{"slug": "hermes", "name": "Hermes", "category": "ai", "category_name": "AI models and assistants", "description": "Open-source, self-hosted AI agent from Nous Research for personal assistance and computer use.", "recommenders": 33, "commenters": 73, "warners": 2, "score": 38.142, "rising": 11.76, "first": "2026-04-04", "latest": "2026-10-26", "why": "HN commenters use it as an everyday personal assistant and homelab sysadmin agent, and several say it is more stable and easier to configure than OpenClaw.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 33, "neutral": 37, "compare": 5, "warn": 2}, "spark": [0, 0, 0, 0, 0, 3, 1, 8, 3, 10, 3, 5], "listed": true, "loved": ["Personal assistant", "Better than OpenClaw"], "caveat": "Model-dependent quality", "short_quote": "I switched to Hermes Agent and it's been night and day how much more stable and usable it is over OpenClaw.", "icon": true, "domain": "nousresearch.com", "github_repo": null, "official_url": "https://hermes-agent.nousresearch.com/", "pricing": "open source", "aliases": ["Hermes", "Hermes Agent", "Hermes agent", "hermes-agent"], "verdict": [{"text": "HN commenters use it as an everyday personal assistant and homelab sysadmin agent,", "cites": [{"id": 774677265, "item_id": 48417329, "url": "https://news.ycombinator.com/item?id=48417329", "by": "igorhvr", "date": "2026-06-05", "stance": "recommend", "quote": "Hermes basically rules my personal life at this point - it is a _very_ useful personal assistant.", "excerpt": "I use PI ( https://pi.dev ) and ( https://hermes-agent.nousresearch.com/ ) as the main drivers together with deepseek-v4-pro as the main model (~10M/day tokens overall there). Hermes basically rules my personal life at this point - it is a _very_ useful personal assistant. I also use it at work (integrated at Slack) and at this point it answers most of both my emails and slack messages (I calibrated https://github.co", "context": "", "use_case": "personal assistant, email and Slack replies", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 788403254, "item_id": 49275203, "url": "https://news.ycombinator.com/item?id=49275203", "by": "ljosifov", "date": "2026-08-12", "stance": "recommend", "quote": "I use Hermes as a general agent, non-coding agent, for everything that's not strictly coding.", "excerpt": "Atm OMP (oh-my-pi) with opencode-go subscription using deepseek-v4-flash-0731 (and mimo-v2.5 as advisor). Used pi before (still good, but too minimalist for all general use; works on Android under Termux btw) and OpenCode (which is ok too). I've used Codex the longest, but the $20 sub doesn't last that long. Before that Claude (and Claude on the web - about Nov'25), but nowadays with the new models not possible to do", "context": "", "use_case": "general non-coding agent", "switched_from": "", "story": "llama.cpp"}, {"id": 775318864, "item_id": 48457429, "url": "https://news.ycombinator.com/item?id=48457429", "by": "apexalpha", "date": "2026-06-08", "stance": "recommend", "quote": "I use Hermes at home. Swapped out Openclaw for this. It seems to work better with smaller contexts", "excerpt": "I use Hermes at home. Swapped out Openclaw for this. It seems to work better with smaller contexts, chuncking it up in smaller pieces. I don't code with it, I use Claude for that. But what I do do: it's a sysadmin for my homelab. It has a read-only mcp server to check the k8s status and has it's own ssh access to fix stuff after I approve it per session. It's magical. Each morning I get a small update whether the bac", "context": "homelab user", "use_case": "homelab sysadmin agent", "switched_from": "OpenClaw", "story": "Hermes Agent \u2013 Open-Source AI Agent with Persistent Memory"}, {"id": 776840512, "item_id": 48552532, "url": "https://news.ycombinator.com/item?id=48552532", "by": "xyzzy123", "date": "2026-06-16", "stance": "recommend", "quote": "I use hermes with crons and kanban for this.", "excerpt": "I use hermes with crons and kanban for this. I have a \"self driving\" homelab where upgrades & config changes happen in a non-prod ct before being applied to \"prod\" (just, a diff ct). Its mainly compose stacks with data volumes on zfs that gets snapshotted a lot to limit possible data loss. I use the orchestrator to break down regular tasks like \"health check the whole env\" or \"find all containers that need an update\"", "context": "homelab operator", "use_case": "self-driving homelab orchestration", "switched_from": "", "story": "My Homelab AI Dev Platform"}]}, {"text": " and several say it is more stable and easier to configure than OpenClaw.", "cites": [{"id": 768932368, "item_id": 48058273, "url": "https://news.ycombinator.com/item?id=48058273", "by": "ikidd", "date": "2026-05-07", "stance": "recommend", "quote": "I switched to Hermes Agent and it's been night and day how much more stable and usable it is over OpenClaw.", "excerpt": "I switched to Hermes Agent and it's been night and day how much more stable and usable it is over OpenClaw. What a mess that's turned into", "context": "", "use_case": "AI agent", "switched_from": "OpenClaw", "story": "OpenClaw Had a Rough Week"}, {"id": 803114496, "item_id": 50194656, "url": "https://news.ycombinator.com/item?id=50194656", "by": "sksksk", "date": "2026-10-22", "stance": "recommend", "quote": "I found hermes a lot easier to use and configure.", "excerpt": "I'm always a bit wary about doing write up on things like this, as I kind of just muddle things together and definitely don't follow best practices. I used OpenClaw a while back, I did find it useful, but it wasn't as reliable. This time around, I found hermes a lot easier to use and configure. One thing I think has improved it is building apps to \"pre-compute\" data. For example, with my email, instead of accessing m", "context": "", "use_case": "personal AI agent", "switched_from": "OpenClaw", "story": "Claude Duet"}, {"id": 764575026, "item_id": 47785939, "url": "https://news.ycombinator.com/item?id=47785939", "by": "superfrank", "date": "2026-04-15", "stance": "recommend", "quote": "it's the first one where it didn't feel like I was constantly needing to fix it", "excerpt": "I don't use OpenClaw I tried but found it fragile and it's personality off putting. I then tried NanoClaw, but found the lack of communication channels limiting and could never really get it to create skills that felt solid. I recently just switched to Hermes Agent (like last week) and it's the first one where it didn't feel like I was constantly needing to fix it, so at the moment I'm happy with it. What do I use it", "context": "", "use_case": "personal assistant and automations", "switched_from": "NanoClaw", "story": "Is anyone actually using OpenClaw?"}]}, {"text": " Complaints are scattered rather than shared: one user says it gets slow as skills pile up,", "cites": [{"id": 792122466, "item_id": 49507654, "url": "https://news.ycombinator.com/item?id=49507654", "by": "iagooar", "date": "2026-08-31", "stance": "neutral", "quote": "it tends to keep growing skills and overhead over time, to the point it is becoming utterly slow and sluggish", "excerpt": "As much as I love my CLI tools, I just cannot go back to not having native built-in browser integration, links, etc which the (Mac) desktop apps like ChatGPT or Claude offer. I do use Hermes sometimes, but it tends to keep growing skills and overhead over time, to the point it is becoming utterly slow and sluggish. The Desktop experience itself seems vibecoded without taste, in contrast to the core of Hermes, which i", "context": "Mac user", "use_case": "agent harness", "switched_from": "", "story": "OpenClaw 2.0, Accidentally"}]}, {"text": " another says it is not well tuned for local models,", "cites": [{"id": 797157409, "item_id": 49822338, "url": "https://news.ycombinator.com/item?id=49822338", "by": "theguysudo", "date": "2026-09-23", "stance": "compare", "quote": "you can use hermes as it offers more kind of productivity though hermes is not optimized right for local agents", "excerpt": "PI is best for any local model not just Qwen but you can use hermes as it offers more kind of productivity though hermes is not optimized right for local agents which will somewhat affect your work balance but with some tweaks like 1.Trim the Token Tax: Run hermes tools and turn off everthing unused 2.Enable KV Cache / Prefix Caching", "context": "", "use_case": "harness for local models", "switched_from": "", "story": "Ask HN: Which harness do you use with Qwen3.8 27B? And why?"}]}, {"text": " and one raises trust concerns about the project.", "cites": [{"id": 777385297, "item_id": 48586581, "url": "https://news.ycombinator.com/item?id=48586581", "by": "_pdp_", "date": "2026-06-18", "stance": "warn", "quote": "OpenClaw, at least initially, and Hermes both appear to have been heavily astroturfed using all kinds of blackhat tactics", "excerpt": "I might be a little more paranoid than most because of my profession, but none of these projects inspire enough trust to justify being installed - let alone directly on the machine I use every day. OpenClaw, at least initially, and Hermes both appear to have been heavily astroturfed using all kinds of blackhat tactics, which is a huge red flag to me. And then there is the code.", "context": "security-minded profession", "use_case": "", "switched_from": "", "story": "Migrate from OpenClaw"}]}], "praise": [{"label": "Personal assistant", "summary": "Handles everyday tasks like email, research, documents, and reminders.", "quotes": [{"id": 774677265, "item_id": 48417329, "url": "https://news.ycombinator.com/item?id=48417329", "by": "igorhvr", "date": "2026-06-05", "stance": "recommend", "quote": "Hermes basically rules my personal life at this point - it is a _very_ useful personal assistant.", "excerpt": "I use PI ( https://pi.dev ) and ( https://hermes-agent.nousresearch.com/ ) as the main drivers together with deepseek-v4-pro as the main model (~10M/day tokens overall there). Hermes basically rules my personal life at this point - it is a _very_ useful personal assistant. I also use it at work (integrated at Slack) and at this point it answers most of both my emails and slack messages (I calibrated https://github.co", "context": "", "use_case": "personal assistant, email and Slack replies", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 788076672, "item_id": 49254792, "url": "https://news.ycombinator.com/item?id=49254792", "by": "l3x4ur1n", "date": "2026-08-11", "stance": "recommend", "quote": "I am getting to know Hermes agent", "excerpt": "I am getting to know Hermes agent and in the last couple of days I used it for searching the web for medical specialists or finding the best deal for a product online, manipulate with excel and word documents, gather data from APIs, finding stuff in my computer or keeping track of itself running in another process and keep the computer awake and when detecting the process is finished, put computer to sleep.", "context": "", "use_case": "web search, documents, computer tasks", "switched_from": "", "story": "LFM2.5 2.6B model competitive with 4x larger models"}, {"id": 764575026, "item_id": 47785939, "url": "https://news.ycombinator.com/item?id=47785939", "by": "superfrank", "date": "2026-04-15", "stance": "recommend", "quote": "it's the first one where it didn't feel like I was constantly needing to fix it", "excerpt": "I don't use OpenClaw I tried but found it fragile and it's personality off putting. I then tried NanoClaw, but found the lack of communication channels limiting and could never really get it to create skills that felt solid. I recently just switched to Hermes Agent (like last week) and it's the first one where it didn't feel like I was constantly needing to fix it, so at the moment I'm happy with it. What do I use it", "context": "", "use_case": "personal assistant and automations", "switched_from": "NanoClaw", "story": "Is anyone actually using OpenClaw?"}]}, {"label": "Better than OpenClaw", "summary": "Users who switched from OpenClaw or NanoClaw call it more stable and easier to set up.", "quotes": [{"id": 768932368, "item_id": 48058273, "url": "https://news.ycombinator.com/item?id=48058273", "by": "ikidd", "date": "2026-05-07", "stance": "recommend", "quote": "I switched to Hermes Agent and it's been night and day how much more stable and usable it is over OpenClaw.", "excerpt": "I switched to Hermes Agent and it's been night and day how much more stable and usable it is over OpenClaw. What a mess that's turned into", "context": "", "use_case": "AI agent", "switched_from": "OpenClaw", "story": "OpenClaw Had a Rough Week"}, {"id": 803114496, "item_id": 50194656, "url": "https://news.ycombinator.com/item?id=50194656", "by": "sksksk", "date": "2026-10-22", "stance": "recommend", "quote": "I found hermes a lot easier to use and configure.", "excerpt": "I'm always a bit wary about doing write up on things like this, as I kind of just muddle things together and definitely don't follow best practices. I used OpenClaw a while back, I did find it useful, but it wasn't as reliable. This time around, I found hermes a lot easier to use and configure. One thing I think has improved it is building apps to \"pre-compute\" data. For example, with my email, instead of accessing m", "context": "", "use_case": "personal AI agent", "switched_from": "OpenClaw", "story": "Claude Duet"}, {"id": 775318864, "item_id": 48457429, "url": "https://news.ycombinator.com/item?id=48457429", "by": "apexalpha", "date": "2026-06-08", "stance": "recommend", "quote": "I use Hermes at home. Swapped out Openclaw for this. It seems to work better with smaller contexts", "excerpt": "I use Hermes at home. Swapped out Openclaw for this. It seems to work better with smaller contexts, chuncking it up in smaller pieces. I don't code with it, I use Claude for that. But what I do do: it's a sysadmin for my homelab. It has a read-only mcp server to check the k8s status and has it's own ssh access to fix stuff after I approve it per session. It's magical. Each morning I get a small update whether the bac", "context": "homelab user", "use_case": "homelab sysadmin agent", "switched_from": "OpenClaw", "story": "Hermes Agent \u2013 Open-Source AI Agent with Persistent Memory"}]}, {"label": "Homelab sysadmin", "summary": "Manages servers, Kubernetes, Home Assistant, and routine upgrades with approval steps.", "quotes": [{"id": 775318864, "item_id": 48457429, "url": "https://news.ycombinator.com/item?id=48457429", "by": "apexalpha", "date": "2026-06-08", "stance": "recommend", "quote": "I use Hermes at home. Swapped out Openclaw for this. It seems to work better with smaller contexts", "excerpt": "I use Hermes at home. Swapped out Openclaw for this. It seems to work better with smaller contexts, chuncking it up in smaller pieces. I don't code with it, I use Claude for that. But what I do do: it's a sysadmin for my homelab. It has a read-only mcp server to check the k8s status and has it's own ssh access to fix stuff after I approve it per session. It's magical. Each morning I get a small update whether the bac", "context": "homelab user", "use_case": "homelab sysadmin agent", "switched_from": "OpenClaw", "story": "Hermes Agent \u2013 Open-Source AI Agent with Persistent Memory"}, {"id": 776840512, "item_id": 48552532, "url": "https://news.ycombinator.com/item?id=48552532", "by": "xyzzy123", "date": "2026-06-16", "stance": "recommend", "quote": "I use hermes with crons and kanban for this.", "excerpt": "I use hermes with crons and kanban for this. I have a \"self driving\" homelab where upgrades & config changes happen in a non-prod ct before being applied to \"prod\" (just, a diff ct). Its mainly compose stacks with data volumes on zfs that gets snapshotted a lot to limit possible data loss. I use the orchestrator to break down regular tasks like \"health check the whole env\" or \"find all containers that need an update\"", "context": "homelab operator", "use_case": "self-driving homelab orchestration", "switched_from": "", "story": "My Homelab AI Dev Platform"}, {"id": 790266400, "item_id": 49391650, "url": "https://news.ycombinator.com/item?id=49391650", "by": "100percentjake", "date": "2026-08-21", "stance": "recommend", "quote": "It's been wonderful for stuff like, say, giving Hermes an account on my Home Assistant server", "excerpt": "Neat stuff. I use Hermes with the $20/mo ChatGPT Codex integration, myself, as well as Qwen running locally on a 64GB M1 Max Macbook Pro to help save my ever-quickly shrinking Codex credits. It's been wonderful for stuff like, say, giving Hermes an account on my Home Assistant server (after taking a backup) and having it make a bunch of configurations, or draw conclusions based on historical sensor data (trying to de", "context": "home lab user", "use_case": "home automation and personal webapps", "switched_from": "", "story": "A self hosted AI software factory"}]}, {"label": "Agent orchestration", "summary": "Used as the coordinating agent that hands work to Codex, OpenCode, OpenClaw, or subagents.", "quotes": [{"id": 792139824, "item_id": 49508739, "url": "https://news.ycombinator.com/item?id=49508739", "by": "SipitenoMK", "date": "2026-08-31", "stance": "recommend", "quote": "The brain is Hermes, OpenClaw from VPS is a fearless executor", "excerpt": "Actually I use Hermes Agent who delegates tasks to OpenClaw. It works perfectly, we run OpenClaw experiments with my partner as an independent drop shipper, it\u2019s much more complicated setup, which cannot disclose publicly, but it works. The brain is Hermes, OpenClaw from VPS is a fearless executor :)", "context": "independent drop shipper", "use_case": "orchestrating agents for drop shipping", "switched_from": "", "story": "OpenClaw 2.0, Accidentally"}, {"id": 788711426, "item_id": 49294464, "url": "https://news.ycombinator.com/item?id=49294464", "by": "Wpnx330", "date": "2026-08-13", "stance": "recommend", "quote": "Tron, my Hermes agent, uses agent storming to orchestrate openCode agents and hermes subagents to handle most of my daily tasks.", "excerpt": "$0. but I use at least $8,000 worth of monthly tokens. I used to have: $200 Claude-max $10 github copilot $20 chatgpt $20 Cursor --- then, I spent roughly $5000 in tokens for a project which turned out to be a dud. Figured, inference wasn't going anywhere as its now 80% of my day. So, I built a 4x DGX Spark cluster and put GLM5.2 on it. Then put a few qwen models for vision and embedding purposes on my original DGX S", "context": "", "use_case": "daily task orchestration", "switched_from": "", "story": "Ask HN: How much money do you spend monthly on subscriptions for AI models?"}, {"id": 798378993, "item_id": 49898687, "url": "https://news.ycombinator.com/item?id=49898687", "by": "rmaxdev", "date": "2026-09-29", "stance": "recommend", "quote": "I use it as main Hermes model that orchestrates codex/droid harnesses", "excerpt": "What do you do? I\u2019m 200 bucks deepseek flash in about 2 months and it\u2019s increasing I use it as main Hermes model that orchestrates codex/droid harnesses with subscriptions for heavy dev work I do have ChatGPT as main assistant that sets direction and delegation of projects to Hermes At my increasing usage, kind of 200 usd subscriptions makes sense and max out on Luna max", "context": "", "use_case": "orchestrating coding agents", "switched_from": "", "story": "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"}]}, {"label": "Flexible models", "summary": "Runs with cheap API models or local models on modest hardware.", "quotes": [{"id": 804024544, "item_id": 50251534, "url": "https://news.ycombinator.com/item?id=50251534", "by": "l3x4ur1n", "date": "2026-10-26", "stance": "recommend", "quote": "I am using Hermes and I did not try charts, but the rest it can do with ease.", "excerpt": "I am using Hermes and I did not try charts, but the rest it can do with ease. And I use DeepSeek flash API as a driver most of the time.", "context": "", "use_case": "local file agent work", "switched_from": "", "story": "Show HN: Hob - Open-source, on device alternative to Claude Cowork and ChatGPT"}, {"id": 790266400, "item_id": 49391650, "url": "https://news.ycombinator.com/item?id=49391650", "by": "100percentjake", "date": "2026-08-21", "stance": "recommend", "quote": "It's been wonderful for stuff like, say, giving Hermes an account on my Home Assistant server", "excerpt": "Neat stuff. I use Hermes with the $20/mo ChatGPT Codex integration, myself, as well as Qwen running locally on a 64GB M1 Max Macbook Pro to help save my ever-quickly shrinking Codex credits. It's been wonderful for stuff like, say, giving Hermes an account on my Home Assistant server (after taking a backup) and having it make a bunch of configurations, or draw conclusions based on historical sensor data (trying to de", "context": "home lab user", "use_case": "home automation and personal webapps", "switched_from": "", "story": "A self hosted AI software factory"}, {"id": 779622368, "item_id": 48726398, "url": "https://news.ycombinator.com/item?id=48726398", "by": "roadside_picnic", "date": "2026-06-29", "stance": "recommend", "quote": "I have an older laptop I run a hermes agent on", "excerpt": "In general if you're setting up a local LLM you should assume it's going to be primarily working as a server and talking to various clients. I use my MBP, but that's because I don't travel much anymore so it can happily work as a server at all times. With the right agent setup you can probably manage most things from your phone even if you don't have a seperate machine to use as a client. I have an older laptop I run", "context": "", "use_case": "local and API-backed agents", "switched_from": "", "story": "Qwen 3.6 27B is the sweet spot for local development"}]}, {"label": "Chat access", "summary": "Users reach it through Slack, Discord, Matrix, or Telegram, including from a phone.", "quotes": [{"id": 787827904, "item_id": 49239244, "url": "https://news.ycombinator.com/item?id=49239244", "by": "resonious", "date": "2026-08-09", "stance": "neutral", "quote": "Right now I use hermes agent and just chat with it on Slack.", "excerpt": "Not surprised at all but there seems to be tons of these kinds of tools and I'm having a hard time picking one. Is there a nice list somewhere? I guess I can ask chatgpt... Honestly right now I do a lot of development from my phone - I don't have the time to pull out my laptop very much. Right now I use hermes agent and just chat with it on Slack. But sometimes I wish I had easier access to more advanced features, an", "context": "develops from phone", "use_case": "developing from phone via chat", "switched_from": "", "story": "OpenChamber: An Agentic Development Environment"}, {"id": 764579312, "item_id": 47786207, "url": "https://news.ycombinator.com/item?id=47786207", "by": "newswasboring", "date": "2026-04-15", "stance": "recommend", "quote": "this week switched to Hermes", "excerpt": "I don't use openclaw but I spent few weeks on nanobot and then this week switched to Hermes. I have simple usecases like a news brief in the morning on my areas of interest, checking my email for latest updates on things I care about right now etc. But I gave my wife access to the discord server, she burned 20% of weekly quota for codex (I use it as the provider) but created a skill which helps her practice dutch her", "context": "", "use_case": "news brief and email checks", "switched_from": "nanobot", "story": "Is anyone actually using OpenClaw?"}, {"id": 796969217, "item_id": 49810576, "url": "https://news.ycombinator.com/item?id=49810576", "by": "jeena", "date": "2026-09-23", "stance": "neutral", "quote": "I also run Hermes Agent", "excerpt": "One is pi.dev on the console, but because the KB is a git repository I have it on each computer. On top of that I also run Hermes Agent and have set up there one agent to be responsible for the KB stuff and that one I connected to a Matrix channel and can use it from the phone and any device where I have a matrix client like Element set up. With pi.dev I use it in a container https://git.jeena.net/jeena/agent-contain", "context": "", "use_case": "knowledge base agent", "switched_from": "", "story": "The new CC, an AI agent built for families"}]}], "caveats": [{"label": "Model-dependent quality", "summary": "Results vary with the model: cheap models hallucinate and some degraded over time.", "quotes": [{"id": 786552480, "item_id": 49159530, "url": "https://news.ycombinator.com/item?id=49159530", "by": "Swapnoneel", "date": "2026-08-03", "stance": "neutral", "quote": "I recently started using the Hermes agent", "excerpt": "So, I recently started using the Hermes agent and hooked it up with Step 3.5 Flash. It\u2019s a cheap and fast model, so I thought it would be enough for my workflow. However, I soon found that it hallucinates during a lot of tasks, and the output quality isn\u2019t something to write home about. On the other hand, using an expensive or frontier-level model means I\u2019ll burn through cash fast. I went down the rabbit hole to find", "context": "", "use_case": "agentic workflow", "switched_from": "", "story": "Is Hermes Agent unusable without a model router?"}, {"id": 796639234, "item_id": 49789952, "url": "https://news.ycombinator.com/item?id=49789952", "by": "jotato", "date": "2026-09-21", "stance": "neutral", "quote": "I made it my default model in Hermes", "excerpt": "Just yesterday I was thinking about gpt-5.6-luna. I made it my default model in Hermes during its fist week of launch. It was just as good as 5.5 which was my previous default. But over the last 2 or 3 weeks I've seen how dumb it is now. I have to be very explicit with it. For example, I used to be able to prompt \"Check the system logs on <server> for....\" and it would just figure it out. Yesterday I asked \"Did <serv", "context": "", "use_case": "AI agent harness", "switched_from": "", "story": "Fable 5 \u2013 Median thinking declined in August"}]}, {"label": "Gets sluggish", "summary": "One user says accumulated skills and overhead make it slow, and the desktop app feels unpolished.", "quotes": [{"id": 792122466, "item_id": 49507654, "url": "https://news.ycombinator.com/item?id=49507654", "by": "iagooar", "date": "2026-08-31", "stance": "neutral", "quote": "it tends to keep growing skills and overhead over time, to the point it is becoming utterly slow and sluggish", "excerpt": "As much as I love my CLI tools, I just cannot go back to not having native built-in browser integration, links, etc which the (Mac) desktop apps like ChatGPT or Claude offer. I do use Hermes sometimes, but it tends to keep growing skills and overhead over time, to the point it is becoming utterly slow and sluggish. The Desktop experience itself seems vibecoded without taste, in contrast to the core of Hermes, which i", "context": "Mac user", "use_case": "agent harness", "switched_from": "", "story": "OpenClaw 2.0, Accidentally"}]}, {"label": "Local model tuning", "summary": "Said to need tweaks such as trimming tools and enabling caching to work well with local models.", "quotes": [{"id": 797157409, "item_id": 49822338, "url": "https://news.ycombinator.com/item?id=49822338", "by": "theguysudo", "date": "2026-09-23", "stance": "compare", "quote": "you can use hermes as it offers more kind of productivity though hermes is not optimized right for local agents", "excerpt": "PI is best for any local model not just Qwen but you can use hermes as it offers more kind of productivity though hermes is not optimized right for local agents which will somewhat affect your work balance but with some tweaks like 1.Trim the Token Tax: Run hermes tools and turn off everthing unused 2.Enable KV Cache / Prefix Caching", "context": "", "use_case": "harness for local models", "switched_from": "", "story": "Ask HN: Which harness do you use with Qwen3.8 27B? And why?"}]}, {"label": "Trust concerns", "summary": "A security-minded commenter suspects astroturfed promotion and would not install it.", "quotes": [{"id": 777385297, "item_id": 48586581, "url": "https://news.ycombinator.com/item?id=48586581", "by": "_pdp_", "date": "2026-06-18", "stance": "warn", "quote": "OpenClaw, at least initially, and Hermes both appear to have been heavily astroturfed using all kinds of blackhat tactics", "excerpt": "I might be a little more paranoid than most because of my profession, but none of these projects inspire enough trust to justify being installed - let alone directly on the machine I use every day. OpenClaw, at least initially, and Hermes both appear to have been heavily astroturfed using all kinds of blackhat tactics, which is a huge red flag to me. And then there is the code.", "context": "security-minded profession", "use_case": "", "switched_from": "", "story": "Migrate from OpenClaw"}]}, {"label": "Fewer features", "summary": "Described as polished but shallower than OpenClaw.", "quotes": [{"id": 777384720, "item_id": 48586545, "url": "https://news.ycombinator.com/item?id=48586545", "by": "Multiplayer", "date": "2026-06-18", "stance": "recommend", "quote": "Hermes is for the less technical and is more polished.", "excerpt": "My simple take: Hermes is for the less technical and is more polished. OpenClaw is deeper with more capabilities. OpenClaw has come so far since its' original launch/craze. I recommend taking a second look if you haven't touched it in a while. If for no other reason than it's just a really fun playground with a LOT of areas to experiment in. Setup a myriad of agents with various models, skills, cron jobs, etc. The co", "context": "", "use_case": "AI agent", "switched_from": "", "story": "Migrate from OpenClaw"}]}, {"label": "Install issues", "summary": "One release stopped installing under Termux on Android.", "quotes": [{"id": 786900482, "item_id": 49181280, "url": "https://news.ycombinator.com/item?id=49181280", "by": "ljosifov", "date": "2026-08-05", "stance": "recommend", "quote": "For general computer use mostly use Hermes.", "excerpt": "Love pi. It's good to have a minimal agent, always welcome. Even if only to bootstrap install other agents. E.g. recently Hermes stopped installing under Termux (v0.19 - no, v0.18 - yes). Agent pi to the rescue: installed it under Termux (Android), started it, pointed pi to the Hermes github, asked for v0.18 specifically - and it did it. Cherry on the top - asked it to install a plugin from github I use (unmerged PR)", "context": "", "use_case": "general computer use agent", "switched_from": "", "story": "Pi's Minimalism Is Its Advantage"}]}], "who": [{"by": "ozymandiax", "context": "builds replicas of ancient computers", "url": "https://news.ycombinator.com/item?id=49976992", "date": "2026-10-06"}, {"by": "SipitenoMK", "context": "independent drop shipper", "url": "https://news.ycombinator.com/item?id=49508739", "date": "2026-08-31"}, {"by": "iagooar", "context": "Mac user", "url": "https://news.ycombinator.com/item?id=49507654", "date": "2026-08-31"}, {"by": "reachableceo", "context": "CTO adopting an agent stack", "url": "https://news.ycombinator.com/item?id=49459948", "date": "2026-08-27"}, {"by": "100percentjake", "context": "home lab user", "url": "https://news.ycombinator.com/item?id=49391650", "date": "2026-08-21"}, {"by": "resonious", "context": "develops from phone", "url": "https://news.ycombinator.com/item?id=49239244", "date": "2026-08-09"}, {"by": "AbsurdCensor", "context": "runs local AI box on solar", "url": "https://news.ycombinator.com/item?id=49156910", "date": "2026-08-03"}, {"by": "diseasedyak", "context": "home setup with RTX 4090", "url": "https://news.ycombinator.com/item?id=48892434", "date": "2026-07-13"}, {"by": "mft_", "context": "experimenting with local models", "url": "https://news.ycombinator.com/item?id=48883545", "date": "2026-07-12"}, {"by": "xyzzy123", "context": "homelab operator", "url": "https://news.ycombinator.com/item?id=48552532", "date": "2026-06-16"}, {"by": "theturtletalks", "context": "runs a business", "url": "https://news.ycombinator.com/item?id=48543186", "date": "2026-06-15"}, {"by": "atonse", "context": "runs a consulting business", "url": "https://news.ycombinator.com/item?id=48461277", "date": "2026-06-09"}], "tags": ["for homelabs", "self-hostable", "for personal assistants", "for agent orchestration", "for local LLM users"], "use_cases": ["agent harness", "ai agent", "personal agent", "agent", "local file agent work", "personal ai agent"], "compared": [{"slug": "openclaw", "name": "OpenClaw", "co": 22, "switched_from": 5, "switched_to": 0}, {"slug": "pi", "name": "Pi", "co": 16, "switched_from": 0, "switched_to": 1}, {"slug": "nanoclaw", "name": "NanoClaw", "co": 5, "switched_from": 3, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 9, "switched_from": 1, "switched_to": 0}, {"slug": "codex", "name": "Codex", "co": 11, "switched_from": 0, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 8, "switched_from": 0, "switched_to": 0}, {"slug": "opencode", "name": "OpenCode", "co": 8, "switched_from": 0, "switched_to": 0}, {"slug": "qwen-3-6", "name": "Qwen 3.6", "co": 6, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49505310", "title": "OpenClaw 2.0, Accidentally", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=48586005", "title": "Migrate from OpenClaw", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=47783940", "title": "Is anyone actually using OpenClaw?", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49789224", "title": "Fable 5 \u2013 Median thinking declined in August", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48884984", "title": "Ask HN: What Are You Working On? (July 2026)", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48721903", "title": "Qwen 3.6 27B is the sweet spot for local development", "mentions": 2}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"recommend": 3, "neutral": 2, "compare": 1}, "2026-05": {"recommend": 1}, "2026-06": {"recommend": 8, "neutral": 9, "warn": 1, "compare": 1}, "2026-07": {"neutral": 8, "recommend": 3}, "2026-08": {"neutral": 11, "recommend": 10, "compare": 1}, "2026-09": {"warn": 1, "compare": 2, "recommend": 3, "neutral": 3}, "2026-10": {"neutral": 4, "recommend": 5}}, "quotes": [{"id": 804024544, "item_id": 50251534, "url": "https://news.ycombinator.com/item?id=50251534", "by": "l3x4ur1n", "date": "2026-10-26", "stance": "recommend", "quote": "I am using Hermes and I did not try charts, but the rest it can do with ease.", "excerpt": "I am using Hermes and I did not try charts, but the rest it can do with ease. And I use DeepSeek flash API as a driver most of the time.", "context": "", "use_case": "local file agent work", "switched_from": "", "story": "Show HN: Hob - Open-source, on device alternative to Claude Cowork and ChatGPT"}, {"id": 803114496, "item_id": 50194656, "url": "https://news.ycombinator.com/item?id=50194656", "by": "sksksk", "date": "2026-10-22", "stance": "recommend", "quote": "I found hermes a lot easier to use and configure.", "excerpt": "I'm always a bit wary about doing write up on things like this, as I kind of just muddle things together and definitely don't follow best practices. I used OpenClaw a while back, I did find it useful, but it wasn't as reliable. This time around, I found hermes a lot easier to use and configure. One thing I think has improved it is building apps to \"pre-compute\" data. For example, with my email, instead of accessing m", "context": "", "use_case": "personal AI agent", "switched_from": "OpenClaw", "story": "Claude Duet"}, {"id": 802995459, "item_id": 50187216, "url": "https://news.ycombinator.com/item?id=50187216", "by": "yisraelgottz", "date": "2026-10-21", "stance": "neutral", "quote": "I took Hermes, FluidAudio, CUA Driver, WisprKit, and OpenWispr, put it all together", "excerpt": "I've been creating products for over a year now, and this was one of those products that changed my day-to-day life. I use Claude and ChatGPT all the time for work, and I was always sick and tired of going into a chat window to do what I needed to do. I wanted to just talk to Claude wherever I was in any app, so that's what I did. I took Hermes, FluidAudio, CUA Driver, WisprKit, and OpenWispr, put it all together, co", "context": "", "use_case": "component of Memoe", "switched_from": "", "story": null}, {"id": 802717616, "item_id": 50169851, "url": "https://news.ycombinator.com/item?id=50169851", "by": "envoked", "date": "2026-10-20", "stance": "neutral", "quote": "Excited to give this a try in my local Hermes setup.", "excerpt": "Excited to give this a try in my local Hermes setup. A poor conversation modality is the only thing that\u2019s been bringing me back to the Claude app.", "context": "", "use_case": "local AI setup", "switched_from": "", "story": "Voxtral 3"}, {"id": 799718064, "item_id": 49982379, "url": "https://news.ycombinator.com/item?id=49982379", "by": "KetoManx64", "date": "2026-10-06", "stance": "recommend", "quote": "I've found it easier to just open up the Hermes app on my phone and just tell it to clone a project and build my features into it", "excerpt": "The last couple of months I've found it easier to just open up the Hermes app on my phone and just tell it to clone a project and build my features into it and then build the app and push it to my phone. 99% of the time I don't bother upstreaming my changes. If it's a project I use regularly I typicallt send the creator $25-50 for all the work they put into the project and for making it open source. I think this will", "context": "", "use_case": "customizing open source projects", "switched_from": "", "story": "Open Source as We Know It Is Dead"}, {"id": 799631873, "item_id": 49976992, "url": "https://news.ycombinator.com/item?id=49976992", "by": "ozymandiax", "date": "2026-10-06", "stance": "neutral", "quote": "Whether a Hermes agent with PDP-1 skills is the best setup, I am frankly not sure.", "excerpt": "Our informal group has been making replicas of ancient computers for years. Of course, the learning curve for these machines is steep. The Agent-PDP1 github is our hope of now 'adding a replicant PDP-1 Hacker to sit with you on the replica machine'. This has been fun, but there is a long way to go. Still, it really does feel like you are sitting next to the PDP-1 from Stephen Levy's \"Hackers\" with an old hacker. A li", "context": "builds replicas of ancient computers", "use_case": "PDP-1 hacker replicant", "switched_from": "", "story": "Show HN: Making an MIT hacker replicant for a PDP-1"}, {"id": 799473328, "item_id": 49967083, "url": "https://news.ycombinator.com/item?id=49967083", "by": "daft_pink", "date": "2026-10-05", "stance": "recommend", "quote": "I use hermes on my work windows computer", "excerpt": "I do feel since I use hermes on my work windows computer and grok bot in the cloud on everything else that computer use is so useful and important, but I'm also worried that Apple will not be a good choice for that.", "context": "", "use_case": "computer use agent", "switched_from": "", "story": "Apple and a hacker's future"}, {"id": 799264417, "item_id": 49954026, "url": "https://news.ycombinator.com/item?id=49954026", "by": "roscas", "date": "2026-10-04", "stance": "recommend", "quote": "I use it with the browser that has a great dashboard and with hermes agent and that it really makes this amazing.", "excerpt": "Coder version with 30t/sec on a Ryzen 3600x with 48GB of RAM with a nvidia 3080. This is not a very fast desktop. Memory speed is around 2000mhz only. My SSD is some of the worst SSD I've seen and 3080 had its days of glory. I still have code, chromium, librewolf and many other programs running. I have video streams running while I also watch tv and many times youtube videos. I use it with the browser that has a grea", "context": "", "use_case": "local coding agent", "switched_from": "", "story": "Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s"}, {"id": 798936273, "item_id": 49933517, "url": "https://news.ycombinator.com/item?id=49933517", "by": "ImaCake", "date": "2026-10-02", "stance": "neutral", "quote": "where I use hermes harness", "excerpt": "A lot of us aren't actually using enough tokens to reach the value add of a $20USD/month subscription versus just paying for the API. Without even mentioning the chinese competitors, you can get a lot of tokens for $10 of ChatGPT Luna, which is more than capable of solving the kinds of problems I have at home (where I use hermes harness).", "context": "", "use_case": "AI harness at home", "switched_from": "", "story": "Pi 1.0"}, {"id": 798378993, "item_id": 49898687, "url": "https://news.ycombinator.com/item?id=49898687", "by": "rmaxdev", "date": "2026-09-29", "stance": "recommend", "quote": "I use it as main Hermes model that orchestrates codex/droid harnesses", "excerpt": "What do you do? I\u2019m 200 bucks deepseek flash in about 2 months and it\u2019s increasing I use it as main Hermes model that orchestrates codex/droid harnesses with subscriptions for heavy dev work I do have ChatGPT as main assistant that sets direction and delegation of projects to Hermes At my increasing usage, kind of 200 usd subscriptions makes sense and max out on Luna max", "context": "", "use_case": "orchestrating coding agents", "switched_from": "", "story": "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"}, {"id": 798138642, "item_id": 49883665, "url": "https://news.ycombinator.com/item?id=49883665", "by": "yipinwong", "date": "2026-09-28", "stance": "neutral", "quote": "on hermes with the same agent.md, and soul.md", "excerpt": "Sticking with OPUS 5.5 for resume/STAR generation for me. Tried Sonnet 5.5 but worse than OPUS for thinking for sure, less error/inconsistency check. I used Opus 5.5 med vs. Sonnet 5.5 High on hermes with the same agent.md, and soul.md It's either Opus is smarter for sure, or Sonnet is ignoring my contexts. --- For those who downvoted my comment last week regarding using Opus 5.5 for resume, go get lost somewhere. I ", "context": "", "use_case": "running agent", "switched_from": "", "story": "Sonnet 5.5"}, {"id": 797157409, "item_id": 49822338, "url": "https://news.ycombinator.com/item?id=49822338", "by": "theguysudo", "date": "2026-09-23", "stance": "compare", "quote": "you can use hermes as it offers more kind of productivity though hermes is not optimized right for local agents", "excerpt": "PI is best for any local model not just Qwen but you can use hermes as it offers more kind of productivity though hermes is not optimized right for local agents which will somewhat affect your work balance but with some tweaks like 1.Trim the Token Tax: Run hermes tools and turn off everthing unused 2.Enable KV Cache / Prefix Caching", "context": "", "use_case": "harness for local models", "switched_from": "", "story": "Ask HN: Which harness do you use with Qwen3.8 27B? And why?"}, {"id": 796969217, "item_id": 49810576, "url": "https://news.ycombinator.com/item?id=49810576", "by": "jeena", "date": "2026-09-23", "stance": "neutral", "quote": "I also run Hermes Agent", "excerpt": "One is pi.dev on the console, but because the KB is a git repository I have it on each computer. On top of that I also run Hermes Agent and have set up there one agent to be responsible for the KB stuff and that one I connected to a Matrix channel and can use it from the phone and any device where I have a matrix client like Element set up. With pi.dev I use it in a container https://git.jeena.net/jeena/agent-contain", "context": "", "use_case": "knowledge base agent", "switched_from": "", "story": "The new CC, an AI agent built for families"}, {"id": 796699760, "item_id": 49793735, "url": "https://news.ycombinator.com/item?id=49793735", "by": "wronglebowski", "date": "2026-09-21", "stance": "recommend", "quote": "I recommend trying Hermes Agent and setting it up fully", "excerpt": "IMO this comes down to your harness. Any frontier model from a huge shop has an inherent benefit in the system you're using it in. Search, memory, skills, integrations you don't realize even exist make them much more powerful. It is some effort but I recommend trying Hermes Agent and setting it up fully, that's the closest you'll get to a more complete experience.", "context": "", "use_case": "harness for open models", "switched_from": "", "story": "Fable 5 \u2013 Median thinking declined in August"}, {"id": 796639234, "item_id": 49789952, "url": "https://news.ycombinator.com/item?id=49789952", "by": "jotato", "date": "2026-09-21", "stance": "neutral", "quote": "I made it my default model in Hermes", "excerpt": "Just yesterday I was thinking about gpt-5.6-luna. I made it my default model in Hermes during its fist week of launch. It was just as good as 5.5 which was my previous default. But over the last 2 or 3 weeks I've seen how dumb it is now. I have to be very explicit with it. For example, I used to be able to prompt \"Check the system logs on <server> for....\" and it would just figure it out. Yesterday I asked \"Did <serv", "context": "", "use_case": "AI agent harness", "switched_from": "", "story": "Fable 5 \u2013 Median thinking declined in August"}, {"id": 795681459, "item_id": 49730091, "url": "https://news.ycombinator.com/item?id=49730091", "by": "browningstreet", "date": "2026-09-16", "stance": "recommend", "quote": "This is exactly how I want to keep working.", "excerpt": "I use Claude/opencode and Orca and Hermes across my vpses, Macbook, Linux, and iOS devices. This is exactly how I want to keep working.", "context": "", "use_case": "", "switched_from": "", "story": "Claude Cowork and chat are now one Claude"}, {"id": 795259282, "item_id": 49703705, "url": "https://news.ycombinator.com/item?id=49703705", "by": "sbankowi", "date": "2026-09-14", "stance": "compare", "quote": "how are you differentiating yourself from something like the Hermes Agent?", "excerpt": "I am looked at the website, but I am not able to understand what problem you are trying to solve. Or why would I use you? (How are you differentiating yourself?) I see you are reliant on ollama and llama.cpp (for example), so why should I not just use those directly if I am focused on local first models. (llama.cpp already makes recommendations on what models to run.) If the argument is then that you are more of an a", "context": "", "use_case": "agentic experience", "switched_from": "", "story": "Show HN: I built Otis, a minimal AI agent that runs local models out of the box"}, {"id": 794313009, "item_id": 49644563, "url": "https://news.ycombinator.com/item?id=49644563", "by": "faangguyindia", "date": "2026-09-10", "stance": "warn", "quote": "Hermes VM doesn't even have JIT.", "excerpt": "React Native is slow. Hermes VM doesn't even have JIT. If the majority of your app is native code and only a few places are stitched together via JS code that runs in the Hermes VM, then React Native is suitable for you. Look at V8 vs. Hermes performance. We use Flutter; we rarely need to write native code. We have three apps: Symbiote workout app, CalorieCodex, an AI calorie tracker app, and MacroCodex with 17,000+ ", "context": "", "use_case": "JS runtime", "switched_from": "", "story": "Shopify is moving from React Native back to Swift and Kotlin"}, {"id": 792145184, "item_id": 49509074, "url": "https://news.ycombinator.com/item?id=49509074", "by": "edtechdev", "date": "2026-08-31", "stance": "neutral", "quote": "Static astro 7 site generated with Hermes and DeepSeek Flash-0731.", "excerpt": "Public domain auto-updating knowledge base of recent open-access research on AI in educational contexts. Currently has ingested 950 research articles, synthesized into 180 concept pages. Static astro 7 site generated with Hermes and DeepSeek Flash-0731. Source and skill files: https://github.com/edtechdev/aied", "context": "", "use_case": "generating knowledge base site", "switched_from": "", "story": "AI in Education Knowledge Base"}, {"id": 792139824, "item_id": 49508739, "url": "https://news.ycombinator.com/item?id=49508739", "by": "SipitenoMK", "date": "2026-08-31", "stance": "recommend", "quote": "The brain is Hermes, OpenClaw from VPS is a fearless executor", "excerpt": "Actually I use Hermes Agent who delegates tasks to OpenClaw. It works perfectly, we run OpenClaw experiments with my partner as an independent drop shipper, it\u2019s much more complicated setup, which cannot disclose publicly, but it works. The brain is Hermes, OpenClaw from VPS is a fearless executor :)", "context": "independent drop shipper", "use_case": "orchestrating agents for drop shipping", "switched_from": "", "story": "OpenClaw 2.0, Accidentally"}, {"id": 792137184, "item_id": 49508574, "url": "https://news.ycombinator.com/item?id=49508574", "by": "nisegami", "date": "2026-08-31", "stance": "recommend", "quote": "I used nanoclaw for a bit before switching to Hermes.", "excerpt": "There's a lot of similar projects out there that are closer to what you're looking for. For example, I used nanoclaw for a bit before switching to Hermes.", "context": "", "use_case": "agent harness", "switched_from": "nanoclaw", "story": "OpenClaw 2.0, Accidentally"}, {"id": 792122466, "item_id": 49507654, "url": "https://news.ycombinator.com/item?id=49507654", "by": "iagooar", "date": "2026-08-31", "stance": "neutral", "quote": "it tends to keep growing skills and overhead over time, to the point it is becoming utterly slow and sluggish", "excerpt": "As much as I love my CLI tools, I just cannot go back to not having native built-in browser integration, links, etc which the (Mac) desktop apps like ChatGPT or Claude offer. I do use Hermes sometimes, but it tends to keep growing skills and overhead over time, to the point it is becoming utterly slow and sluggish. The Desktop experience itself seems vibecoded without taste, in contrast to the core of Hermes, which i", "context": "Mac user", "use_case": "agent harness", "switched_from": "", "story": "OpenClaw 2.0, Accidentally"}, {"id": 792098786, "item_id": 49506174, "url": "https://news.ycombinator.com/item?id=49506174", "by": "teekert", "date": "2026-08-31", "stance": "compare", "quote": "2nd iteration I was indeed eyeballing Hermes which is supposed to be more structured", "excerpt": "I think this is a good question, as with any of these new things you don't really feel any need indeed. My claw scrapes some APIs, receives some emails with job listings, and matches it all to my profile. It can also fill two folders at 2 domains with anything (ie a demo for a website). It can also receive emails, make PFDs out of them and forward them to my bookkeeping software (which can only deal with attachments,", "context": "", "use_case": "agent harness", "switched_from": "", "story": "OpenClaw 2.0, Accidentally"}, {"id": 791638610, "item_id": 49477413, "url": "https://news.ycombinator.com/item?id=49477413", "by": "nameless912", "date": "2026-08-28", "stance": "neutral", "quote": "I'm running a Hermes agent as of recently on a DigitalOcean VM", "excerpt": "This article smells AI generated, which is _very_ funny given the argument being made. Either way, while this is true in the absolute, this is the value of building good MCP servers: they should expose only exactly the surface you expect your agent to need, and adding functionality should be carefully considered. The best MCP servers I use day to day (Cloudflare sticks out) do a really good job of exposing only what ", "context": "", "use_case": "isolated AI agent", "switched_from": "", "story": "AI Agent Has Root"}, {"id": 791359171, "item_id": 49459948, "url": "https://news.ycombinator.com/item?id=49459948", "by": "reachableceo", "date": "2026-08-27", "stance": "neutral", "quote": "interacting with scoped Hermes profiles", "excerpt": "It\u2019s called using systems of record. I use redmine and discourse. Jointly with my stack of agents (COO) (managed by four very high trust humans via OWUI interacting with scoped Hermes profiles ). I\u2019m adopting this stack under me (CTO) and integrating it into agent zero", "context": "CTO adopting an agent stack", "use_case": "agent profiles", "switched_from": "", "story": "CEO fired developers to make room for AI. Developers create open source AI CEO"}, {"id": 790903681, "item_id": 49431480, "url": "https://news.ycombinator.com/item?id=49431480", "by": "NicoJuicy", "date": "2026-08-25", "stance": "neutral", "quote": "Daily driver for my hermes atm", "excerpt": "Tbh. I think it's a chinese model ( cheap and inefficient in execution, but it's the best cheap ( free ) model atm. Daily driver for my hermes atm, but albeit slow in execution).", "context": "", "use_case": "agent harness", "switched_from": "", "story": "Ox Alpha \u2013 A mysterious new AI model"}, {"id": 790368336, "item_id": 49398021, "url": "https://news.ycombinator.com/item?id=49398021", "by": "fallinditch", "date": "2026-08-22", "stance": "recommend", "quote": "My agent (Hermes) responds to a made-up command", "excerpt": "I use the LLM-wiki pattern for a structured directory of topic folders of .md files, and made it also compatible with the Open Knowledge Format [1]. My agent (Hermes) responds to a made-up command \"vaultize this doc/link/text, etc\" to add new .md files in the right format in the right place. The agent does a pretty good job of maintaining the index.md file, cross-links, etc. A Quartz website builder creates a static ", "context": "", "use_case": "maintaining markdown knowledge base", "switched_from": "", "story": "Show HN: OzBrain, a shared brain for knowledge between agents and your team"}, {"id": 790266400, "item_id": 49391650, "url": "https://news.ycombinator.com/item?id=49391650", "by": "100percentjake", "date": "2026-08-21", "stance": "recommend", "quote": "It's been wonderful for stuff like, say, giving Hermes an account on my Home Assistant server", "excerpt": "Neat stuff. I use Hermes with the $20/mo ChatGPT Codex integration, myself, as well as Qwen running locally on a 64GB M1 Max Macbook Pro to help save my ever-quickly shrinking Codex credits. It's been wonderful for stuff like, say, giving Hermes an account on my Home Assistant server (after taking a backup) and having it make a bunch of configurations, or draw conclusions based on historical sensor data (trying to de", "context": "home lab user", "use_case": "home automation and personal webapps", "switched_from": "", "story": "A self hosted AI software factory"}, {"id": 788924320, "item_id": 49307770, "url": "https://news.ycombinator.com/item?id=49307770", "by": "jeffnash", "date": "2026-08-14", "stance": "neutral", "quote": "a daemon running on the host machine which can, in turn, talk to Hermes", "excerpt": "What was the modality of interpreting the UI/interacting with the phone via ADB? Did you/your agent use screenshots + vision model to essentially target coordinates on screen? I ask because I'm curious if you found a non-screenshot + coordinate based ADB method to do so (that doesn't rely on UIAutomator). I wrote an APK that gives access to the accessibility service via an in-Android http server, which talks to a dae", "context": "", "use_case": "AI agent controlling Android", "switched_from": "", "story": "AI Driven Testing"}, {"id": 788711426, "item_id": 49294464, "url": "https://news.ycombinator.com/item?id=49294464", "by": "Wpnx330", "date": "2026-08-13", "stance": "recommend", "quote": "Tron, my Hermes agent, uses agent storming to orchestrate openCode agents and hermes subagents to handle most of my daily tasks.", "excerpt": "$0. but I use at least $8,000 worth of monthly tokens. I used to have: $200 Claude-max $10 github copilot $20 chatgpt $20 Cursor --- then, I spent roughly $5000 in tokens for a project which turned out to be a dud. Figured, inference wasn't going anywhere as its now 80% of my day. So, I built a 4x DGX Spark cluster and put GLM5.2 on it. Then put a few qwen models for vision and embedding purposes on my original DGX S", "context": "", "use_case": "daily task orchestration", "switched_from": "", "story": "Ask HN: How much money do you spend monthly on subscriptions for AI models?"}, {"id": 788403254, "item_id": 49275203, "url": "https://news.ycombinator.com/item?id=49275203", "by": "ljosifov", "date": "2026-08-12", "stance": "recommend", "quote": "I use Hermes as a general agent, non-coding agent, for everything that's not strictly coding.", "excerpt": "Atm OMP (oh-my-pi) with opencode-go subscription using deepseek-v4-flash-0731 (and mimo-v2.5 as advisor). Used pi before (still good, but too minimalist for all general use; works on Android under Termux btw) and OpenCode (which is ok too). I've used Codex the longest, but the $20 sub doesn't last that long. Before that Claude (and Claude on the web - about Nov'25), but nowadays with the new models not possible to do", "context": "", "use_case": "general non-coding agent", "switched_from": "", "story": "llama.cpp"}, {"id": 788362080, "item_id": 49272630, "url": "https://news.ycombinator.com/item?id=49272630", "by": "diseasedyak", "date": "2026-08-12", "stance": "neutral", "quote": "I use Hermes locally and you can't get around any of that", "excerpt": "I don't understand how they get around bot blockers and captcha. I use Hermes locally and you can't get around any of that, even using your own credentials.", "context": "", "use_case": "browser automation agent", "switched_from": "", "story": "Grok Bot"}, {"id": 788076672, "item_id": 49254792, "url": "https://news.ycombinator.com/item?id=49254792", "by": "l3x4ur1n", "date": "2026-08-11", "stance": "recommend", "quote": "I am getting to know Hermes agent", "excerpt": "I am getting to know Hermes agent and in the last couple of days I used it for searching the web for medical specialists or finding the best deal for a product online, manipulate with excel and word documents, gather data from APIs, finding stuff in my computer or keeping track of itself running in another process and keep the computer awake and when detecting the process is finished, put computer to sleep.", "context": "", "use_case": "web search, documents, computer tasks", "switched_from": "", "story": "LFM2.5 2.6B model competitive with 4x larger models"}, {"id": 787827904, "item_id": 49239244, "url": "https://news.ycombinator.com/item?id=49239244", "by": "resonious", "date": "2026-08-09", "stance": "neutral", "quote": "Right now I use hermes agent and just chat with it on Slack.", "excerpt": "Not surprised at all but there seems to be tons of these kinds of tools and I'm having a hard time picking one. Is there a nice list somewhere? I guess I can ask chatgpt... Honestly right now I do a lot of development from my phone - I don't have the time to pull out my laptop very much. Right now I use hermes agent and just chat with it on Slack. But sometimes I wish I had easier access to more advanced features, an", "context": "develops from phone", "use_case": "developing from phone via chat", "switched_from": "", "story": "OpenChamber: An Agentic Development Environment"}, {"id": 787523329, "item_id": 49220208, "url": "https://news.ycombinator.com/item?id=49220208", "by": "saturn5k", "date": "2026-08-08", "stance": "recommend", "quote": "I've been using V4 Flash Free with Hermes through Opencode Zen both personally and at my company and I've been having a great experience", "excerpt": "For the last 3 months I've been using V4 Flash Free with Hermes through Opencode Zen both personally and at my company and I've been having a great experience so far. It's my go-to model for terminal work, managing my entire ubuntu server, Cloudpanel, managing static websites, doing SEO audits, network tests, DNS troubleshooting, e-mail deliverability troubleshooting... Furthermore, in my company we are using MCPs fo", "context": "", "use_case": "agent harness", "switched_from": "", "story": "DeepSeek V4 Flash 0731"}, {"id": 786945538, "item_id": 49184096, "url": "https://news.ycombinator.com/item?id=49184096", "by": "hagen8", "date": "2026-08-05", "stance": "recommend", "quote": "How Claude Code/PI/ Hermes!! agent works", "excerpt": "Check out academic papers about: 1. Hierarchical skills, workflow, skill learning 2. Meta Harness, self-learning harnesses 3. Trace/trajectory representation 4. Common agentic benchmarks But first more basic things like 5. Blog posts form anthropic 6. How Claude Code/PI/ Hermes!! agent works 7. Agent sessions/ Forking/ Hooks", "context": "", "use_case": "learning agent harness design", "switched_from": "", "story": "Building an Advanced Agentic Harness"}, {"id": 786900482, "item_id": 49181280, "url": "https://news.ycombinator.com/item?id=49181280", "by": "ljosifov", "date": "2026-08-05", "stance": "recommend", "quote": "For general computer use mostly use Hermes.", "excerpt": "Love pi. It's good to have a minimal agent, always welcome. Even if only to bootstrap install other agents. E.g. recently Hermes stopped installing under Termux (v0.19 - no, v0.18 - yes). Agent pi to the rescue: installed it under Termux (Android), started it, pointed pi to the Hermes github, asked for v0.18 specifically - and it did it. Cherry on the top - asked it to install a plugin from github I use (unmerged PR)", "context": "", "use_case": "general computer use agent", "switched_from": "", "story": "Pi's Minimalism Is Its Advantage"}, {"id": 786552480, "item_id": 49159530, "url": "https://news.ycombinator.com/item?id=49159530", "by": "Swapnoneel", "date": "2026-08-03", "stance": "neutral", "quote": "I recently started using the Hermes agent", "excerpt": "So, I recently started using the Hermes agent and hooked it up with Step 3.5 Flash. It\u2019s a cheap and fast model, so I thought it would be enough for my workflow. However, I soon found that it hallucinates during a lot of tasks, and the output quality isn\u2019t something to write home about. On the other hand, using an expensive or frontier-level model means I\u2019ll burn through cash fast. I went down the rabbit hole to find", "context": "", "use_case": "agentic workflow", "switched_from": "", "story": "Is Hermes Agent unusable without a model router?"}, {"id": 786510560, "item_id": 49156910, "url": "https://news.ycombinator.com/item?id=49156910", "by": "AbsurdCensor", "date": "2026-08-03", "stance": "recommend", "quote": "I have it hooked into Hermes and have been using it to help bulk rename my media folders", "excerpt": "Not OP, but I use it for a ton of smaller things. I have it hooked into Hermes and have been using it to help bulk rename my media folders so they all follow a common format, add titles that sort of thing which wouldn't be easy to 'script'. Another thing I use it for is comparing data sets, looking at my exported Spotify artists and compare to what I have locally, and letting me know where there are missing artists, ", "context": "runs local AI box on solar", "use_case": "bulk renaming media, comparing data sets", "switched_from": "", "story": "Qwen3.8-Max: A New Bar for Coding and Cowork"}, {"id": 786356291, "item_id": 49147268, "url": "https://news.ycombinator.com/item?id=49147268", "by": "redrove", "date": "2026-08-02", "stance": "neutral", "quote": "I use it mostly in Hermes and sometimes for coding.", "excerpt": "The FP8 version from DeepSeek themselves [0], around 1800 tps prefill and 45 tokens per second decode. I\u2019ve been running a custom VLLM image with b12x as well as nvfp4_ds_mla. I would say it\u2019s quite fantastic in day to day, I use it mostly in Hermes and sometimes for coding. I have qwen 3.6 27b in an rtx 6000 pro as well so I use that as a workhorse in pi with DS as a reviewer/planner. [0] https://huggingface.co/deep", "context": "", "use_case": "agent harness", "switched_from": "", "story": "Show HN: NixOS-DGX-Spark \u2013 Nix and NixOS on the DGX Spark"}, {"id": 777385297, "item_id": 48586581, "url": "https://news.ycombinator.com/item?id=48586581", "by": "_pdp_", "date": "2026-06-18", "stance": "warn", "quote": "OpenClaw, at least initially, and Hermes both appear to have been heavily astroturfed using all kinds of blackhat tactics", "excerpt": "I might be a little more paranoid than most because of my profession, but none of these projects inspire enough trust to justify being installed - let alone directly on the machine I use every day. OpenClaw, at least initially, and Hermes both appear to have been heavily astroturfed using all kinds of blackhat tactics, which is a huge red flag to me. And then there is the code.", "context": "security-minded profession", "use_case": "", "switched_from": "", "story": "Migrate from OpenClaw"}, {"id": 776840512, "item_id": 48552532, "url": "https://news.ycombinator.com/item?id=48552532", "by": "xyzzy123", "date": "2026-06-16", "stance": "recommend", "quote": "I use hermes with crons and kanban for this.", "excerpt": "I use hermes with crons and kanban for this. I have a \"self driving\" homelab where upgrades & config changes happen in a non-prod ct before being applied to \"prod\" (just, a diff ct). Its mainly compose stacks with data volumes on zfs that gets snapshotted a lot to limit possible data loss. I use the orchestrator to break down regular tasks like \"health check the whole env\" or \"find all containers that need an update\"", "context": "homelab operator", "use_case": "self-driving homelab orchestration", "switched_from": "", "story": "My Homelab AI Dev Platform"}, {"id": 775318864, "item_id": 48457429, "url": "https://news.ycombinator.com/item?id=48457429", "by": "apexalpha", "date": "2026-06-08", "stance": "recommend", "quote": "I use Hermes at home. Swapped out Openclaw for this. It seems to work better with smaller contexts", "excerpt": "I use Hermes at home. Swapped out Openclaw for this. It seems to work better with smaller contexts, chuncking it up in smaller pieces. I don't code with it, I use Claude for that. But what I do do: it's a sysadmin for my homelab. It has a read-only mcp server to check the k8s status and has it's own ssh access to fix stuff after I approve it per session. It's magical. Each morning I get a small update whether the bac", "context": "homelab user", "use_case": "homelab sysadmin agent", "switched_from": "OpenClaw", "story": "Hermes Agent \u2013 Open-Source AI Agent with Persistent Memory"}, {"id": 774677265, "item_id": 48417329, "url": "https://news.ycombinator.com/item?id=48417329", "by": "igorhvr", "date": "2026-06-05", "stance": "recommend", "quote": "Hermes basically rules my personal life at this point - it is a _very_ useful personal assistant.", "excerpt": "I use PI ( https://pi.dev ) and ( https://hermes-agent.nousresearch.com/ ) as the main drivers together with deepseek-v4-pro as the main model (~10M/day tokens overall there). Hermes basically rules my personal life at this point - it is a _very_ useful personal assistant. I also use it at work (integrated at Slack) and at this point it answers most of both my emails and slack messages (I calibrated https://github.co", "context": "", "use_case": "personal assistant, email and Slack replies", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 768932368, "item_id": 48058273, "url": "https://news.ycombinator.com/item?id=48058273", "by": "ikidd", "date": "2026-05-07", "stance": "recommend", "quote": "I switched to Hermes Agent and it's been night and day how much more stable and usable it is over OpenClaw.", "excerpt": "I switched to Hermes Agent and it's been night and day how much more stable and usable it is over OpenClaw. What a mess that's turned into", "context": "", "use_case": "AI agent", "switched_from": "OpenClaw", "story": "OpenClaw Had a Rough Week"}, {"id": 764575026, "item_id": 47785939, "url": "https://news.ycombinator.com/item?id=47785939", "by": "superfrank", "date": "2026-04-15", "stance": "recommend", "quote": "it's the first one where it didn't feel like I was constantly needing to fix it", "excerpt": "I don't use OpenClaw I tried but found it fragile and it's personality off putting. I then tried NanoClaw, but found the lack of communication channels limiting and could never really get it to create skills that felt solid. I recently just switched to Hermes Agent (like last week) and it's the first one where it didn't feel like I was constantly needing to fix it, so at the moment I'm happy with it. What do I use it", "context": "", "use_case": "personal assistant and automations", "switched_from": "NanoClaw", "story": "Is anyone actually using OpenClaw?"}]}