Fact-checked by Grok 2 weeks ago

Unikernel

A unikernel is a specialized, single-purpose operating system constructed as a single-address-space image, where an application and its minimal required OS components—drawn from a library operating system—are compiled together into a compact, statically linked that executes directly on a or bare metal without a traditional kernel-user space separation. This approach contrasts with conventional general-purpose operating systems like , which include extensive, multi-user functionality that often remains unused in specialized deployments, leading to larger footprints and increased complexity. Unikernels emerged as a response to the demands of , where efficiency and security are paramount, with early prototypes like MirageOS demonstrating their viability by compiling network services such as DNS resolvers or HTTP servers into images as small as 200 KB that boot in under 50 milliseconds on hypervisors like . The compilation process integrates the application's (often in high-level languages like or ) with type-safe libraries and device drivers, eliminating unnecessary features to create an immutable, sealed appliance optimized for a specific task. This results in a single-process environment with full privileges, supporting features like while avoiding the overhead of or multi-tenancy abstractions found in traditional OSes. Key advantages of unikernels include a drastically reduced due to their minimal code base, which excludes unused components and enforces strong isolation through static linking; enhanced performance from low-latency boots and the absence of context-switching between kernel and user modes; and lower , making them ideal for scalable infrastructures where cost and density matter. However, challenges persist, such as the need for recompilation to reconfigure services and a higher burden in managing numerous instances, though ongoing projects like Unikraft address these by providing modular, binary-compatible frameworks that ease development and portability across . Since their introduction in the early , unikernels have influenced research in OSes and , with growing adoption in and secure enclaves.

History

Origins and Early Concepts

A unikernel is defined as a single-address-space machine image compiled from a operating system (libOS), incorporating only the application-specific code and necessary system components required to execute a single task, without the traditional distinction between and space. This design eliminates the overhead of a general-purpose by linking the application directly with minimal OS services, resulting in a compact, specialized that runs on a . The conceptual foundations of unikernels trace back to library OS ideas developed in the 1990s, which aimed to allow applications to manage resources directly through user-level libraries while the kernel handled only secure multiplexing. Pioneering efforts include the Exokernel project at MIT, which exported hardware resources via a minimal kernel interface to untrusted libOSes, enabling application-level customization of abstractions like virtual memory and interprocess communication. Similarly, the Nemesis operating system from the University of Cambridge adopted a single-address-space model, using modular libraries for OS functions to support efficient sharing and time-sensitive applications. These approaches paralleled single-purpose OS images in embedded systems, such as real-time kernels like VxWorks, where stripped-down configurations tailored to specific hardware and tasks minimized footprint and improved predictability. Unikernels emerged prominently in 2013 amid growing concerns over OS bloat and overhead in environments, following the post-2000s boom in enabled by hypervisors like , first released in 2003. Academic work, such as the ASPLOS paper introducing unikernels via the prototype, sought to reduce the size and complexity of images by compiling away unused code, addressing inefficiencies in deploying general-purpose OSes on commodity . Initial motivations centered on minimizing the through compile-time specialization and type-safe languages, achieving faster times by avoiding initialization of extraneous components, and enhancing resource efficiency for single-task workloads in virtualized settings. This conceptual framework paved the way for practical implementations like MirageOS.

Key Developments and Projects

The development of unikernels gained momentum in the early 2010s with foundational research from the , where MirageOS emerged as a pioneering OCaml-based system for secure networking applications in 2013. MirageOS version 1.0 was released in December 2013, emphasizing modular library operating systems compiled directly into lightweight virtual machines. This work built on the 2013 ASPLOS paper "Unikernels: Library Operating Systems for the Cloud," which formalized the concept and demonstrated order-of-magnitude reductions in code size for cloud deployments. The ideas were further popularized in a 2014 ACM Queue article, "Unikernels: Rise of the Virtual Library Operating System," highlighting their potential for flexible, secure cloud services. In 2014, practical implementations proliferated, with IncludeOS launching on August 18 as a C++-based unikernel targeting x86 architectures for efficient cloud services. That same year, OSv was introduced via a paper, focusing on JVM-optimized environments to run single applications faster on virtual machines with boot times under one second. By 2015, Rumprun extended NetBSD's components to enable unmodified applications as unikernels, supporting platforms like and KVM. The mid-2010s saw accelerated open-source growth, with projects like MirageOS and Rumprun integrating deeply with the for high-density deployments, as evidenced by tools like Jitsu for just-in-time unikernel summoning on Xen in 2015. Concurrently, efforts expanded to cloud platforms, including OSv's compatibility with AWS EC2 instances for rapid application execution. These integrations, spanning 2016-2018, facilitated broader adoption in production environments by leveraging existing and cloud infrastructures. Entering the 2020s, Unikraft introduced a modular in 2018, allowing pluggable components for languages like C/C++, Go, and , with significant maturity achieved by 2021 as detailed in a ;login article and EuroSys paper. Unikraft's design emphasized easy customization and deployment on platforms like AWS and , marking a shift toward developer-friendly unikernel . In 2025, adaptations of the RTOS emerged to achieve unikernel-like minimalism, enhancing performance for specialized systems by trimming the OS footprint while retaining capabilities. Notably, the original 2013 MirageOS paper received an Influential Paper Award at ASPLOS 2025, underscoring its lasting impact on the field.

Design Principles

Core Architecture

Unikernels adopt a single-address-space model in which the application code and a minimal set of operating system services operate entirely within mode, avoiding the context switches and system calls that characterize conventional operating systems with distinct user and spaces. This unified execution environment simplifies and enhances by eliminating mode transitions. Building on the library operating system paradigm pioneered in earlier research like the exokernel, unikernels implement OS functionality—such as device drivers and networking stacks—as libraries that are linked directly to the application at , rather than as a separate . This approach allows for the creation of a specialized, lightweight tailored to the application's needs, excluding unnecessary components. The architecture features no explicit boundary between user and modes, which minimizes overhead from privilege level changes and permits direct access to hardware resources via interfaces provided by a host or directly in bare metal deployments. Key components typically encompass the core application logic, a sparse collection of essential drivers, and basic support including a allocator and an optional scheduler for . When deployed in virtualized environments, unikernels rely on an underlying , such as or KVM, for , , and secure multiplexing of hardware, as they forgo built-in mechanisms for full . They can also execute directly on bare metal.

Construction Process

The construction of a unikernel involves compile-time , where the application's and selected operating system libraries are integrated and compiled into a single, standalone tailored to the specific . This process eliminates the traditional separation between user-space and kernel-space components, resulting in a minimal that runs directly on a or bare metal in a single-address-space model. Developers use specialized build systems to achieve this, such as OPAM for OCaml-based systems like MirageOS, which resolves dependencies and performs static type checking to ensure only necessary components are included. Library selection is a critical step, allowing developers to link solely the required modules—such as a TCP/IP stack for network-dependent applications—while discarding unused code to minimize the image footprint, often achieving sizes under 5 MB. In systems like Unikraft, this is facilitated through modular micro-libraries (e.g., allocators or drivers) configured via manifests or Kconfig-based tools, where users specify dependencies like for networking or for libc support. Cross-compilation targets architectures such as x86 or , with optimizations like and link-time optimization (LTO) further reducing bloat during the compilation phase. The tooling workflow typically begins with configuration using graphical interfaces like or declarative files (e.g., Config.uk in Unikraft), followed by fetching sources, compiling the core and libraries, and linking into a platform-specific image deployable on hypervisors such as KVM or or directly on bare metal. Once built, the immutable unikernel image boots directly without , requiring full recompilation for any modifications to incorporate changes statically. Challenges arise in accommodating dynamic requirements, addressed through ahead-of-time static analysis or predefined configuration decisions to maintain minimalism without runtime flexibility.

Benefits and Challenges

Advantages

Unikernels offer significant performance improvements over traditional operating systems like due to their specialized, single-purpose design. Boot times are dramatically reduced, often achieving startup in milliseconds—such as under 50 ms for a DNS implementation—compared to seconds or more for full distributions. This rapid initialization stems from the absence of unnecessary kernel components and user-space initialization, enabling faster deployment in dynamic environments. Additionally, runtime overhead is minimized by eliminating traditional system calls and context switches through a single-address-space model, resulting in up to 30% faster I/O operations in certain benchmarks, with some cases showing over 200% throughput gains for applications like . Memory footprints are also substantially smaller, typically ranging from 1-10 MB—such as 8 MB for a unikernel or 11 MB for a syscall-compatible variant—versus over 100 MB for minimal kernels, allowing for denser resource packing in virtualized settings. In terms of security, unikernels reduce the by compiling only the essential code required for the application, excluding unused services, shells, and general-purpose features that could introduce vulnerabilities. This minimalism has been shown to mitigate a significant portion of common errors, such as 25% of memory-related vulnerabilities in software like , through compile-time specialization and . The lack of a privileged kernel-user and the ability to leverage hardware isolation further enhance , making more feasible due to the reduced codebase size—often 4-5 times fewer lines of code than equivalents. Efficiency gains make unikernels particularly suited for and , where resource utilization in multi-tenant environments is critical; their small size enables higher density of instances per host, improving overall system throughput. They align well with serverless and Function-as-a-Service (FaaS) models by supporting quick scaling and low-latency invocation without the overhead of full OS stacks. Furthermore, static compilation ensures deterministic behavior, eliminating runtime variability from .

Limitations

Unikernels present several development hurdles that complicate their use in practice. is particularly challenging due to the absence of standard tools like gdb or , as the monolithic structure of the compiled image hinders isolation of issues and requires attaching debuggers to the underlying monitor. Additionally, the limited forces developers to reimplement or port code manually, as many unikernels lack full compatibility or support for dynamic linking, leading to compatibility issues with existing dependencies. The immaturity of unikernel tooling further exacerbates these issues. There is a notable gap in support for dynamic languages and integrated environments, with recompilation of the entire required even for minor changes, unlike the incremental updates possible in containerized environments. Compatibility with legacy applications remains problematic, as edge cases often break due to incomplete of traditional OS behaviors, and dependency management tools struggle with bundling complex libraries. Scalability limitations restrict unikernels' applicability to certain workloads. Their single-process design makes them less flexible for multi-process applications, often necessitating the of software into multiple separate unikernels, which increases complexity and potential technology lock-in. Networking support beyond basic functionality poses ongoing challenges, and the higher initial engineering costs for porting and maintenance deter broader use, particularly in scenarios. Surveys as of 2020 highlight criticisms regarding unikernels' maturity for production-scale workloads, with difficulties cited as key barriers to , though recent 2025 developments such as Unikraft's $6 million launch and research demonstrating performance advantages over containers in indicate ongoing efforts to address these issues.

Implementations

Major Unikernel Systems

MirageOS is a library operating system developed in , primarily focused on constructing secure, high-performance unikernels for network applications such as HTTP servers. It enables developers to build modular, type-safe systems by composing libraries at compile time, targeting hypervisors like and KVM. Active since its initial release in 2013, MirageOS has been deployed in production environments, including integration within Desktop for networking tasks and on AWS Elastic Compute Cloud for cloud workloads. IncludeOS is a minimal unikernel operating system designed for C++ applications, emphasizing simplicity through an "includable" approach where OS functionality is compiled directly into the application code via a simple header inclusion. This results in nano-sized images that boot quickly and run efficiently in environments or on bare . Supporting both x86 and architectures, IncludeOS prioritizes resource efficiency and ease of use for general-purpose services, with open-source availability since 2015. OSv is an open-source unikernel tailored for running unmodified Linux applications, particularly those leveraging the Java Virtual Machine (JVM), by integrating the JVM directly into the kernel for seamless execution. Developed by Cloudius Systems starting in 2013 and later evolving under ScyllaDB after the company's rebranding, OSv supports microVMs on hypervisors and focuses on rapid boot times under one second. It maintains Linux binary compatibility while optimizing for cloud workloads like database backends. Unikraft is a modular, polyglot unikernel development kit that allows construction of customized operating systems using libraries in languages such as C and , with built-in support for deployment. Launched in 2018, it emphasizes fast build times and configurability for specific performance needs, producing minimal VMs compatible with and APIs. As of 2025, Unikraft has seen updates and funding to enhance support for AI workloads, including optimizations for inference in cloud-native settings. Other notable systems include Rumprun, a lightweight unikernel derived from NetBSD's rump kernels, which enables the execution of existing POSIX-compliant applications on without major modifications. NanoVMs specializes in WebAssembly-focused unikernels, allowing WASM binaries to run as secure, high-performance VMs with rapid deployment across clouds. Additionally, adaptations of the RTOS have emerged in 2025 experiments, trimming it into unikernel forms for systems to boost application performance through tighter integration.

Comparative Features

Unikernels vary significantly in their language support, which influences their safety, performance, and developer accessibility. MirageOS primarily uses OCaml, a functional language that emphasizes type safety and immutability, enabling robust error handling and reduced attack surfaces through compile-time guarantees. In contrast, IncludeOS is built around C++, leveraging its performance-oriented features like manual memory management and low-level optimizations for high-speed cloud services, though this introduces potential vulnerabilities if not carefully managed. Unikraft offers greater flexibility by supporting multiple languages through pre-built images and modular libraries, accommodating C, Rust, and others, which facilitates porting diverse applications without rewriting code. Target environments also differ, tailoring unikernels to specific deployment needs. OSv and MirageOS focus on cloud and virtualization settings, with OSv designed for unmodified applications in and serverless contexts on platforms like Amazon EC2. MirageOS similarly targets cloud and mobile, running under or KVM hypervisors for networked applications. For embedded and scenarios, Zephyr RTOS can operate as a unikernel with its lightweight footprint, supporting resource-constrained devices through modular components. Rumprun extends to both embedded/ and virtualized environments, enabling POSIX-compliant apps on bare hardware, , or KVM. compatibility highlights these distinctions: Unikraft and Rumprun broadly support and KVM alongside , while IncludeOS emphasizes for virtual hardware in cloud setups. Feature sets reflect trade-offs in modularity, minimalism, and efficiency. Unikraft's pluggable libraries allow fine-grained customization with over 100 components, enabling tailored builds that balance functionality and size, such as kilobyte-scale idle memory usage. IncludeOS prioritizes minimalism with zero-overhead OS integration and no virtual memory costs, resulting in boot times of tens of milliseconds and few-megabyte footprints, though it forgoes extensive debugging in production for speed. MirageOS exemplifies size/performance trade-offs, producing a web server unikernel around 0.7 MB with startup in milliseconds, optimized for event-driven networking without preemptive threading.
UnikernelLanguage SupportPrimary TargetsKey FeaturesExample Size/Performance
MirageOSCloud, mobile (Xen/KVM)Event-driven, type-safe libraries~0.7 MB web server, ms startup
IncludeOSC++Cloud VMs ()Zero-overhead, no VMFew MB, 10s ms boot
UnikraftMulti (C, Rust, etc.)Cloud, embedded (/KVM/)Pluggable libs, modularKB idle memory, 20 ms cold-start
OSvMulti (JVM, Node.js, etc.)Cloud microservicesFast build/deploy6-7 MB overhead, 3s build
RumprunMulti (C, Go, , etc.)Embedded/IoT, virtualized (/KVM)POSIX-compatibleEfficient for unmodified apps
ZephyrPrimarily CEmbedded/IoTModular RTOS componentsLow-resource, single address space
Maturity metrics underscore evolving adoption, with variations in debugging support. Unikraft has seen significant growth from 2021 to 2025, evidenced by over 3,200 GitHub stars, 100+ contributors, and $6 million in funding by late 2025, alongside integrated for both application and OS code using standard tools. MirageOS maintains steady maturity through version releases up to 4.10.3 in October 2025 and self-hosted infrastructure, but relies on OCaml-specific tools with limited runtime introspection. IncludeOS offers via GDB-like integration during development, though production builds minimize overhead at the expense of . OSv and Rumprun provide POSIX-aligned for broader compatibility, supporting established ecosystems but with less recent activity compared to Unikraft's momentum.

Applications

Primary Use Cases

Unikernels are particularly suited for and , where they facilitate the deployment of in Function-as-a-Service (FaaS) platforms as lightweight alternatives to container-based systems like . The UniFaaS platform, for example, employs MirageOS unikernels to execute serverless functions efficiently, offering hypervisor-level isolation and rapid invocation for edge-deployed workloads. MirageOS further enables fast-scaling by compiling applications into specialized machines that integrate seamlessly with infrastructures, reducing deployment overhead for distributed services. In edge and (IoT) environments, unikernels address the challenges of resource-constrained devices, such as sensors, by providing a minimal that supports efficient, single-purpose operations. IncludeOS, a C++-based unikernel, powers intrusion detection systems on IoT sensors, enabling monitoring and threat response with modular networking capabilities tailored to low-power hardware like devices. Unikernels also enhance secure firmware updates for IoT ecosystems by limiting the through code minimization, allowing verifiable over-the-air deployments across large-scale device networks while maintaining . For tasks, unikernels are applied in networking appliances, such as firewalls, where their streamlined ensures low-latency packet processing in virtualized settings. IncludeOS-based firewalls, implemented as virtual unikernel network functions (VUNFs) on KVM hypervisors, handle complex rule sets effectively, supporting high-throughput scenarios in and virtual Evolved Packet (vEPC) deployments. In 2025 trends, Unikraft unikernels are emerging for at the edge, enabling the execution of models on specialized, lightweight virtual machines that scale rapidly in distributed pipelines. Unikernels find critical application in security-sensitive areas, including isolated workloads for and healthcare, where they support to safeguard data in use. Integration with hardware enclaves like Secure Encrypted Virtualization (SEV) allows unikernels to encrypt application memory, protecting sensitive information such as financial transactions or patient health records from unauthorized access by cloud providers or hypervisors. Their reduced code surface further bolsters by minimizing potential vulnerabilities, aiding in these high-stakes domains. Unikernels demonstrate significant performance advantages in boot times, memory usage, and certain workload efficiencies compared to traditional operating systems and containers. For instance, Unikraft-based unikernels typically boot in a few milliseconds, representing two orders of magnitude faster than Linux-based systems, which often require around 30 seconds for full initialization. Similarly, these systems maintain a minimal memory footprint of 2-6 MB during operation, enabling deployment on resource-constrained environments without the overhead of full OS kernels. In I/O-intensive scenarios, while results vary by implementation, some unikernels achieve significantly higher throughput than containers in certain network-bound tasks, such as up to an order of magnitude in Go-based workloads, though containers may edge out in multi-threaded I/O due to their shared kernel optimizations. Adoption of unikernels began in the early as a focus for specialized workloads, evolving into production use by the . A notable example is OSv, developed by Cloudius Systems and later maintained under , which runs unmodified applications in a secure microVM environment for database and serverless deployments. As of 2025, industry explorations indicate growing integration in AI and cloud sectors, with platforms like Tyk.io developing unikernel-based gateways for reduced latency and NanoVMs leveraging (WASM) for lightweight, secure executions in . Recent evaluations highlight unikernels' efficiency in specific domains. In CPU-bound tasks, Unikraft implementations show 1.7x to 2.7x speedup over virtual machines, attributed to the elimination of unnecessary OS layers. Antmicro's 2025 exploration of RTOS as a unikernel further supports gains in applications through code trimming and direct access, though exact metrics depend on workload specialization. Security analyses emphasize a reduced , with unikernel codebases often 90% smaller than full OS equivalents—typically 500 KB to 32 MB—facilitating comprehensive audits and minimizing exposure. Emerging trends point to deeper integration with orchestration tools like , where platforms such as Unikraft enable seamless management of unikernel deployments alongside containers. In November 2025, Unikraft announced backend support for MirageOS unikernels, improving compatibility and performance across devices. However, mainstream adoption faces hurdles from immature tooling for and multi-application support, limiting widespread use beyond niche scenarios. As of late 2025, emerging trends suggest increasing adoption of unikernels in edge applications, driven by their low-latency boot times and efficiency in inference workloads on resource-limited devices.

References

  1. [1]
    [PDF] Unikernels: library operating systems for the cloud - CS@UCSB
    Abstract. We present unikernels, a new approach to deploying cloud services via applications written in high-level source code. Unikernels are.
  2. [2]
    Unikernels - Rethinking Cloud Infrastructure
    What are unikernels? Unikernels are specialised, single-address-space machine images constructed by using library operating systems.Blog · Projects · Resources · Contribute
  3. [3]
    Unikernels: The Rise of the Virtual Library Operating System
    Jan 1, 2014 · These unikernels are single-purpose libOS VMs that perform only the task defined in their application source and configuration files, and they ...
  4. [4]
    [PDF] Unikernels: General Introduction - ASPLOS'22 Tutorial
    Mar 1, 2025 · Definition. 10. Unikernel: application + dependencies + thin OS compiled as a static binary running on top of a hypervisor ¹. ¹ Madhavapeddy et ...
  5. [5]
    [PDF] Unikernels: Library Operating Systems for the Cloud
    Abstract. We present unikernels, a new approach to deploying cloud services via applications written in high-level source code. Unikernels are.
  6. [6]
    [PDF] 1 Unikernels: Rise of the Virtual Library Operating System
    The basic enabling technology for the cloud is operating-system virtualization such as Xen1 or VMWare, which allows customers to multiplex VMs. (virtual ...Missing: bloat | Show results with:bloat
  7. [7]
    [PDF] Exokernel - PDOS-MIT
    In the exokernel architecture, a small kernel securely exports all hardware resources through a low- level interface to untrusted library operating systems.Missing: unikernel historical
  8. [8]
    [PDF] Linkage in the Nemesis Single Address Space Operating System
    May 9, 1994 · Nemesis is also a native operating system, rather than one running over another operating system such as Mach. Writing programs in this manner ...Missing: 1990s | Show results with:1990s
  9. [9]
    Celebrating 15 Years of the Xen Project and Our Future
    Oct 23, 2018 · It's been an incredible journey from Xen's early beginnings in the University, to making our first open source release in 2003, to building a ...
  10. [10]
    Xen Project Releases Mirage OS, Welcomes ARM as Newest Member
    Jul 9, 2013 · Mirage OS v1.0 is a unikernel for constructing secure, cost-effective and high-performance network applications that run across a variety of ...
  11. [11]
    Unikernels: library operating systems for the cloud
    We present unikernels, a new approach to deploying cloud services via applications written in high-level source code.Missing: key timeline
  12. [12]
    Unikernels: the rise of the virtual library operating system
    What if all the software layers in a virtual appliance were compiled within the same safe, high-level language framework?
  13. [13]
    (PDF) IncludeOS: A Minimal, Resource Efficient Unikernel for Cloud ...
    Dec 5, 2015 · In this paper we present IncludeOS, a single tasking library operating system for cloud services, written from scratch in C++. Key features ...Missing: launch | Show results with:launch
  14. [14]
    [PDF] OSv—Optimizing the Operating System for Virtual Machines - USENIX
    Jun 19, 2014 · OSv is a new guest OS designed for single applications on cloud VMs, aiming to run faster and with a smaller image than traditional OSs.
  15. [15]
    On rump kernels and the Rumprun unikernel - Xen Project
    Aug 6, 2015 · The Rumprun unikernel, based on the driver components offered by rump kernels, provides a means to run existing POSIX applications as unikernels on Xen.
  16. [16]
    [PDF] Jitsu: Just-In-Time Summoning of Unikernels - USENIX
    May 4, 2015 · The specific contributions of this paper are thus: a de- scription of how to build efficient, secure unikernels on the new open-source Xen/ARM ( ...
  17. [17]
    Unikraft and the Coming of Age of Unikernels - USENIX
    Jul 12, 2021 · Unikraft is a novel micro-library OS that (1) fully modularizes OS primitives so that it is easy to customize the unikernel and include only relevant ...Missing: 2018 | Show results with:2018
  18. [18]
    [PDF] Unikraft: Fast, Specialized Unikernels the Easy Way - arXiv
    Apr 26, 2021 · The kernel should be fully modular in order to allow for the unikernel to be fully and easily customizable. In Unikraft, OS primitives such as ...
  19. [19]
    Unikraft is a fast, secure and open-source Unikernel Development ...
    Unikraft powers the next-generation of cloud native applications by enabling you to radically customize and build custom OS/kernels.Unikraft Guides · Unikraft's Documentation · Concepts · PerformanceMissing: 2018 2021 USENIX
  20. [20]
    Using Zephyr RTOS as a unikernel for improved application ...
    Unikernels help increase the performance of specialized systems by tightly coupling specific applications with a heavily trimmed OS, and ...Missing: adaptations | Show results with:adaptations
  21. [21]
    Reflections on Unikernels - Dave Scott
    Unikernels allow us to explore new ideas: to rethink old OS interfaces and to remove unnecessary layers of code accumulated over the last several decades.Missing: historical precursors embedded
  22. [22]
    [PDF] Unikernels: Library Operating Systems for the Cloud
    Abstract. We present unikernels, a new approach to deploying cloud services via applications written in high-level source code. Unikernels are.Missing: Rise | Show results with:Rise
  23. [23]
    Build Process - Unikraft
    Unikraft's build process includes configuring, fetching source code, compiling, and linking. Configuration is done using Kconfig and make menuconfig.
  24. [24]
    Performance - Unikraft
    Unikraft unikernels using mainstream, off-the-shelf applications boot in a few milliseconds, require a few MBs to run, and can yield a 1.7x-2.7x performance ...Missing: seconds | Show results with:seconds
  25. [25]
    [PDF] Unikernels: The Next Stage of Linux's Dominance
    Apr 10, 2019 · In this paper, we posit that an up- streamable unikernel target is achievable from the Linux kernel, and, through an early Linux unikernel ...
  26. [26]
    [PDF] A Syscall-Level Binary-Compatible Unikernel
    Abstract—Unikernels are minimal single-purpose virtual machines. They are highly popular in the research domain due to the ben- efits they provide.
  27. [27]
    [PDF] Unikernels as Processes - People
    Oct 13, 2018 · Nexen [41] splits the hypervisor (Xen in this case) into two pieces, one with higher privileges and in charge of managing the MMU. 7 CONCLUSION.Missing: integrations | Show results with:integrations
  28. [28]
    Current State Survey of Unikernels - Fixstars Corporation Tech Blog
    Jul 21, 2025 · In this article, we explore the potential of Unikernels as a means to achieve desired functionality with a minimal machine image size on ...Missing: timeline | Show results with:timeline
  29. [29]
    Welcome to MirageOS
    MirageOS is a library operating system that constructs unikernels for secure, high-performance network applications across a variety of cloud computing and ...Announcing MirageOS 4.0.0 · Blog · Docs · Community
  30. [30]
    MirageOS is a library operating system that constructs unikernels
    MirageOS is a library operating system that constructs unikernels for secure, high-performance network applications across various cloud computing and mobile ...
  31. [31]
    How MirageOS Powers Docker Desktop
    Apr 6, 2022 · MirageOS networking libraries transparently handle the traffic of millions of containers, simplifying many developers' experience every day.
  32. [32]
    unikernel/mirage - Docker Image
    Xen and KVM power many public clouds; MirageOS unikernels are currently running on Amazon's Elastic Compute Cloud and Google Compute Engine, and maybe others!
  33. [33]
    includeos/IncludeOS: A minimal, resource efficient ... - GitHub
    IncludeOS is an includable, minimal unikernel operating system for C++ services running in the cloud and on real HW.Missing: 2014 | Show results with:2014
  34. [34]
    Technology | IncludeOS
    IncludeOS allows you to run your application in the cloud without an operating system. IncludeOS adds operating system functionality to your application ...
  35. [35]
    IncludeOS: A Minimal, Resource Efficient Unikernel for Cloud Services
    In this paper we present IncludeOS, a single tasking library operating system for cloud services, written from scratch in C++. Key features include ...
  36. [36]
    OSv - the operating system designed for the cloud
    OS v is the open-source versatile modular unikernel designed to run unmodified Linux applications securely on micro-VMs in the cloud.
  37. [37]
    cloudius-systems/osv: OSv, a new operating system for the cloud.
    OSv is an open-source versatile modular unikernel designed to run single unmodified Linux application securely as microVM on top of a hypervisor.
  38. [38]
    The ScyllaDB Story
    This was Cloudius Systems and its product OSv. OSv's main targets were JVM-based applications that are weakly bound to the OS due to the managed runtime.Missing: unikernel | Show results with:unikernel
  39. [39]
    Invest In ScyllaDB Stock | Buy Pre-IPO Shares - EquityZen
    ScyllaDB was founded under the name Cloudius Systems. As Cloudius Systems, the company pioneered the unikernel trend with the development of OSv, designed ...
  40. [40]
    Unikraft | Xen Project
    Unikraft is an open-source project for building efficient, secure unikernels. It provides customizable libraries and tools to create lightweight, single-purpose ...
  41. [41]
    Unikraft Launches With $6M to Drive Dramatic New Efficiencies in ...
    Oct 10, 2025 · Unikraft Launches With $6M to Drive Dramatic New Efficiencies in Scale and Cost for Cloud Computing in the AI Era.<|control11|><|separator|>
  42. [42]
    Running WASM Unikernels - NanoVMs
    WASM is a new way of transpiling high level languages to a common binary format. Here we show how we can take WASM and run it as a unikernel.
  43. [43]
  44. [44]
    The Rumprun unikernel and toolchain for various platforms - GitHub
    The Rumprun unikernel supports applications written in, for example but not limited to: C, C++, Erlang, Go, Java, Javascript (node.js), Python, Ruby and Rust.Missing: targets | Show results with:targets
  45. [45]
    Reducing mirageos image size using ocamlclean? - OCaml Discuss
    Aug 27, 2018 · ... Web Server 0.673 MB (and 0.172 MB after ocamlclean). I wonder why we cannot have a similar size for native-code mirageos? 1 Like. samoht ...
  46. [46]
    Unikraft Launches With $6M to Drive Dramatic New Efficiencies in ...
    Oct 10, 2025 · Unikraft Launches With $6M to Drive Dramatic New Efficiencies in Scale and Cost for Cloud Computing in the AI Era · Cloud economies of scale for ...Missing: adoption | Show results with:adoption
  47. [47]
    Debugging a Unikernel - Unikraft
    Since the application and OS are linked into a single binary, debuggers can be used on the running unikernel to debug both application and OS code at the same ...Missing: MirageOS OSv
  48. [48]
  49. [49]
    Developing and debugging IncludeOS applications
    Nov 19, 2018 · Developing and debugging IncludeOS applications. One of the criticisms raised against Unikernels is that they are hard to debug.
  50. [50]
    [PDF] Demonstrating the Practicality of Unikernels to Build a Serverless ...
    We are planning to integrate the proposed unikernel-based approach into an orchestration framework such as Kubernetes. The orchestration will help evaluate ...
  51. [51]
    [PDF] UIDS: Unikernel-based Intrusion Detection System for the Internet of ...
    Our prototype is based on the IncludeOS unikernel, ensuring low resource utilization, high modularity, and a minimalist code surface. In particular, we evaluate ...
  52. [52]
    [PDF] Enterprise IoT Security and Scalability: How Unikernels can Improve ...
    Dec 9, 2016 · Companies producing the IoT devices (e.g., Smart. Light Bulbs, Heat Sensors) need ways of updating the mil- lions of deployed devices. Compared ...
  53. [53]
    Performance evaluation of a firewall service based on virtualized ...
    Jan 4, 2024 · This paper presents performance evaluation of a firewall service based on IncludeOS unikernels. It shows that IncludeOS unikernels achieve promising ...
  54. [54]
    Are Unikernels the Answer for Next-Gen AI Cloud Workloads?
    Oct 23, 2025 · Unikernels surfaced about 10 years ago, but were nearly forgotten amid Docker's emerging popularity. AI's crushing demands on infrastructure ...
  55. [55]
    Confidential Computing with AMD SEV Enabled Unikernels
    Confidential computing is a term to that describes protecting data in use and is a part of the end to end encryption framework. What is End to End Encryption?Missing: healthcare | Show results with:healthcare
  56. [56]
    [1911.06260] A Security Perspective on Unikernels - arXiv
    Nov 14, 2019 · In this work, we provide an exhaustive description of the unikernel ecosystem; we demonstrate unikernel vulnerabilities and further discuss the security ...Missing: finance healthcare confidential
  57. [57]
    Are we getting Cloud Deployments wrong and are Unikernels the ...
    Nov 5, 2023 · As shown, Unikraft has cold boot times that are 2 orders of magnitude less than Linux; one could even argue that those boot times are no longer ...Missing: benchmarks | Show results with:benchmarks<|separator|>
  58. [58]
    Unikernels vs. Containers: A Runtime-Level Performance ... - arXiv
    Sep 9, 2025 · As the allocated memory is reduced to 128 MB, the Docker container becomes the superior platform, outperforming the unikernel. The throughput of ...Missing: 10MB 100MB
  59. [59]
    Unikernels - Xen Project Wiki
    Jun 11, 2021 · A Unikernel, on the other hand, is (generally) single-purpose. It is not designed to run on hardware, and so lacks the bloat and complexity of ...
  60. [60]
    Unikernels and API management: The future of performance ... - Tyk.io
    Apr 16, 2025 · Lightning-fast performance – faster boot times and lower API latency. Resource efficiency – reduced CPU, memory, and storage overhead.
  61. [61]
    Deploying Tyk with Unikraft: Exploring the alignment of unikernels ...
    May 21, 2025 · Is it feasible yet to deploy a unikernel-based Tyk API Gateway? Read on to discover how we got on with our proof of concept (PoC).Missing: NanoVMs | Show results with:NanoVMs
  62. [62]
    Unikernels are secure. Here is why.
    Jul 10, 2017 · Unikernels use sophisticated build systems that analyze the code you're using and only link in the code that is actually used. The unused code ...Missing: finance healthcare confidential
  63. [63]
    [PDF] Assessing Unikernel Security
    Apr 2, 2019 · • Rumprun unikernels were run on Xen 4.8.0 on Ubuntu 16.04.2 LTS x86_64. • We used the latest version of Rumprun at the time of testing ...
  64. [64]
    Demystifying Open-Source Orchestration of Unikernels With Unik
    Apr 11, 2023 · Financial services and healthcare organizations often use this approach to satisfy industry-specific regulations while maintaining ...
  65. [65]
    Unikernels will make a comeback in 2025 - YouTube
    Jan 20, 2025 · Today's guest in our Prediction Video Series is Ram Iyengar, Chief Evangelist at Cloud Foundry Foundation (CFF). Iyengar shares his 2025 ...Missing: survey | Show results with:survey