [DeepSeek Harness](<https://devfeed.tech/topics/dsh.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [approximation](<https://devfeed.tech/tags/approximation.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [budget](<https://devfeed.tech/tags/budget.md>), [code](<https://devfeed.tech/tags/code.md>), [code-execution](<https://devfeed.tech/tags/code-execution.md>), [construction](<https://devfeed.tech/tags/construction.md>), [covering](<https://devfeed.tech/tags/covering.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [execution](<https://devfeed.tech/tags/execution.md>), [latency](<https://devfeed.tech/tags/latency.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [packages](<https://devfeed.tech/tags/packages.md>), [public](<https://devfeed.tech/tags/public.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>)

### AI overview

Readie targets slow startup in code sandboxes used by AI agents. Instead of relying on one compact snapshot to cover diverse generated code, it learns a set of small, quickly initialized snapshots, each covering part of the workload and collectively covering most of it. The set is constructed from a large training workload by formulating snapshot selection as an optimization problem and solving it with an approximation algorithm. On 15,000 public and LLM-synthesized scripts, the abstract reports 3-22x lower startup latency and 1.3-3.3x lower end-to-end runtime than existing approaches at the same storage budget.

### Source excerpt

arXiv:2611.22171v1 Announce Type: cross Abstract: From quantitative research to personal assistance, AI agents act by iteratively generating and executing code. To decouple the agent harness from code execution, many agents offload execution to dedicated systems called code sandboxes. However, existing code sandboxes suffer from slow startup. Whether they rely on custom snapshots or a single fat image, the root cause is the same: it is hard to build a compact, pre-warmed snapshot that can be shared across diverse agent-generated code while covering nearly all the artifacts (e.g., packages, datasets) it requires. In this work, we propose learned startup snapshots for low-latency code sandboxes. Our insight is that while it is hard for a single snapshot to be both compact and cover most workloads, a set of snapshots can achieve both. Each snapshot is small, initializes quickly, and covers a fraction of agent-generated code; together, the set covers most of it. We learn this set from a large training workload by formulating snapshot construction as an optimization problem and solving it with an approximation algorithm. Planned on 15K public and LLM-synthesized scripts, our system, Readie, reduces startup latency by 3-22$\times$ and end-to-end runtime by 1.3-3.3$\times$ compared to existing approaches at the same storage budget.

## External sandboxes for coding agents

DevFeed: [External sandboxes for coding agents](<https://devfeed.tech/articles/external-sandboxes-for-coding-agents-138614.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/17/external-sandboxes-for-coding-agents/>)

Author: Simon Willison

Published: 2026-11-17T22:52:29Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-328](<https://devfeed.tech/tags/ai-2-328.md>), [alpine-linux](<https://devfeed.tech/tags/alpine-linux.md>), [api](<https://devfeed.tech/tags/api.md>), [apple](<https://devfeed.tech/tags/apple.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-136](<https://devfeed.tech/tags/claude-code-136.md>), [codex](<https://devfeed.tech/tags/codex.md>), [codex-62](<https://devfeed.tech/tags/codex-62.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [coding-agents-267](<https://devfeed.tech/tags/coding-agents-267.md>), [containers](<https://devfeed.tech/tags/containers.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-066](<https://devfeed.tech/tags/generative-ai-2-066.md>), [http](<https://devfeed.tech/tags/http.md>), [https](<https://devfeed.tech/tags/https.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-030](<https://devfeed.tech/tags/llms-2-030.md>), [local-models](<https://devfeed.tech/tags/local-models.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [node-js](<https://devfeed.tech/tags/node-js.md>), [pattern](<https://devfeed.tech/tags/pattern.md>), [pi](<https://devfeed.tech/tags/pi.md>), [pi-7](<https://devfeed.tech/tags/pi-7.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [qemu](<https://devfeed.tech/tags/qemu.md>), [safely](<https://devfeed.tech/tags/safely.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [sandboxing](<https://devfeed.tech/tags/sandboxing.md>), [sandboxing-59](<https://devfeed.tech/tags/sandboxing-59.md>), [security](<https://devfeed.tech/tags/security.md>), [security-646](<https://devfeed.tech/tags/security-646.md>), [webassembly](<https://devfeed.tech/tags/webassembly.md>), [webassembly-137](<https://devfeed.tech/tags/webassembly-137.md>)

### AI overview

The external sandbox pattern keeps the coding agent outside a dedicated environment where its executed code runs, aiming to reduce the risk of harmful actions from mistakes or prompt injection. Three servers provide the same localhost API: external-sandbox-v86 uses Node.js, v86, and Alpine Linux in WebAssembly; external-sandbox-container uses a Python web server and Apple Containers; and external-sandbox-quicksand uses a Python web server with Microsoft's Quicksand library, QEMU, and Alpine Linux. Pi, Claude Code, and Codex can be configured to send execution requests to them. Optional HTTP/HTTPS allow-list proxying restricts which hosts sandboxed code can contact, while credential replacement supports authenticated API calls without exposing secrets to the agent. The excerpt presents these as implementations for experimenting with the pattern, not as a comparative security evaluation.

### Source excerpt

External sandboxes for coding agents I've been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or prompt injection attack might cause them to take damaging actions on a machine. I worked on this project with Prime Radiant, the AI research lab behind Superpowers and other projects. My post on the Prime Radiant blog introduces the external sandbox pattern, where code executed by the agent runs inside a dedicated sandbox while the agent itself lives outside of that sandbox. To demonstrate this pattern we've released three sandbox server implementations: external-sandbox-v86 runs a Node.js server which then uses v86 to run Alpine Linux inside WebAssembly. external-sandbox-container is a Python web server which runs the sandbox in Alpine Linux inside an Apple Containers instance. external-sandbox-quicksand is another Python web server, this time using Microsoft's Quicksand sandboxing library, which bundles QEMU and Alpine Linux in a Python package! Each of these implementations offers the same localhost API. You can then configure Pi, Claude Code, or Codex to send API calls to that sandbox any time they want to execute code. The sandboxes also include an optional HTTP/HTTPS allow-list proxy, so you can control exactly which hosts your agent's code is allowed to communicate with - plus a credential replacement mechanism to make authenticated API calls without sharing a secret with the agent. Here's the UI you can use to reconfigure that proxy while the sandbox is still running: I continue to be fascinated by the challenge of safely running untrusted code. This external sandbox pattern provides a neat way to experiment with different approaches. Tags: sandboxing, security, ai, webassembly, generative-ai, llms, coding-agents, claude-code, codex, pi

## CI in 2027: Why the future of coding needs instant back-pressure

DevFeed: [CI in 2027: Why the future of coding needs instant back-pressure](<https://devfeed.tech/articles/ci-in-2027-why-the-future-of-coding-needs-instant-back-pressure-128969.md>)

Original publisher: [Read original article](<https://www.chainguard.dev/unchained/ci-in-2027-why-the-future-of-coding-needs-instant-back-pressure>)

Published: 2026-11-09T00:00:00Z

Content type: article

Language: en

Sources: [Chainguard: Unchained](<https://devfeed.tech/sources/chainguard-unchained.md>)

Topics: [CI/CD](<https://devfeed.tech/topics/cicd.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2015](<https://devfeed.tech/tags/2015.md>), [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [can](<https://devfeed.tech/tags/can.md>), [chainguard](<https://devfeed.tech/tags/chainguard.md>), [ci](<https://devfeed.tech/tags/ci.md>), [coding](<https://devfeed.tech/tags/coding.md>), [faster](<https://devfeed.tech/tags/faster.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [future](<https://devfeed.tech/tags/future.md>), [instant](<https://devfeed.tech/tags/instant.md>), [keep](<https://devfeed.tech/tags/keep.md>), [learn](<https://devfeed.tech/tags/learn.md>), [machine](<https://devfeed.tech/tags/machine.md>), [needs](<https://devfeed.tech/tags/needs.md>), [speed](<https://devfeed.tech/tags/speed.md>), [up](<https://devfeed.tech/tags/up.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The article argues that pull request CI is too slow and brittle to give coding agents useful back-pressure: GitHub Actions' August 6 outage halted the company's patch pipeline, while routine PR cycles brought long waits, lost agent context, API dependency, repeated setup costs, and risks from running untrusted code near secrets. The authors describe using CI failures as structured findings for fresh agents, with retries capped at five before human intervention; this worked but was costly and slow. They say the next system must isolate execution, make failures verifiable, and return feedback in seconds. Part 2 is previewed as covering ephemeral microVMs adapted from SLSA L3 build technology, an out-of-guest proxy for injecting secrets, and a lazy virtual filesystem for toolchains; the excerpt does not provide implementation details or results.

### Source excerpt

Traditional CI can't keep up with AI coding agents. Learn why Chainguard is rethinking CI to deliver faster, safer feedback at machine speed.

## ZDI-26-894: Docker Sandboxes Inclusion of Functionality from Untrusted Control Sphere Remote Code Execution Vulnerability

DevFeed: [ZDI-26-894: Docker Sandboxes Inclusion of Functionality from Untrusted Control Sphere Remote Code Execution Vulnerability](<https://devfeed.tech/articles/zdi-26-894-docker-sandboxes-inclusion-of-functionality-from-untrusted-control-sphere-remote-code-execution-vulnerability-121853.md>)

Original publisher: [Read original article](<http://www.zerodayinitiative.com/advisories/ZDI-26-894/>)

Published: 2026-11-06T06:00:00Z

Content type: news

Language: en

Sources: [Zero Day Initiative](<https://devfeed.tech/sources/zero-day-initiative.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [Exploit](<https://devfeed.tech/topics/exploit.md>), [AI Sandbox](<https://devfeed.tech/topics/ai-sandbox.md>)

Tags: [clone](<https://devfeed.tech/tags/clone.md>), [code](<https://devfeed.tech/tags/code.md>), [code-execution](<https://devfeed.tech/tags/code-execution.md>), [cve](<https://devfeed.tech/tags/cve.md>), [docker-sandboxes](<https://devfeed.tech/tags/docker-sandboxes.md>), [local](<https://devfeed.tech/tags/local.md>), [user-interaction](<https://devfeed.tech/tags/user-interaction.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

Docker Sandboxes has a remote code execution vulnerability in sandbox creation using clone mode: it launches an executable from an untrusted location. A local attacker can exploit it to run arbitrary code as the current user, but exploitation requires the target to visit a malicious page or open a malicious file. The ZDI rates it CVSS 7.8 and identifies it as CVE-2026-121614. Docker has issued an update to correct the vulnerability.

### Source excerpt

This vulnerability allows local attackers to execute arbitrary code on affected installations of Docker Sandboxes. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-121614.

## Docker Sandboxes vs. Containers: Choosing the Right Isolation for AI Agents

DevFeed: [Docker Sandboxes vs. Containers: Choosing the Right Isolation for AI Agents](<https://devfeed.tech/articles/docker-sandboxes-vs-containers-choosing-the-right-isolation-for-ai-agents-120910.md>)

Original publisher: [Read original article](<https://www.docker.com/blog/docker-sandboxes-vs-containers/>)

Author: Jackie Frederick

Published: 2026-11-06T03:17:04Z

Content type: article

Language: en

Sources: [Docker](<https://devfeed.tech/sources/docker.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [Docker](<https://devfeed.tech/topics/docker.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [virtualization](<https://devfeed.tech/topics/virtualization.md>), [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>), [Docker AI Governance](<https://devfeed.tech/topics/docker-ai-governance.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [cloud-sandboxes](<https://devfeed.tech/tags/cloud-sandboxes.md>), [concepts](<https://devfeed.tech/tags/concepts.md>), [containers](<https://devfeed.tech/tags/containers.md>), [docker-sandboxes](<https://devfeed.tech/tags/docker-sandboxes.md>), [products](<https://devfeed.tech/tags/products.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Containers isolate processes while sharing the host kernel, making them fast and well suited to packaged applications, CI jobs, and short-lived execution. Docker Sandboxes place autonomous coding agents in dedicated microVMs with their own kernel, filesystem, network, and private Docker Engine; agents can use sudo, build images, and run Compose without access to the host Docker daemon. Host-enforced network rules and credential mediation can limit access, while workspace files, MCP servers, and skills remain reachable if shared. Sandboxes preserve session state but require a supported hypervisor and more memory and disk; cloud sandboxes are an option when local resources are limiting. The article recommends containers for controlled workloads and Sandboxes when agents run unattended, handle untrusted input, need Docker capabilities or protected credentials, or work across longer sessions. Kits and environment files support repeatable setups, though both are described as early access or experimental.

### Source excerpt

A container shares the host kernel. Docker Sandboxes are microVMs with their own kernel and private Docker Engine. See how they differ and when to use each.

## Where should your code live in a Docker Sandbox?

DevFeed: [Where should your code live in a Docker Sandbox?](<https://devfeed.tech/articles/where-should-your-code-live-in-a-docker-sandbox-113426.md>)

Original publisher: [Read original article](<https://www.docker.com/blog/docker-sandbox-code-checkout-workflows/>)

Author: Jin Kim

Published: 2026-11-02T14:00:00Z

Content type: comparison

Language: en

Sources: [Docker](<https://devfeed.tech/sources/docker.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [versioning](<https://devfeed.tech/topics/versioning.md>), [Docker](<https://devfeed.tech/topics/docker.md>), [remote-development](<https://devfeed.tech/topics/remote-development.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [clone](<https://devfeed.tech/tags/clone.md>), [code](<https://devfeed.tech/tags/code.md>), [devex](<https://devfeed.tech/tags/devex.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-sandbox](<https://devfeed.tech/tags/docker-sandbox.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [git](<https://devfeed.tech/tags/git.md>), [git-worktrees](<https://devfeed.tech/tags/git-worktrees.md>), [products](<https://devfeed.tech/tags/products.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [worktrees](<https://devfeed.tech/tags/worktrees.md>)

### AI overview

Docker Sandboxes offer several ways to place code, with different tradeoffs in collaboration, Git access, isolation, and handoff. A direct host mount lets you watch edits in your local editor and share Git operations, but branch switches and edits affect the agent's working tree; dependencies may also conflict across host and sandbox operating systems. A linked Git worktree gives each task its own directory and branch, but its `.git` metadata sits outside the mount, so Git status, branching, and commits must happen on the host. Clone mode gives the agent an independent checkout with Git and keeps its branches and dependencies separate; results return through a host remote or the repository's normal Git workflow. A mountless sandbox keeps code and tools inside the sandbox, with work returned by pushing or copying it out; previews require a published port, and removing the sandbox deletes files stored only there. Multiple repositories can be mounted or cloned together, including read-only references, though writable checkouts need coordination. These arrangements can be combined to fit a task.

### Source excerpt

Docker Sandboxes support three ways to organize an agent's code: shared mounts, Git worktrees, and clone mode. Here's how to choose between them.

## The Ecosystem is the Answer: Docker, the Blueprint Alliance, and the Importance of Collaboration in the Agentic Era

DevFeed: [The Ecosystem is the Answer: Docker, the Blueprint Alliance, and the Importance of Collaboration in the Agentic Era](<https://devfeed.tech/articles/the-ecosystem-is-the-answer-docker-the-blueprint-alliance-and-the-importance-of-collaboration-in-the-agentic-era-113425.md>)

Original publisher: [Read original article](<https://www.docker.com/blog/docker-blueprint-alliance-agent-baseline/>)

Author: Jin Kim

Published: 2026-11-02T14:00:00Z

Content type: opinion

Language: en

Sources: [Docker](<https://devfeed.tech/sources/docker.md>)

Topics: [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Docker](<https://devfeed.tech/topics/docker.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [Docker Hardened Images](<https://devfeed.tech/topics/docker-hardened-images.md>), [Docker AI Governance](<https://devfeed.tech/topics/docker-ai-governance.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>)

Tags: [2015](<https://devfeed.tech/tags/2015.md>), [2025](<https://devfeed.tech/tags/2025.md>), [academics](<https://devfeed.tech/tags/academics.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [blueprint](<https://devfeed.tech/tags/blueprint.md>), [blueprint-alliance](<https://devfeed.tech/tags/blueprint-alliance.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [company](<https://devfeed.tech/tags/company.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-ai-governance](<https://devfeed.tech/tags/docker-ai-governance.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [era](<https://devfeed.tech/tags/era.md>), [governance](<https://devfeed.tech/tags/governance.md>), [partnerships](<https://devfeed.tech/tags/partnerships.md>), [questions](<https://devfeed.tech/tags/questions.md>), [reference](<https://devfeed.tech/tags/reference.md>), [reference-architecture](<https://devfeed.tech/tags/reference-architecture.md>), [security](<https://devfeed.tech/tags/security.md>), [security-packages](<https://devfeed.tech/tags/security-packages.md>)

### AI overview

The Blueprint Alliance maps how enterprise AI governance components connect, while Agent Baseline defines what those components must do and how to verify it. The Alliance's 12 founding companies are pursuing interoperability over MCP, OCSF, SSF and CAEP and publishing reference integrations; its architecture addresses agent discovery, permissions, activity and response. Agent Baseline v1.0-draft defines six outcomes and 35 open, versioned controls. The excerpt recommends assessing against the baseline, beginning with discovery before policy, and testing containment in advance. It places Docker at the execution boundary: Docker Sandboxes support isolated execution, while Docker MCP Gateway and Docker Hardened Images address tool access and software supply chain. The article argues runtime support matters because API-driven containment without a way to pause an agent may provide a false sense of security. This is an excerpt, so it does not establish full-document coverage.

### Source excerpt

Docker is a founding member of the Blueprint Alliance, a 12-company reference architecture for securing AI agents, built around four governance questions.

## Coding Agent Horror Stories: The CVE That Did Not Exist

DevFeed: [Coding Agent Horror Stories: The CVE That Did Not Exist](<https://devfeed.tech/articles/coding-agent-horror-stories-the-cve-that-did-not-exist-107268.md>)

Original publisher: [Read original article](<https://www.docker.com/blog/coding-agent-horror-stories-the-cve-that-did-not-exist/>)

Author: Jennifer Kohl

Published: 2026-10-29T13:00:00Z

Content type: article

Language: en

Sources: [Docker](<https://devfeed.tech/sources/docker.md>)

Topics: [ai code review](<https://devfeed.tech/topics/ai-code-review.md>), [AI agent hallucinations](<https://devfeed.tech/topics/ai-agent-hallucinations.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-code-review](<https://devfeed.tech/tags/ai-code-review.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [community](<https://devfeed.tech/tags/community.md>), [cve](<https://devfeed.tech/tags/cve.md>), [docker-sandboxes](<https://devfeed.tech/tags/docker-sandboxes.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>)

### AI overview

A read-only code review agent named BuaJi invented a CVE, a nonexistent company and Kubernetes resources, then recommended dangerous remediation for a routine PostgreSQL version update. Its permissions prevented it from acting, but a person could have followed its convincing report. The article proposes containing the agent in a Docker Sandbox: mount the repository read-only, provide no credentials, allow network access only to the Ollama model, and save the review as text. It also recommends checking cited CVE IDs against NVD, labeling agent output as untrusted, and reviewing suggested commands before use. The sandbox limits what the agent can reach but cannot verify its claims or prevent a human from trusting them; the CVE check catches nonexistent IDs, not fabricated details generally.

### Source excerpt

An AI code review agent invented a CVE and recommended dangerous fixes. Learn how Docker Sandboxes contain agents and why their output needs verification.

## Harbor Adds Docker Sandboxes to Run Reproducible AI Agent Evals in Isolated MicroVMs

DevFeed: [Harbor Adds Docker Sandboxes to Run Reproducible AI Agent Evals in Isolated MicroVMs](<https://devfeed.tech/articles/harbor-adds-docker-sandboxes-to-run-reproducible-ai-agent-evals-in-isolated-microvms-95268.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/10/ai-agents-harbor-docker/>)

Author: Claudio Masolo

Published: 2026-10-22T09:00:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [AI Sandbox](<https://devfeed.tech/topics/ai-sandbox.md>), [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>), [Docker Compose](<https://devfeed.tech/topics/docker-compose.md>), [Testcontainers](<https://devfeed.tech/topics/testcontainers.md>)

Tags: [agent-evals](<https://devfeed.tech/tags/agent-evals.md>), [agentic-ai-architecture](<https://devfeed.tech/tags/agentic-ai-architecture.md>), [ai-agents-harbor-docker](<https://devfeed.tech/tags/ai-agents-harbor-docker.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cloud-sandboxes](<https://devfeed.tech/tags/cloud-sandboxes.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [compose](<https://devfeed.tech/tags/compose.md>), [daytona](<https://devfeed.tech/tags/daytona.md>), [devops](<https://devfeed.tech/tags/devops.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-sandboxes](<https://devfeed.tech/tags/docker-sandboxes.md>), [harbor](<https://devfeed.tech/tags/harbor.md>), [microvm](<https://devfeed.tech/tags/microvm.md>), [news](<https://devfeed.tech/tags/news.md>)

### AI overview

Harbor can run each agent evaluation task in its own Docker Sandbox microVM, isolating it from the host and other tasks. Docker reports testing 64 concurrent cloud tasks; the excerpt gives no data on startup overhead, cost per task, or score variance. Cloud Sandboxes can allow dependency downloads during setup and restrict network access during agent work, while local runs support only public or no-network modes under the machine's existing policy. Docker Compose tasks are supported within one cloud sandbox. The integration is in the nightly release, pinned here to version 0.24.1.dev202610150414, with stable release stated for October 23. Cloud use requires Docker Cloud access and a personal access token with Cloud Sandboxes permission, supplied through SBX_DOCKER_USERNAME and SBX_DOCKER_PAT; select it with `-e sbx`. Local use requires `sbx login` and `--ek target=local`. Network restriction reduces one avenue for reward hacking but does not prevent tampering with writable tests or score files.

### Source excerpt

Docker announced that Harbor, the open-source agent evaluation framework, now works with Docker Sandboxes. This change allows each evaluation task to run in its own microVM. So, instead of sharing a container, tasks are isolated for better performance By Claudio Masolo

## Your Agent Runs in a Docker Sandbox. Now It Can Join a Team.

DevFeed: [Your Agent Runs in a Docker Sandbox. Now It Can Join a Team.](<https://devfeed.tech/articles/your-agent-runs-in-a-docker-sandbox-now-it-can-join-a-team-92965.md>)

Original publisher: [Read original article](<https://www.docker.com/blog/your-agent-runs-in-a-docker-sandbox-now-it-can-join-a-team/>)

Author: Jennifer Kohl

Published: 2026-10-21T16:10:49Z

Content type: tutorial

Language: en

Sources: [Docker](<https://devfeed.tech/sources/docker.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [a-team](<https://devfeed.tech/tags/a-team.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [api-credits](<https://devfeed.tech/tags/api-credits.md>), [band](<https://devfeed.tech/tags/band.md>), [connect](<https://devfeed.tech/tags/connect.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-sandbox](<https://devfeed.tech/tags/docker-sandbox.md>), [docker-sandboxes](<https://devfeed.tech/tags/docker-sandboxes.md>), [environments](<https://devfeed.tech/tags/environments.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [join](<https://devfeed.tech/tags/join.md>), [learn-how-to](<https://devfeed.tech/tags/learn-how-to.md>), [manage](<https://devfeed.tech/tags/manage.md>), [products](<https://devfeed.tech/tags/products.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [sandbox-kit](<https://devfeed.tech/tags/sandbox-kit.md>), [team](<https://devfeed.tech/tags/team.md>)

### AI overview

The BAND Python kit connects an agent running inside a local Docker Sandbox to a shared BAND room, where it can collaborate with people and agents running locally, in the cloud, or on other infrastructure. The agent opens an outbound WebSocket and sends replies through BAND's API; it works in an isolated microVM with access to its mounted workspace. The Repo Doctor example uses a Python entrypoint, Claude, and tools to inspect files, edit code, and run tests. Setup requires Docker Sandboxes, a BAND account and agent API key, plus an Anthropic API key for this example; the kit itself does not require a particular model provider. Docker keeps the real keys on the host and injects them into outbound requests as placeholders. After storing credentials, create and run the sandbox, allow network access to api.anthropic.com for Claude, and add the connected agent to a room. The excerpt also describes multi-agent rooms, where only the local agent that needs repository access runs in the sandbox.

### Source excerpt

Run AI agents in Docker Sandboxes with BAND AI. Learn how to connect isolated agents, collaborate across environments, and manage access securely.

## Running Pulumi Neo in a Docker Sandbox: workshop recap

DevFeed: [Running Pulumi Neo in a Docker Sandbox: workshop recap](<https://devfeed.tech/articles/running-pulumi-neo-in-a-docker-sandbox-workshop-recap-92883.md>)

Original publisher: [Read original article](<https://www.pulumi.com/blog/running-pulumi-neo-in-a-docker-sandbox/>)

Author: Mike Coleman

Published: 2026-10-21T00:00:00Z

Content type: article

Language: en

Sources: [Pulumi](<https://devfeed.tech/sources/pulumi.md>)

Topics: [pulumi-neo](<https://devfeed.tech/topics/pulumi-neo.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [pulumi](<https://devfeed.tech/topics/pulumi.md>), [Docker](<https://devfeed.tech/topics/docker.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [personal access token](<https://devfeed.tech/topics/personal-access-token.md>), [World models](<https://devfeed.tech/topics/world-models.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [community](<https://devfeed.tech/tags/community.md>), [data](<https://devfeed.tech/tags/data.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-sandbox](<https://devfeed.tech/tags/docker-sandbox.md>), [esc](<https://devfeed.tech/tags/esc.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [neo](<https://devfeed.tech/tags/neo.md>), [policy](<https://devfeed.tech/tags/policy.md>), [production](<https://devfeed.tech/tags/production.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [pulumi](<https://devfeed.tech/tags/pulumi.md>), [pulumi-neo](<https://devfeed.tech/tags/pulumi-neo.md>), [recap](<https://devfeed.tech/tags/recap.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [security](<https://devfeed.tech/tags/security.md>), [token](<https://devfeed.tech/tags/token.md>), [workshop](<https://devfeed.tech/tags/workshop.md>)

### AI overview

The workshop describes running Pulumi Neo in a Docker Sandbox with controls outside the agent's prompt. Neo runs in an isolated microVM with access limited to mounted files and permitted network hosts; a proxy injects the Pulumi token so Neo does not hold the real credential. Pulumi governs permissions and approvals: manual asks before each tool call, balanced before `pulumi up`, and auto never asks. Read-only blocks Pulumi Cloud writes but does not prevent access to ESC environments or their cloud accounts; role permissions must restrict environment access. Preventative Pulumi Policies can block violations, `protect: true` can stop deletion of protected resources, and ESC can issue short-lived AWS credentials, which limit leak damage but do not prevent it. Docker's network proxy can deny unapproved hosts, though allowed hosts still receive what Neo sends. The excerpt recommends starting with a locked-down network preset and balanced approvals near production. Centralized Docker sandbox controls are paid; local sandboxes and the `sbx` CLI are free. The final teardown demonstration was not completed.

### Source excerpt

The more an agent can do on its own, the more infrastructure work you can hand it, as long as its limits hold when it gets something wrong. In April, they didn't hold for PocketOS. A coding agent on a routine staging task deleted the company's production volume in 9 seconds. According to founder Jer Crane's account, it used an API token it found in an unrelated file. Its explanation afterward: "I guessed that deleting a staging volume via the API would be scoped to staging only. I didn't verify." Railway recovered the data two days later. The agent had been told not to. "System prompts are advisory, not enforcing," Crane wrote afterward. If the prompt can't stop an agent, the limits have to sit where the agent can't negotiate with them. That was the premise of Neo in a Docker Sandbox, the workshop Adam Gordon Bell and I ran with Mike Coleman from Docker. So we gave Pulumi Neo two layers. The first is a Docker Sandbox. Neo runs in its own microVM and reaches only the files and hosts we allow. The Pulumi token gets injected by a proxy on the way out, so Neo never holds the real credential. The second is Pulumi itself, which decides what Neo may change and when it has to ask. With both in place, you can let Neo work without approving every step. For why YOLO mode belongs in a sandbox at all, see my August post. Mike Coleman is a Principal Solutions Architect at Docker. His running joke is that agents "want to be helpful". It happens in his own demos: Mike Coleman I talk to people about agents a lot. They just really want to please you. I don't know how many times I've done a demo [of] governance for MCP servers, and I'll be like, "Can you write to my Notion page?" And there will be a policy applied to the sandbox that says it can't. But I have a connector enabled in Claude somewhere. And it's like, "Well, not with that MCP server, but I can use this thing over here to do it." Mike's answer is to close those doors before the agent finds them: Mike Coleman The more you c

## How to Run SQL Server Outside Docker Sandboxes

DevFeed: [How to Run SQL Server Outside Docker Sandboxes](<https://devfeed.tech/articles/how-to-run-sql-server-outside-docker-sandboxes-90003.md>)

Original publisher: [Read original article](<https://spin.atomicobject.com/sql-server-outside-sandboxes/>)

Author: John Ruble

Published: 2026-10-19T12:00:34Z

Content type: tutorial

Language: en

Sources: [Atomic Object](<https://devfeed.tech/sources/atomic-object.md>)

Topics: [sql-server](<https://devfeed.tech/topics/sql-server.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-for-developers](<https://devfeed.tech/tags/ai-for-developers.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [docker](<https://devfeed.tech/tags/docker.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [sql](<https://devfeed.tech/tags/sql.md>)

### AI overview

The tutorial connects Claude Code agents in Docker Sandboxes to a shared SQL Server running on the host when the database image cannot run inside the sandbox. It uses socat to forward localhost connections, an outbound network allowlist to restrict access, and AGENT_NAME database suffixes to isolate each sandbox's tests. Agent guidance explains how to access the external database without attempting to start another server.

### Source excerpt

Like many of my colleagues, I've been experimenting with tooling around sandboxed agents. Lately for me this looks like a handful of Claude Code agents, each in an isolated Docker sbx. Today I'm going to share what it took to give them access to a test database. SQL Server and Docker sbx My current project, [...] The post How to Run SQL Server Outside Docker Sandboxes appeared first on Atomic Spin.

## Perplexity Open-Sources SPACE, a Firecracker MicroVM Sandbox for AI Agents

DevFeed: [Perplexity Open-Sources SPACE, a Firecracker MicroVM Sandbox for AI Agents](<https://devfeed.tech/articles/perplexity-open-sources-space-a-firecracker-microvm-sandbox-for-ai-agents-88911.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/10/16/perplexity-open-sources-space-firecracker-microvm-sandbox-ai-agents/>)

Author: Asif Razzaq

Published: 2026-10-17T00:09:12Z

Content type: news

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [Firecracker](<https://devfeed.tech/topics/firecracker.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [api](<https://devfeed.tech/tags/api.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [isolation](<https://devfeed.tech/tags/isolation.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [microvm](<https://devfeed.tech/tags/microvm.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>)

### AI overview

Perplexity open-sourced SPACE, a Rust sandbox platform that runs each agent task in its own Firecracker microVM. Its host-side gateway controls outbound traffic and credentials, while the HTTP API supports creating environments, running commands, and streaming output. The article describes its architecture, deployment requirements, performance claims, and red-team results, including initial partial-network policy bypasses that Perplexity says it addressed.

### Source excerpt

Perplexity has open-sourced SPACE, the sandbox platform behind every task in Perplexity Computer. The Perplexity SPACE sandbox gives each agent task its own Firecracker microVM. Credentials and outbound traffic are controlled from outside that VM. The code ships under Apache 2.0 on GitHub. For teams building coding or browsing agents, this is a production-tested isolation [...] The post Perplexity Open-Sources SPACE, a Firecracker MicroVM Sandbox for AI Agents appeared first on MarkTechPost.

## From Containers to Sandboxes: Developer Trust in the Agentic Era

DevFeed: [From Containers to Sandboxes: Developer Trust in the Agentic Era](<https://devfeed.tech/articles/from-containers-to-sandboxes-developer-trust-in-the-agentic-era-88877.md>)

Original publisher: [Read original article](<https://www.docker.com/blog/stack-overflow-survey-2026-ai-agent-trust/>)

Author: Jin Kim

Published: 2026-10-16T16:00:00Z

Content type: opinion

Language: en

Sources: [Docker](<https://devfeed.tech/sources/docker.md>)

Topics: [trust](<https://devfeed.tech/topics/trust.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [cloud-sandboxes](<https://devfeed.tech/tags/cloud-sandboxes.md>), [company](<https://devfeed.tech/tags/company.md>), [docker-sandboxes](<https://devfeed.tech/tags/docker-sandboxes.md>), [research](<https://devfeed.tech/tags/research.md>), [sandbox-kit](<https://devfeed.tech/tags/sandbox-kit.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [security](<https://devfeed.tech/tags/security.md>), [stack-overflow](<https://devfeed.tech/tags/stack-overflow.md>), [stack-overflow-developer-survey](<https://devfeed.tech/tags/stack-overflow-developer-survey.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

The author uses findings from the 2026 Stack Overflow Developer Survey about developers' trust in AI output and concerns about security and privacy to argue that running agents safely requires stronger isolation. The article describes Docker's Cloud Sandboxes and Sandbox Kit as efforts to build trust for AI agents.

### Source excerpt

The 2026 Stack Overflow Developer Survey shows only 7% of developers trust AI output for important decisions. Here's what that means for running agents safely.

## How to Run Coding Agents in Parallel in the Cloud (2026)

DevFeed: [How to Run Coding Agents in Parallel in the Cloud (2026)](<https://devfeed.tech/articles/how-to-run-coding-agents-in-parallel-in-the-cloud-2026-88071.md>)

Original publisher: [Read original article](<https://upstash.com/blog/run-coding-agents-in-parallel-with-upstash-box>)

Author: Ali Tarık Şahin

Published: 2026-10-15T00:00:00Z

Content type: tutorial

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [parallel workspaces](<https://devfeed.tech/topics/parallel-workspaces.md>), [AI Sandbox](<https://devfeed.tech/topics/ai-sandbox.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [box](<https://devfeed.tech/tags/box.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [snapshot](<https://devfeed.tech/tags/snapshot.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

The article explains how to run coding agents in parallel with Upstash Box by preparing and snapshotting a repository, launching an isolated box for each task, testing and reviewing each agent's patch, and cleaning up the boxes. It also discusses acceptance checks, pull requests, merge conflicts, security limits, pricing, and alternatives.

### Source excerpt

Run coding agents in parallel with Upstash Box. Clone once, snapshot the repo, and give each agent an isolated sandbox for tests, patches, and PRs.

## Harbor + Docker Sandboxes: Run Safe, Reproducible Agent Evals

DevFeed: [Harbor + Docker Sandboxes: Run Safe, Reproducible Agent Evals](<https://devfeed.tech/articles/harbor-docker-sandboxes-run-safe-reproducible-agent-evals-87258.md>)

Original publisher: [Read original article](<https://www.docker.com/blog/harbor-docker-sandboxes-run-safe-reproducible-agent-evals/>)

Author: Srini Sekaran

Published: 2026-10-14T21:45:27Z

Content type: article

Language: en

Sources: [Docker](<https://devfeed.tech/sources/docker.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [AI Sandbox](<https://devfeed.tech/topics/ai-sandbox.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-evals](<https://devfeed.tech/tags/agent-evals.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [code](<https://devfeed.tech/tags/code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [concurrent](<https://devfeed.tech/tags/concurrent.md>), [container](<https://devfeed.tech/tags/container.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-sandboxes](<https://devfeed.tech/tags/docker-sandboxes.md>), [environments](<https://devfeed.tech/tags/environments.md>), [evals](<https://devfeed.tech/tags/evals.md>), [harbor](<https://devfeed.tech/tags/harbor.md>), [microvm](<https://devfeed.tech/tags/microvm.md>), [network](<https://devfeed.tech/tags/network.md>), [products](<https://devfeed.tech/tags/products.md>), [run](<https://devfeed.tech/tags/run.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [scaling](<https://devfeed.tech/tags/scaling.md>)

### AI overview

Harbor integrates with Docker Sandboxes to run agent evaluation tasks in isolated microVMs, locally or in the cloud. Configurable network policies support consistent testing conditions, and Cloud Sandboxes can run tasks concurrently. The current integration supports single-container CPU tasks; GPU and multi-container support are described as forthcoming.

### Source excerpt

Harbor can now run every eval task in Docker Sandboxes Docker Sandboxes are MicroVM environments to run agents like Claude Code, Codex, Cursor, and more safely With Sandboxes, define custom network policies for fair, reproducible evals Run your evals locally or in the cloud: starting for free on Docker Sandboxes on local surfaces and scaling...

## Researchers left a hidden message for rogue AI agents. Then the agents wrote back.

DevFeed: [Researchers left a hidden message for rogue AI agents. Then the agents wrote back.](<https://devfeed.tech/articles/researchers-left-a-hidden-message-for-rogue-ai-agents-then-the-agents-wrote-back-87276.md>)

Original publisher: [Read original article](<https://thenewstack.io/rogue-ai-agent-fleet-tencent/>)

Author: Amanda Caswell

Published: 2026-10-14T17:47:11Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [Kiro](<https://devfeed.tech/topics/kiro.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [bot-defenses](<https://devfeed.tech/tags/bot-defenses.md>), [breach](<https://devfeed.tech/tags/breach.md>), [browser](<https://devfeed.tech/tags/browser.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [development](<https://devfeed.tech/tags/development.md>), [environments](<https://devfeed.tech/tags/environments.md>), [execution](<https://devfeed.tech/tags/execution.md>), [failed](<https://devfeed.tech/tags/failed.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Researchers report that AI agents running on Tencent Cloud repeatedly tried to retrieve data from Alibaba's Amap while bypassing anti-bot protections. The agents used public browser and page-reader services, exposed credentials, and other workarounds. A hidden message on the researchers' report led some agents to contact them, illustrating indirect prompt injection and trust-boundary risks. The researchers say they found no evidence of real-time coordination and could not independently establish which models were running.

### Source excerpt

A team of researchers investigating AI agents trying to bypass Alibaba's anti-bot protections left a hidden message inviting the agents The post Researchers left a hidden message for rogue AI agents. Then the agents wrote back. appeared first on The New Stack.

## Introducing Chainguard Checks

DevFeed: [Introducing Chainguard Checks](<https://devfeed.tech/articles/introducing-chainguard-checks-86537.md>)

Original publisher: [Read original article](<https://www.chainguard.dev/unchained/introducing-chainguard-checks>)

Published: 2026-10-14T00:00:00Z

Content type: release

Language: en

Sources: [Chainguard: Unchained](<https://devfeed.tech/sources/chainguard-unchained.md>)

Topics: [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [chainguard agent skills](<https://devfeed.tech/topics/chainguard-agent-skills.md>), [staging](<https://devfeed.tech/topics/staging.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [attack-surface](<https://devfeed.tech/tags/attack-surface.md>), [bug](<https://devfeed.tech/tags/bug.md>), [chainguard-checks](<https://devfeed.tech/tags/chainguard-checks.md>), [ci](<https://devfeed.tech/tags/ci.md>), [developers](<https://devfeed.tech/tags/developers.md>), [for-developers](<https://devfeed.tech/tags/for-developers.md>)

### AI overview

Chainguard introduces Checks, a beta CI service that lets developers and AI agents run pre-commit tests through a CLI, hooks, GitHub integration, or agent tools. It uses warm, isolated microVMs, controlled network access, ephemeral credentials, and signed attestations to provide faster feedback while limiting exposure to untrusted code.

### Source excerpt

Introducing Chainguard Checks, secure CI for developers and AI agents with fast pre-commit testing, isolated microVMs, and signed attestations.

## Why Are Coding Agents So Dumb?

DevFeed: [Why Are Coding Agents So Dumb?](<https://devfeed.tech/articles/why-are-coding-agents-so-dumb-84305.md>)

Original publisher: [Read original article](<https://mtlynch.io/why-are-coding-agents-so-dumb/>)

Author: Michael Lynch

Published: 2026-10-09T00:00:00Z

Content type: opinion

Language: en

Sources: [Mtlynch](<https://devfeed.tech/sources/mtlynch-io.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [blast-radius](<https://devfeed.tech/tags/blast-radius.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

The author argues that coding agents lag behind the language models they connect to, citing weak task management, limited parallel work and delegation, poor planning and communication, and inadequate security boundaries. The article outlines desired capabilities such as model selection by task, clearer plans, OS-level sandboxing, and user control of subagents. The author's explanation for the gap is a hypothesis: leaders may prioritize demos and model benchmarks over agent security and developer time.

### Source excerpt

The first time I used a coding agent, I was mesmerized. Before the agent, I was copy/pasting between my IDE and an AI chat interface. It was amazing to see an agent edit files directly and fix its own errors in real time. After a few days, the honeymoon wore off as I encountered frequent bugs. The agent would stop responding entirely until I restarted it. Development workflows felt stiflingly primitive, and the agent would often declare tasks finished when work had barely begun.

## Introducing Strands Box: AI agent sandboxes powered by Dogwood

DevFeed: [Introducing Strands Box: AI agent sandboxes powered by Dogwood](<https://devfeed.tech/articles/introducing-strands-box-ai-agent-sandboxes-powered-by-dogwood-66984.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/opensource/introducing-strands-box-ai-agent-sandboxes-powered-by-dogwood/>)

Author: Fernando Dingler

Published: 2026-10-07T17:36:46Z

Content type: release

Language: en

Sources: [AWS Open Source Blog](<https://devfeed.tech/sources/aws-open-source-blog.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [agent-safety](<https://devfeed.tech/tags/agent-safety.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-safety](<https://devfeed.tech/tags/ai-agent-safety.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [apis](<https://devfeed.tech/tags/apis.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-cli](<https://devfeed.tech/tags/aws-cli.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [box](<https://devfeed.tech/tags/box.md>), [claude-agent-sdk](<https://devfeed.tech/tags/claude-agent-sdk.md>), [commands](<https://devfeed.tech/tags/commands.md>), [developers](<https://devfeed.tech/tags/developers.md>), [files](<https://devfeed.tech/tags/files.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [shell](<https://devfeed.tech/tags/shell.md>)

### AI overview

AWS introduces Strands Box, an open source sandbox in developer preview that combines operating system isolation with Dogwood policies to govern AI agent actions. The article explains enforcement across filesystem, shell, network, Python, and MCP operations, including temporal rules and credential handling. It also describes planned platform support and deployment integrations.

### Source excerpt

As developers increasingly delegate work to AI agents, these agents require broader access to systems and resources. They read files, run shell commands, execute generated code, and call APIs. That is what makes agents useful, but that same autonomy is the source of the biggest risks. Coding assistants, home-grown harnesses, and off-the-shelf agents increasingly run [...]

## When 2,000 Agents Share One CPU

DevFeed: [When 2,000 Agents Share One CPU](<https://devfeed.tech/articles/when-2-000-agents-share-one-cpu-84275.md>)

Original publisher: [Read original article](<https://www.daytona.io/dotfiles/when-2000-agents-share-one-cpu>)

Author: Daniel Thi Graviet ML Researcher

Published: 2026-10-07T00:00:00Z

Content type: article

Language: en

Sources: [Dotfiles Insider](<https://devfeed.tech/sources/dotfiles-insider.md>)

Topics: [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>), [NVIDIA Vera](<https://devfeed.tech/topics/nvidia-vera.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [Nitro Isolation Engine](<https://devfeed.tech/topics/nitro-isolation-engine.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [bottlenecks](<https://devfeed.tech/tags/bottlenecks.md>), [browser-based-ide](<https://devfeed.tech/tags/browser-based-ide.md>), [browser-ide](<https://devfeed.tech/tags/browser-ide.md>), [cloud-coding](<https://devfeed.tech/tags/cloud-coding.md>), [cloud-dev-environment](<https://devfeed.tech/tags/cloud-dev-environment.md>), [cloud-development-environment](<https://devfeed.tech/tags/cloud-development-environment.md>), [cloud-editor](<https://devfeed.tech/tags/cloud-editor.md>), [cloud-ide](<https://devfeed.tech/tags/cloud-ide.md>), [cloud-programming](<https://devfeed.tech/tags/cloud-programming.md>), [code-in-cloud](<https://devfeed.tech/tags/code-in-cloud.md>), [code-on-web](<https://devfeed.tech/tags/code-on-web.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-environment](<https://devfeed.tech/tags/coding-environment.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [developers](<https://devfeed.tech/tags/developers.md>), [ide-editor-online](<https://devfeed.tech/tags/ide-editor-online.md>), [ide-in-browser](<https://devfeed.tech/tags/ide-in-browser.md>), [ide-online](<https://devfeed.tech/tags/ide-online.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [nvidia-vera](<https://devfeed.tech/tags/nvidia-vera.md>), [online-code-editor](<https://devfeed.tech/tags/online-code-editor.md>), [online-ide](<https://devfeed.tech/tags/online-ide.md>), [online-programming](<https://devfeed.tech/tags/online-programming.md>), [online-web-dev-ide](<https://devfeed.tech/tags/online-web-dev-ide.md>), [online-web-development-ide](<https://devfeed.tech/tags/online-web-development-ide.md>), [sde](<https://devfeed.tech/tags/sde.md>), [standardised-development-environment](<https://devfeed.tech/tags/standardised-development-environment.md>), [stories-insights](<https://devfeed.tech/tags/stories-insights.md>), [web-based-coding](<https://devfeed.tech/tags/web-based-coding.md>), [web-ide](<https://devfeed.tech/tags/web-ide.md>)

### AI overview

The article reports Daytona's comparison of NVIDIA Vera and AMD EPYC CPUs on coding-agent workloads run in isolated sandboxes. In the reported tests, Vera brought 1,000 sandboxes online in 10.8 seconds and sustained about 13 completed agent jobs per second at concurrency up to 2,000. The article argues that provisioning speed and sustained throughput matter for operating dense agent infrastructure.

### Source excerpt

AI agents need dense infrastructure. See how NVIDIA Vera brings 2,000 Daytona sandboxes online fast while sustaining high throughput.

## The Best Daytona Alternatives for AI Agent Sandboxes in 2026

DevFeed: [The Best Daytona Alternatives for AI Agent Sandboxes in 2026](<https://devfeed.tech/articles/the-best-daytona-alternatives-for-ai-agent-sandboxes-in-2026-87115.md>)

Original publisher: [Read original article](<https://upstash.com/blog/best-daytona-alternatives>)

Author: Ali Tarık Şahin

Published: 2026-10-06T00:00:00Z

Content type: comparison

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [Service fabric](<https://devfeed.tech/topics/service-fabric.md>), [Cloudflare Workers](<https://devfeed.tech/topics/cloudflare-workers.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [api](<https://devfeed.tech/tags/api.md>), [box](<https://devfeed.tech/tags/box.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [container](<https://devfeed.tech/tags/container.md>), [containers](<https://devfeed.tech/tags/containers.md>), [daytona](<https://devfeed.tech/tags/daytona.md>), [modal](<https://devfeed.tech/tags/modal.md>), [python](<https://devfeed.tech/tags/python.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [typescript](<https://devfeed.tech/tags/typescript.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

### AI overview

This comparison explains why software teams might seek alternatives to Daytona and weighs Upstash Box, E2B, Vercel Sandbox, Modal, Tensorlake, and Northflank by coding-agent support, isolation, pricing, compute, and deployment needs. It also outlines Daytona's strengths and trade-offs and notes migration and self-hosting considerations.

### Source excerpt

The best Daytona alternatives in 2026: Upstash Box if your TypeScript or Python team wants coding agents with less integration work, plus E2B, Vercel Sandbox, Modal, Tensorlake and Northflank, and when Daytona is still the better choice.

## Introducing the Mobile Sandbox: A Disposable Cloud Phone Your Agents Can Drive

DevFeed: [Introducing the Mobile Sandbox: A Disposable Cloud Phone Your Agents Can Drive](<https://devfeed.tech/articles/introducing-the-mobile-sandbox-a-disposable-cloud-phone-your-agents-can-drive-84800.md>)

Original publisher: [Read original article](<https://usenaive.ai/blogs/introducing-mobile-sandbox>)

Author: Naïve

Published: 2026-10-06T00:00:00Z

Content type: release

Language: en

Sources: [Naïve](<https://devfeed.tech/sources/naive.md>)

Topics: [native-client](<https://devfeed.tech/topics/native-client.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [cloud-infrastructure](<https://devfeed.tech/topics/cloud-infrastructure.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>)

Tags: [android-13](<https://devfeed.tech/tags/android-13.md>), [android-phones](<https://devfeed.tech/tags/android-phones.md>), [api](<https://devfeed.tech/tags/api.md>), [apps](<https://devfeed.tech/tags/apps.md>), [browser](<https://devfeed.tech/tags/browser.md>), [bug](<https://devfeed.tech/tags/bug.md>), [build](<https://devfeed.tech/tags/build.md>), [button](<https://devfeed.tech/tags/button.md>), [code](<https://devfeed.tech/tags/code.md>), [computers](<https://devfeed.tech/tags/computers.md>), [costs](<https://devfeed.tech/tags/costs.md>), [launch](<https://devfeed.tech/tags/launch.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>)

### AI overview

Naive Managed Agents introduces disposable Android cloud phones that code, tests, and agents can control through screenshots, UI selectors, and touch actions. The release describes API, SDK, CLI, and dashboard access, device timeouts and billing, and limitations including virtual Android devices only and no app uploads.

### Source excerpt

Naive Managed Agents now runs disposable cloud phones that your code and your agents drive by looking and touching. Here is what one is, how it ends itself, and what it costs.

[Next page](<https://devfeed.tech/topics/docker-sandboxes.md?cursor=WyIyMDI2LTEwLTA2VDAwOjAwOjAwKzAwOjAwIiwgIjlmNDc0YzM3LTc0MzYtNGI1MC1hMDhlLTNhZTdlMmRlYWY3NCJd>)