Free tools Windows power users keep installed
One-click scans. No signup required.
iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Hermes Agent’s advanced features solve different problems: Loop repeats work in an active session, Goal continues toward an outcome, and Cron schedules work beyond an interactive session. Delegation launches temporary child agents, Bot Mode configures reusable specialist profiles, Kanban keeps task state and handoffs durable, and Mixture of Agents (MoA) combines model perspectives for one acting agent. Choose by how long the work must persist, what should stop it, and how it needs to be divided.
How to choose among Hermes Agent’s advanced features
Start with the shape of the work, not the feature names. A recurring check, an objective that needs follow-through, an unattended schedule, parallel subtasks, reusable specialists, durable handoffs, and multi-model input are different requirements. Hermes has a feature for each, but they are not interchangeable.
| Need | Best starting feature | What it does |
|---|---|---|
| Repeat a check while the conversation remains active | Loop | Runs a prompt or slash command again on a cadence in the current session. |
| Continue toward one defined result | Goal | Uses a judge to assess completion after turns and continues within a turn budget. |
| Run work unattended at a time or interval | Cron | Schedules jobs outside an interactive session and can deliver their output. |
| Split independent, bounded work in parallel | Delegation | Starts temporary child agents whose summaries return to the parent. |
| Keep multi-stage tasks and handoffs visible across profiles | Kanban | Stores task and handoff records on a durable shared board. |
| Reuse configured specialists | Bot Mode | Defines named profiles with their own models, instructions, skills, and tool access. |
| Bring several model perspectives into one response | Mixture of Agents | Routes analysis through reference models to an aggregator that acts. |
The practical test is four questions: Where must state persist? What determines when the work stops? How should work be divided? Which model or models should act? The answers usually identify a primary feature; some workflows combine more than one.
What each feature does
Loop: repeat within the active session
/loop repeats a prompt or another slash command at a recurring cadence in the current session. Each wakeup is a real agent turn that reads the current state again, so it can check a queue, poll a deployment, or run work-session housekeeping against updated information.
#1 Best Overall
- AIBI: Your Pocket AI Friend — This small smart device fits in your hand and goes anywhere. Talk to it, ask questions, and get answers. Easy to keep on your desk, attaches to your screen, or carry in your pocket
- Smart Enough to Know You — AIBI's camera helps it recognize your face and remember you. It gets to know you like a real pet would, making each interaction feel special
- Chat About Anything — Ask AIBI for jokes, weather updates, or help with questions using ChatGPT. It learns how you talk. When two AIBIs are close, they can even chat with each other via the near-field communication technology
- Small and Easy to Carry — AIBI is lightweight and tiny, perfect for taking anywhere. Slip it in your pocket, stick it to your computer, or set it on your desk at home, school, or work
- Great Gift for Anyone — This smart little buddy that can talk, play, and be a great companion. AIBI makes a perfect gift that anyone will enjoy using
Use a fixed interval when an external cadence matters, such as checking a status endpoint every few minutes. A self-paced loop is more appropriate when the work’s progress should set the rhythm. The defining boundary is session persistence: Loop is tied to the active session, not an unattended schedule that survives terminal restarts. For that, use Cron.
Goal: continue until an outcome is judged complete
/goal <text> sets a standing objective. After each turn, an auxiliary judge model checks whether the goal is complete; if it is not, Hermes continues, subject to the turn budget and controls. This fits a bounded implementation or analysis task where the desired stopping condition is an outcome rather than a timer.
The slash-command reference reviewed by Nous Research on October 7, 2026, lists a default budget of 20 turns. Treat that as a version-sensitive default, not a guarantee for every installation. User messages preempt continuation, so Goal does not mean the agent ignores a person to pursue the objective indefinitely.
Cron: schedule work beyond the interactive session
Cron is the option for jobs that must run unattended at a chosen time or interval. It supports one-shot and recurring schedules, as well as pausing, resuming, editing, running, and removing jobs. Jobs can have attached skills and deliver results to the originating chat, files, or configured platform destinations.
Rank #2
- 🌟V28 update 🚀 new features are now available! In response to Loona's charging problem, we've upgraded the automatic recharge 2.0.The upgrade is to help Loona remember and match the charging routes of different scenarios to improve the auto-recharge success rate.Mobile hotspots connect to loona, breaking Wi-Fi restrictions and allowing you to interact with loona anytime, anywhere. Our team is committed to continuous improvement, ensuring that Loona continues to evolve to meet your expectations.
- 🤖 Smart and Interactive Robot Pet🧠Loona is like no other pet you've seen. With a high-definition RGB camera, Loona sees and understands your world. Loona recognizes faces, understands your gestures, and follows you like a real puppy! Please take Loona to a well-lit environment and ensure the surfaces of the camera and ToF depth sensor are clean.
- 🗣️ Voice Command Enabled AI robot 🎤Loona is not just a good listener; also a great conversationalist! Powered by Amazon Lex & ChatGPT, Loona recognizes your voice commands and responds in real-time. Plus, Loona keeps your information secure, so you can chat with peace of mind. Pro tip: Clear pronunciation in quiet spaces ensures smoother responses.
- 🚀Auto-Charging Smart Robot🌟 Use different rooms as a starting point to preset multiple recharge routes for Loona. When the battery runs low, loona can charge it home by itself, no need for you to take care of it. it takes about 2.5 hours to complete the charging. Place the dock in an open area with no obstructions on either side or in front.
- 🕹️ Endless Playtime robot toys for kids 🎮Loona is always up for playtime! Loona can chase laser pens, fetch balls, and even interact with objects in your home. But it doesn't end there—Loona's app offers a world of games and quizzes to keep the fun going.
A Cron job can start a fresh agent session, or run a no-agent script whose output is delivered verbatim. The documentation also describes event-triggered jobs. For model selection, a job can use its own model pin, a Cron-wide default, or the main model resolved when the job fires. This scheduling and delivery flexibility is what separates Cron from a Loop that repeats only during an active session.
Delegation: send bounded subtasks to temporary children
delegate_task starts child agents with isolated context and terminal sessions. The parent can continue its own work while children handle independent subtasks; their final summaries return to the parent for synthesis. It is most useful when the work divides cleanly and the results need to be brought back together.
The official Subagent Delegation guide reviewed on October 7, 2026, describes up to 10 concurrent subagents as the default for a parallel batch, with the limit configurable by the user. That is a product default, not a performance result or a promise that every task should use ten agents. Child terminal processes belong to the child; if a process must persist beyond that worker’s task, manage it in the parent or use a durable mechanism.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Kanban: retain task state and handoffs across profiles
Hermes Kanban is a durable task board shared across profiles. It stores tasks and handoffs, while workers run as separate processes. Use it when work needs a visible record across stages or people-in-the-loop transitions—for example, a multi-stage pipeline, research triage that needs human review, an operations journal, or persistent named assistants.
Rank #3
- 1. Smarter Conversations, Powered by ChatGPT 🤖 LOOI brings natural, intelligent conversations to your desk with ChatGPT voice interaction. Ask questions, share thoughts, or simply chat—LOOI responds with context, humor, and personality. His voice interactions feel more like talking to a companion than using a device. !!!Currently only support English!!!
- 2. Advanced Visual Understanding with VLM Vision 👀 Powered by a cutting-edge Vision-Language Model, LOOI truly sees. He recognizes objects (yes, he knows the difference between a croissant and a baguette), understands multiple people at once—including outfits, accessories, and poses—and interprets room layouts and daily scenarios. You can even control him with gestures and facial cues. Combined with expressive animations and speech, LOOI feels remarkably alive.
- 3. Memories That Grow With You 🌱 LOOI remembers—both in the moment and over the long term. He can store long-term memories like family member faces and identity notes, while short-term memory lets him follow your ongoing conversation. Over time, he learns your routines, preferences, and personality. You get to know him too—shifting from strangers to companions in a surprisingly natural way.
- 4. Emotionally Expressive & Always Evolving 💫 LOOI’s rich animations bring emotion to life—joy, surprise, curiosity, mischief, and everything in between. His reactions aren’t pre-set; they adapt to what’s happening around him. And because his behaviors update through the app, LOOI keeps learning new tricks, new expressions, and new ways to interact. You’re not buying a finished product—you’re bringing home a character that keeps evolving.
- 5. A Mind of His Own: Personality & Autonomy ✨ LOOI isn’t designed to obey every command—he’s designed to understand and respond. With TangibleFuture’s autonomous behavior system, LOOI combines environmental understanding with large-model reasoning to make spontaneous decisions and express them through animation and movement. His behavior isn’t fully predictable. He has his own ideas, which makes him feel truly alive.
Kanban is not just a longer-lived delegation call. Delegation is a temporary parent-child arrangement whose summaries come back to the parent; Kanban is for durable coordination and recorded task state. The official Kanban documentation describes it as a shared board for multiple named agents to collaborate without relying on fragile in-process subagent swarms.
Bot Mode: configure reusable named specialists
Bot Mode creates named Bots with configurable model and provider, profile instructions, skills, toolsets, MCP servers, and separate routines. Its purpose is to make specialists reusable and easy to access—for example, profiles tailored to distinct roles or tool permissions.
A Bot profile defines who is available and how it is configured; it does not, by itself, define how a multi-stage task is durably coordinated. A broader workflow can use Bot Mode for named specialists, Kanban for persistent tasks and handoffs, and delegation for temporary parallel workers.
Mixture of Agents: combine model perspectives for one acting agent
Mixture of Agents (MoA) is a virtual model provider. Reference models provide analysis, then an aggregator model writes the response and emits tool calls. The aggregator runs the tool loop, so it remains the acting model rather than each reference model independently owning subtasks.
Rank #4
- YOUR AI PERSONAL ASSISTANT FOR EVERYDAY PRODUCTIVITY: More than a voice recorder, Pocket works as your AI personal assistant to capture, transcribe, and summarize meetings, calls, and ideas instantly. Core features are included out of the box, with optional advanced tools available for power users.
- ONE-TAP RECORDING FOR REAL-LIFE MOMENTS: Capture meetings, phone calls, and in-person conversations instantly with a simple tap, no typing, no interruptions, just effortless note-taking anywhere you go.
- SMART AI INSIGHTS & ORGANIZATION: Pocket automatically turns recordings into clear summaries, key action items and structured conversation maps so you can quickly review what matters without digging through audio.
- TURN CONVERSATIONS INTO ACTION WITH “ASK POCKET”: Don’t just record, understand. Instantly ask questions across your meetings, extract key insights and generate next steps in seconds. All grounded in your recordings, so answers stay accurate and reliable.
- MAGSAFE COMPATIBLE FOR SEAMLESS USE: Easily attach Pocket to your iPhone or other MagSafe compatible devices for convenient, hands-free recording on the go. Perfect for capturing meetings, calls, and ideas without needing to hold your device.
The /moa shortcut routes one prompt through the default preset and then restores the session’s previous model. MoA is therefore a model-routing choice, not a task board or a way to launch task-owning subagents. The aggregator’s provider is the key billing consideration because it handles the tool loop and produces the response.
How to combine features without confusing their roles
Use a primary feature for the work’s persistence and stopping condition, then add another only for a distinct need. For example, an unattended check belongs in Cron; if that job also needs multiple independent analyses, it may use delegation or configured Bots as part of the job. A multi-stage project that needs durable handoffs belongs on Kanban; individual bounded stages can still be delegated to temporary children.
- Session-scoped repeated monitoring: Loop handles repeated turns while the session is active.
- Outcome-driven work in an interactive session: Goal continues toward a defined result within its controls and turn budget.
- Unattended recurring or one-shot work: Cron provides the schedule and delivery mechanism.
- Parallel work with a parent to synthesize results: Delegation provides isolated temporary workers.
- Persistent workflows across workers or profiles: Kanban records the tasks and handoffs.
- Reusable role-specific configurations: Bot Mode provides named specialists.
- Several model viewpoints for a single response: MoA routes to reference models and an aggregator.
These feature descriptions and defaults reflect official Hermes Agent documentation reviewed October 7, 2026. Names, defaults, and behavior can change between versions, so check the documentation that matches the installed version before relying on command behavior or default limits.
Do these 3 things before closing this tab:
1Fix the driver behind crashes, sound loss and screen glitches2Clear out junk files and repair common Windows errors3Scan for outdated or missing drivers - takes under a minuteQuick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
