{"id":131603,"date":"2026-04-23T13:04:10","date_gmt":"2026-04-23T13:04:10","guid":{"rendered":"https:\/\/www.hostinger.com\/uk\/tutorials\/what-is-hermes-agent\/"},"modified":"2026-04-23T13:04:10","modified_gmt":"2026-04-23T13:04:10","slug":"what-is-hermes-agent","status":"publish","type":"post","link":"\/uk\/tutorials\/what-is-hermes-agent","title":{"rendered":"What is Hermes Agent? How it works and what makes it different"},"content":{"rendered":"<p>Hermes Agent is an open-source, autonomous AI agent framework from Nous Research, released in February 2026 under the MIT license.<\/p><p>It runs on self-hosted infrastructure as an <strong>always-on service<\/strong>, not a per-session chat tool. It uses a large language model (LLM) as its <strong>reasoning engine<\/strong>, a set of tools for <strong>user interaction<\/strong>, and a multi-layer <strong>memory system<\/strong> that carries context across sessions.<\/p><p>While many AI assistants excel at one-off questions, they struggle with workflows that unfold over days. Hermes Agent takes a different approach. Built around persistence, it retains memory, develops reusable skills, and runs quietly in the background.<\/p><p>This shift moves beyond isolated interactions toward continuous, self-hosted AI workflows where progress compounds over time.<\/p><p><\/p><h2 class=\"wp-block-heading\" id=\"h-what-is-hermes-agent\"><strong>What is Hermes Agent?<\/strong><\/h2><p>Hermes Agent is an open-source, MIT-licensed <a href=\"\/uk\/tutorials\/what-are-ai-agents\">AI agent<\/a> framework that runs 24\/7 on a self-hosted infrastructure.<\/p><p>It handles multi-step tasks on its own, uses tools such as a terminal and a browser, and keeps memory across sessions.<\/p><p>Nous Research, the lab behind the Hermes, Nomos, and Psyche model families, released Hermes Agent in February 2026 as its first standalone agent framework.<\/p><p>Running as a background process, Hermes Agent receives instructions through platforms like Telegram, Discord, or Slack, executes tool calls on your machine, and continues working even after you&rsquo;ve closed the chat.<\/p><p>As a result, the same agent can retain context, build reusable skills, and improve over time.<\/p><p>Hermes Agent sits alongside other open-source agents but takes a more infrastructure-first approach. It targets people who&rsquo;d rather run their own AI agent on a <a href=\"\/uk\/tutorials\/what-is-vps-hosting\">virtual private server (VPS)<\/a> or a home server than rely on a managed cloud service.<\/p><p>This is because it operates as part of your infrastructure, not as something you open in a browser or use as a coding assistant embedded in an IDE.<\/p><h2 class=\"wp-block-heading\" id=\"h-how-hermes-agent-works\"><strong>How Hermes Agent works<\/strong><\/h2><p>Hermes Agent runs on your server, takes input, plans the next step with a language model, executes tools, stores results in memory, and then repeats until the task is complete.<\/p><p>To get started, you&rsquo;ll need a self-hosted environment, such as a VPS or a serverless backend. Then, deploy the agent by running the installer, which sets up a Python environment and creates the agent&rsquo;s home directory at <strong>~\/.hermes\/<\/strong>.<\/p><p>From there, the Hermes Agent workflow looks like this:<\/p><ol class=\"wp-block-list\">\n<li><strong>Receiving input.<\/strong> A task reaches the agent through the CLI, a connected messaging platform, or a scheduled cron job.<\/li>\n\n\n\n<li><strong>Task planning with an <\/strong><a href=\"\/uk\/tutorials\/large-language-models\">LLM<\/a><strong>.<\/strong> The agent sends the request to the configured language model, while taking into account its current memory and available tools. The model decides the next step.<\/li>\n\n\n\n<li><strong>Tool execution.<\/strong> The agent calls the tools it needs, such as a terminal, file editor, web browser, or MCP servers, to carry out the plan. Each tool&rsquo;s output feeds back into the loop.<\/li>\n\n\n\n<li><strong>Memory storage and retrieval.<\/strong> The agent writes results, facts, and reasoning to a local database. When relevant, it also stores curated memory files so future sessions can build on them.<\/li>\n\n\n\n<li><strong>Iteration and continuous operation.<\/strong> The loop repeats until the task is complete, then the agent waits for the next trigger without shutting down.<\/li>\n<\/ol><p>Together, these steps form <strong>a persistent loop<\/strong> that keeps running across tasks, platforms, and sessions.<\/p><div class=\"wp-block-image\"><figure data-wp-context='{\"imageId\":\"69ea513acf8ae\"}' data-wp-interactive=\"core\/image\" class=\"aligncenter size-large wp-lightbox-container\"><img decoding=\"async\" data-wp-class--hide=\"state.isContentHidden\" data-wp-class--show=\"state.isContentVisible\" data-wp-init=\"callbacks.setButtonStyles\" data-wp-on-async--click=\"actions.showLightbox\" data-wp-on-async--load=\"callbacks.setButtonStyles\" data-wp-on-async-window--resize=\"callbacks.setButtonStyles\" src=\"https:\/\/www.hostinger.com\/tutorials\/wp-content\/uploads\/sites\/2\/2026\/04\/how-hermes-agent-works-1024x572.jpg\" alt=\"An illustration of Hermes Agent workflow\" class=\"wp-image-146134\"><button class=\"lightbox-trigger\" type=\"button\" aria-haspopup=\"dialog\" aria-label=\"Enlarge\" data-wp-init=\"callbacks.initTriggerButton\" data-wp-on-async--click=\"actions.showLightbox\" data-wp-style--right=\"state.imageButtonRight\" data-wp-style--top=\"state.imageButtonTop\">\n\t\t\t<svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"12\" height=\"12\" fill=\"none\" viewbox=\"0 0 12 12\">\n\t\t\t\t<path fill=\"#fff\" d=\"M2 0a2 2 0 0 0-2 2v2h1.5V2a.5.5 0 0 1 .5-.5h2V0H2Zm2 10.5H2a.5.5 0 0 1-.5-.5V8H0v2a2 2 0 0 0 2 2h2v-1.5ZM8 12v-1.5h2a.5.5 0 0 0 .5-.5V8H12v2a2 2 0 0 1-2 2H8Zm2-12a2 2 0 0 1 2 2v2h-1.5V2a.5.5 0 0 0-.5-.5H8V0h2Z\"><\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div><h2 class=\"wp-block-heading\" id=\"h-what-makes-hermes-agent-different-from-other-ai-agents\"><strong>What makes Hermes Agent different from other AI agents<\/strong><\/h2><p>Hermes Agent is a standalone, self-hosted agent that runs <strong>continuously<\/strong>, acts <strong>autonomously<\/strong>, and <strong>improves over time<\/strong>.<\/p><p>It ships with <strong>memory, skills, messaging, and scheduling already included<\/strong>, so you don&rsquo;t have to build everything from scratch. You can still swap the LLM, add tools, or customize its behavior through a <strong>SOUL.md<\/strong> file.<\/p><p>Then, after a task is done, Hermes Agent captures the work, turning complex tasks into reusable skills that future runs can build on.<\/p><p>For instance, if you ask it to debug a failing deployment and it works through the fix across several steps, it writes that process down as a skill. The next time a similar deployment issue comes up, it already knows what worked.<\/p><p>This is a category that <strong>most AI tools don&rsquo;t fit<\/strong> into, as they often fall into one of three buckets: chatbots that <strong>answer one question at a time<\/strong>, IDE assistants <strong>scoped to your editor<\/strong>, or orchestration frameworks like LangChain that give you building blocks but<strong> leave memory, scheduling, and the learning loop up to you<\/strong>.<\/p><h3 class=\"wp-block-heading\"><strong>Hermes Agent vs. OpenClaw<\/strong><\/h3><p>Hermes Agent and <a href=\"\/uk\/tutorials\/what-is-openclaw\">OpenClaw<\/a> are both self-hosted, autonomous AI agents, but they take different approaches.<\/p><p>Hermes focuses on a <strong>learning loop that creates reusable skills<\/strong>, while OpenClaw focuses on <strong>direct, conversational task execution on your machine<\/strong>.<\/p><p>See the table below for a more detailed comparison of Hermes Agent and OpenClaw.<\/p><div class=\"wp-block-group\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\">\n<figure tabindex=\"0\" class=\"wp-block-table\"><table><tbody><tr><td><strong>Aspect<\/strong><\/td><td><strong>Hermes Agent<\/strong><\/td><td><strong>OpenClaw<\/strong><\/td><\/tr><tr><td><strong>Core focus<\/strong><\/td><td>Self-improvement through autonomous skill creation<\/td><td>Direct task execution through natural language<\/td><\/tr><tr><td><strong>Memory model<\/strong><\/td><td>Four-tier memory, prompt files, SQLite archive, skills, and external providers<\/td><td>Long-term conversational memory<\/td><\/tr><tr><td><strong>Persistence<\/strong><\/td><td>Continuous loop with scheduled tasks and cron support<\/td><td>Always-on assistant<\/td><\/tr><tr><td><strong>Autonomy<\/strong><\/td><td>Plans, executes, and writes its own skill documents<\/td><td>Interprets intent, then acts on your infrastructure<\/td><\/tr><tr><td><strong>Hosting model<\/strong><\/td><td>Local machine, VPS, or serverless backends like Modal or Daytona<\/td><td>Local machine, Raspberry Pi, or VPS<\/td><\/tr><\/tbody><\/table><\/figure>\n<\/div><\/div><p>In case you&rsquo;re already running OpenClaw, you can migrate to Hermes without losing your existing work.<\/p><p>Simply run this<strong> <\/strong>command to import your settings, memories, skills, and API keys during the initial setup:<\/p><pre class=\"wp-block-preformatted\">hermes claw migrate<\/pre><p>This way, you&rsquo;re keeping your LLM provider configurations, messaging platform connections, and accumulated context, rather than having to set everything up from scratch.<\/p><h3 class=\"wp-block-heading\"><strong>Hermes Agent vs. Paperclip<\/strong><\/h3><p>Hermes Agent and <a href=\"\/uk\/tutorials\/what-is-paperclip-ai\">Paperclip<\/a> operate at different layers, so they work better as complements than direct competitors.<\/p><p>In practice, Hermes is the <strong>agent you interact with daily<\/strong>. Paperclip is the <strong>orchestration layer <\/strong>you use when a task requires multiple agents to coordinate.<\/p><p>That means you can run a Hermes Agent instance as a worker inside a Paperclip organization.<\/p><div class=\"wp-block-group\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\">\n<figure tabindex=\"0\" class=\"wp-block-table\"><table><tbody><tr><td><strong>Aspect<\/strong><\/td><td><strong>Hermes Agent<\/strong><\/td><td><strong>Paperclip<\/strong><\/td><\/tr><tr><td><strong>Role<\/strong><\/td><td>Single persistent agent<\/td><td>Orchestration platform for multiple agents<\/td><\/tr><tr><td><strong>Unit of work<\/strong><\/td><td>One agent with memory and skills<\/td><td>Multiple agents with defined roles, goals, and tasks<\/td><\/tr><tr><td><strong>Structure<\/strong><\/td><td>Personal AI that evolves over time<\/td><td>Organization-style hierarchy with governance<\/td><\/tr><tr><td><strong>Best fit<\/strong><\/td><td>Individual productivity, developer automation, and research<\/td><td>End-to-end workflows across agent teams<\/td><\/tr><tr><td><strong>Interaction<\/strong><\/td><td>Messaging apps, CLI, cron jobs<\/td><td>Dashboard, task system, shared context<\/td><\/tr><\/tbody><\/table><\/figure>\n<\/div><\/div><p>If you&rsquo;re interested in building a full AI organization with Paperclip and Hermes Agent, follow our tutorial on <a href=\"\/uk\/tutorials\/how-to-set-up-paperclip\">setting up a Paperclip instance<\/a>.<\/p><h2 class=\"wp-block-heading\" id=\"h-key-features-of-hermes-agent\"><strong>Key <\/strong><strong>features of Hermes Agent<\/strong><\/h2><p>Hermes Agent combines multiple features that most AI agents offer separately, such as:<\/p><ul class=\"wp-block-list\">\n<li><strong>Persistent 24\/7 execution<\/strong>. Once you deploy it as a <strong>systemd<\/strong> service, the agent continues to listen for messages, run scheduled cron tasks, and resume work after reboots. This makes long-running workflows practical, like a nightly research digest, an overnight code build, or a weekly report, without starting a new conversation each time.<\/li>\n\n\n\n<li><strong>Autonomous decision-making and skill creation<\/strong>. After complex tasks involving five or more tool calls, the agent writes a structured skill document for reuse. Skills live as Markdown files under <strong>~\/.hermes\/skills\/<\/strong> and follow the open <strong>agentskills.io<\/strong> standard, which makes them portable across compatible agents. You can also import community skills from the Skills Hub using slash commands like <strong>\/gif-search<\/strong> or <strong>\/github-pr-workflow<\/strong>. The agent can update its own skills when they become outdated.<\/li>\n\n\n\n<li><strong>Long-term memory retention<\/strong>. Hermes stores memory across four layers. Two curated files, <strong>MEMORY.md<\/strong> and <strong>USER.md<\/strong>, contain environment facts and user preferences, and are loaded into every system prompt at the start of a session. A SQLite database at <strong>~\/.hermes\/state.db<\/strong>, with FTS5 full-text search, archives each session for recall. The skills directory stores procedural memory. On top of that, pluggable providers like Honcho, Mem0, OpenViking, or Supermemory handle long-term user modeling.<\/li>\n\n\n\n<li><strong>Tool and API integration<\/strong>. More than 40 built-in tools cover web search, terminal execution, file operations like <strong>read_file<\/strong> and <strong>patch<\/strong>, browser automation, vision, image generation, text-to-speech, and subagent delegation. Tools self-register at import time, so you can add your own by placing a plugin in the user, project, or pip entry point directories.&nbsp;<\/li>\n\n\n\n<li><strong>A wide range of LLM compatibility. <\/strong>Any OpenAI-compatible endpoint works with Hermes Agent, including Nous Portal, OpenRouter, Anthropic, or a local <a href=\"\/uk\/tutorials\/what-is-ollama\">Ollama<\/a> instance.<\/li>\n\n\n\n<li><strong>Built-in MCP support.<\/strong> You can connect any MCP server over stdio or HTTP, control which tools each server exposes, and manage everything through a single <strong>config.yaml<\/strong> file.&nbsp;<\/li>\n\n\n\n<li><strong>Self-hosted deployment<\/strong>. Hermes Agent runs on any platform that supports Python 3.11, including Linux, macOS, WSL2 on Windows, and Android via Termux. It offers six terminal backends for command execution: local for speed, <a href=\"\/uk\/tutorials\/what-is-docker\">Docker<\/a> for isolation, SSH for remote servers, and serverless options like Daytona, Singularity, or Modal. Docker is the safest default on a VPS because its containers act as a security boundary.<\/li>\n<\/ul><h2 class=\"wp-block-heading\" id=\"h-what-are-the-main-use-cases-of-hermes-agent\"><strong>What are the main use cases of Hermes Agent?<\/strong><\/h2><p>Hermes Agent is best suited for <strong>technical workflows that benefit from persistence and automation<\/strong>. Its core use cases include development automation, research and data analysis, scheduled workflows, and personal AI assistance.<\/p><div class=\"wp-block-image\"><figure data-wp-context='{\"imageId\":\"69ea513ad2746\"}' data-wp-interactive=\"core\/image\" class=\"aligncenter size-large wp-lightbox-container\"><img decoding=\"async\" data-wp-class--hide=\"state.isContentHidden\" data-wp-class--show=\"state.isContentVisible\" data-wp-init=\"callbacks.setButtonStyles\" data-wp-on-async--click=\"actions.showLightbox\" data-wp-on-async--load=\"callbacks.setButtonStyles\" data-wp-on-async-window--resize=\"callbacks.setButtonStyles\" src=\"https:\/\/www.hostinger.com\/tutorials\/wp-content\/uploads\/sites\/2\/2026\/04\/hermes-agent-use-cases-1024x572.jpg\" alt=\"A visual illustration of Hermes Agent use cases\" class=\"wp-image-146135\"><button class=\"lightbox-trigger\" type=\"button\" aria-haspopup=\"dialog\" aria-label=\"Enlarge\" data-wp-init=\"callbacks.initTriggerButton\" data-wp-on-async--click=\"actions.showLightbox\" data-wp-style--right=\"state.imageButtonRight\" data-wp-style--top=\"state.imageButtonTop\">\n\t\t\t<svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"12\" height=\"12\" fill=\"none\" viewbox=\"0 0 12 12\">\n\t\t\t\t<path fill=\"#fff\" d=\"M2 0a2 2 0 0 0-2 2v2h1.5V2a.5.5 0 0 1 .5-.5h2V0H2Zm2 10.5H2a.5.5 0 0 1-.5-.5V8H0v2a2 2 0 0 0 2 2h2v-1.5ZM8 12v-1.5h2a.5.5 0 0 0 .5-.5V8H12v2a2 2 0 0 1-2 2H8Zm2-12a2 2 0 0 1 2 2v2h-1.5V2a.5.5 0 0 0-.5-.5H8V0h2Z\"><\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div><p>In a development environment, it can handle tasks such as reviewing pull requests, running tests, and managing long-running refactors &ndash; continuing work across sessions without losing context.<\/p><p>For research and data analysis, it combines browsing, code execution, and memory to gather, process, and revisit information over time.<\/p><p>It also supports scheduled workflows through built-in automation, such as recurring reports or updates delivered via messaging platforms like Telegram or Discord.<\/p><p>On a personal level, it can be a persistent assistant that adapts to your preferences, remembers your past work, and helps you streamline repetitive tasks.<\/p><h2 class=\"wp-block-heading\" id=\"h-challenges-and-limitations-of-hermes-agent\"><strong>Challenges and limitations of Hermes Agent<\/strong><\/h2><p>Hermes Agent trades convenience for control, and that comes with real operational considerations:<\/p><ul class=\"wp-block-list\">\n<li><strong>Technical overhead.<\/strong> Running a persistent agent means managing your own infrastructure, which requires familiarity with Linux, systemd, or container tools to troubleshoot issues.<\/li>\n\n\n\n<li><strong>Security risks.<\/strong> An autonomous agent with terminal access and API keys expands your attack surface. While Hermes Agent includes safeguards like a dangerous-command blocklist and sudo prompts, these may be bypassed in container setups. This means securing the host, isolating credentials, and reviewing logs falls on you.<\/li>\n\n\n\n<li><strong>Resource consumption.<\/strong> A lightweight setup can run on a low-cost VPS, but heavier workloads, like browser automation or parallel subagents, quickly increase CPU, memory, and token usage. At scale, this can strain hardware and drive up LLM costs.<\/li>\n\n\n\n<li><strong>Model limitations.<\/strong> The agent is only as reliable as the model behind it. Hermes Agent requires models with large context windows (64K+ tokens), but issues such as hallucinations, misinterpretations of tool output, or losing track of multi-step logic can still occur.<\/li>\n\n\n\n<li><strong>Learning loop latency.<\/strong> Skill creation happens after complex tasks and isn&rsquo;t immediate. If your workflows are highly varied, the system has fewer patterns to learn from, making the feedback loop less effective.<\/li>\n\n\n\n<li><strong>Platform gaps.<\/strong> Native Windows support isn&rsquo;t available (WSL2 is required), and while Android works via Termux, some voice and media features are limited due to compatibility constraints.<\/li>\n<\/ul><p>Note that none of these points make Hermes Agent unusable. They merely mean that the framework is for technical users who already manage their own infrastructure, not for those looking for a fully managed, plug-and-play assistant.<\/p><h2 class=\"wp-block-heading\" id=\"h-how-to-get-started-with-hermes-agent\"><strong>How to get started with Hermes Agent?<\/strong><\/h2><p>Getting started with Hermes Agent involves preparing a <strong>self-hosted environment<\/strong>, installing <strong>dependencies<\/strong>, configuring an <strong>LLM provider<\/strong>, and <strong>running it<\/strong> as a continuous service.<\/p><p>The first decision is where the agent will run. A setup that only works while your device is awake defeats the purpose of persistence, which is why a VPS is the more practical choice.<\/p><p>If you want to skip most of the setup, a preconfigured <a href=\"\/uk\/vps\/docker\/hermes-agent\">Hermes Agent VPS<\/a> can handle the runtime requirements out of the box.<\/p><p>If you prefer setting it up manually, start by preparing the environment. This typically means a Linux server, a macOS machine, or a WSL2 instance with Python 3.11 installed.<\/p><p>A Docker instance is optional but recommended, as it adds a layer of isolation for the terminal backend.<\/p><p>After <a href=\"\/uk\/tutorials\/docker-tutorial\">setting up Docker<\/a>, run the official Hermes Agent installer on your terminal:<\/p><pre class=\"wp-block-preformatted\">curl -fsSL https:\/\/raw.githubusercontent.com\/NousResearch\/hermes-agent\/main\/scripts\/install.sh | bash<\/pre><p>This installs core dependencies such as uv, Python, Node.js, ripgrep, and ffmpeg, and creates the <strong>~\/.hermes\/<\/strong> directory.<\/p><p>Once installed, configure the agent by selecting an LLM provider with the <strong>hermes model<\/strong> command, connecting messaging platforms like Telegram or Discord via the gateway setup, and, optionally, enabling an external memory provider with<strong> hermes memory setup<\/strong>.<\/p><p>After that, run the agent as a <strong>systemd<\/strong> service so it continues operating across reboots, and monitor logs or session history to confirm it&rsquo;s receiving input and executing tasks as expected.<\/p><?xml encoding=\"utf-8\" ?><figure class=\"wp-block-image size-large\"><a href=\"\/uk\/vps-hosting\" target=\"_blank\" rel=\"noreferrer noopener\"><img decoding=\"async\" width=\"1024\" height=\"300\" src=\"https:\/\/www.hostinger.com\/tutorials\/wp-content\/uploads\/sites\/2\/2023\/02\/VPS-hosting-banner-1024x300.png\" alt=\"\" class=\"wp-image-77934\" srcset=\"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-content\/uploads\/sites\/51\/2023\/02\/VPS-hosting-banner.png 1024w, https:\/\/www.hostinger.com\/uk\/tutorials\/wp-content\/uploads\/sites\/51\/2023\/02\/VPS-hosting-banner-300x88.png 300w, https:\/\/www.hostinger.com\/uk\/tutorials\/wp-content\/uploads\/sites\/51\/2023\/02\/VPS-hosting-banner-150x44.png 150w, https:\/\/www.hostinger.com\/uk\/tutorials\/wp-content\/uploads\/sites\/51\/2023\/02\/VPS-hosting-banner-768x225.png 768w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/a><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Hermes Agent is an open-source, autonomous AI agent framework from Nous Research, released in February 2026 under the MIT license. It runs on self-hosted infrastructure as an always-on service, not a per-session chat tool. It uses a large language model (LLM) as its reasoning engine, a set of tools for user interaction, and a multi-layer [&#8230;]<\/p>\n<p><a class=\"btn btn-secondary understrap-read-more-link\" href=\"\/uk\/tutorials\/what-is-hermes-agent\">Read More&#8230;<\/a><\/p>\n","protected":false},"author":411,"featured_media":131604,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"rank_math_title":"What is Hermes Agent? Definition, features, and how it works","rank_math_description":"Learn what Hermes Agent is, how it works, and why it stands apart from other AI agents. See its features, use cases, and how to get started.","rank_math_focus_keyword":"what is hermes agent","footnotes":""},"categories":[22640],"tags":[],"class_list":["post-131603","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-vps"],"hreflangs":[{"locale":"en-US","link":"https:\/\/www.hostinger.com\/tutorials\/what-is-hermes-agent\/","default":1},{"locale":"en-PH","link":"https:\/\/www.hostinger.com\/ph\/tutorials\/what-is-hermes-agent\/","default":0},{"locale":"en-MY","link":"https:\/\/www.hostinger.com\/my\/tutorials\/what-is-hermes-agent\/","default":0},{"locale":"en-UK","link":"https:\/\/www.hostinger.com\/uk\/tutorials\/what-is-hermes-agent\/","default":0},{"locale":"en-IN","link":"https:\/\/www.hostinger.com\/in\/tutorials\/what-is-hermes-agent\/","default":0},{"locale":"en-CA","link":"https:\/\/www.hostinger.com\/ca\/tutorials\/what-is-hermes-agent\/","default":0},{"locale":"en-AU","link":"https:\/\/www.hostinger.com\/au\/tutorials\/what-is-hermes-agent\/","default":0},{"locale":"en-NG","link":"https:\/\/www.hostinger.com\/ng\/tutorials\/what-is-hermes-agent\/","default":0}],"_links":{"self":[{"href":"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-json\/wp\/v2\/posts\/131603","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-json\/wp\/v2\/users\/411"}],"replies":[{"embeddable":true,"href":"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-json\/wp\/v2\/comments?post=131603"}],"version-history":[{"count":0,"href":"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-json\/wp\/v2\/posts\/131603\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-json\/wp\/v2\/media\/131604"}],"wp:attachment":[{"href":"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-json\/wp\/v2\/media?parent=131603"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-json\/wp\/v2\/categories?post=131603"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.hostinger.com\/uk\/tutorials\/wp-json\/wp\/v2\/tags?post=131603"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}