Renew

Hermes Agent on Unraid — Complete Install Guide (v0.14.0, Built from Hard-Won Experience) Prerequisites Unraid 6.12+ Docker enabled An SSD or NVMe pool mounted (e.g., /mnt/cache/ or /mnt/ssd/) — not an array disk via /mnt/user/ An Ollama container already running and accessible on your LAN At least one Ollama model with native context ≥ 64K (gemma4, qwen 3.6, llama 3.x, etc.) Optional: a Telegram bot token from @BotFather and your numeric user ID from @userinfobot Phase 1 — Prep Ollama Properly Before Hermes touches anything, make sure Ollama is configured for agent work. Edit your Ollama container template Add these environment variables (or update them if they exist): Key Value Purpose OLLAMA_HOST 0.0.0.0:11434 Reachable from other containers OLLAMA_CONTEXT_LENGTH 65536 Agent workloads need 64K+ OLLAMA_KEEP_ALIVE 24h Keep model warm in VRAM OLLAMA_FLASH_ATTENTION 1 Faster, less VRAM OLLAMA_NUM_PARALLEL 2 Allow concurrent requests OLLAMA_MAX_LOADED_MODELS 2 Main model + optional aux OLLAMA_SCHED_SPREAD 1 (optional) Force multi-GPU split (only if needed) Apply. Verify with: docker exec ollama printenv | grep OLLAMA docker exec ollama nvidia-smi Both GPUs should be visible. Pick and prepare a model Run: docker exec ollama ollama list Pick one with native context ≥ 64K. Verify: docker exec ollama ollama show <model-name> | grep -i "context length" If the number is ≥ 65536, you're set. If lower, pick a different model or create a derived Modelfile. Phase 2 — Prepare the Appdata Directory This is the single biggest source of failure later. Get it right now. Critical: use a direct pool path, NOT /mnt/user/ The FUSE-based /mnt/user/ filesystem breaks SQLite locking. Always use the direct pool mount. in console: mkdir -p /mnt/cache/appdata/hermes-agent (Replace /mnt/cache/ with /mnt/ssd/ or whichever pool you use for appdata.) Do NOT chown to 99:100 The Hermes image expects UID 10000 internally. Match that: in console: chown -R 10000:10000 /mnt/cache/appdata/hermes-agent Phase 3 — Run the Setup Wizard (Carefully) Pull the image and run the wizard docker run -it --rm \ -v /mnt/cache/appdata/hermes-agent:/opt/data \ nousresearch/hermes-agent setup Wizard answers — exact values Model provider: Choose Custom Endpoint (enter URL manually) — NOT "Custom Direct API." API base URL: http://<your-unraid-ip>:11434/v1 (e.g., http://10.10.10.150:11434/v1 — the /v1 is required, OpenAI-compat path) API key: ollama (any non-empty string — Ollama doesn't validate it) Model name: Exact tag from ollama list, e.g., gemma4:26b Context length: 65536 ⚠️ Critical typing rule: Do NOT press the up arrow during text input. The wizard captures the literal \e[A escape sequence and corrupts the value. If you mistype, use Backspace, never arrow keys. Configure aux models: Skip / use main provider for everything. Adding aux models with mismatched context windows causes silent failures. Telegram setup (optional): Bot token: paste the full <numeric>:<alphanumeric> from BotFather (40+ chars). If you only have a placeholder, skip this step rather than entering junk. Allowed users: paste your numeric Telegram user ID from @userinfobot. Never leave empty — "open access" means anyone with your bot username can burn your tokens. Agent name / SOUL: accept defaults. ⚠️ Critical: NEVER Ctrl+C the wizard The wizard atomic-commits at the end. Ctrl+C = lost configuration. If a step asks something you don't have an answer for, enter a placeholder (e.g., none, skip) and edit the file afterward. Always let the wizard run to completion. Verify what the wizard wrote cat /mnt/cache/appdata/hermes-agent/config.yaml | head -10 grep -E "TELEGRAM|HERMES" /mnt/cache/appdata/hermes-agent/.env The config.yaml should have a clean model: block. The .env should have your Telegram credentials if you set them up. Phase 4 — Build the Unraid Docker Template Switch to Advanced View in the top-right toggle of the Add Container page. Without this, you can't add Post Arguments or Extra Parameters. Top section Field Value Name hermes-agent Repository nousresearch/hermes-agent:latest Network Type Bridge Console shell command Bash Privileged Off Post Arguments gateway run Extra Parameters --restart=unless-stopped --shm-size=1g --memory=8g Icon URL (optional) https://avatars.githubusercontent.com/u/134168893?s=200 WebUI http://[IP]:[PORT:9119]/ Ports — add BOTH at once Gateway API: Field Value Config Type Port Name Gateway API Container Port 8642 Host Port 8642 Default Value 8642 Connection Type TCP Web Dashboard: Field Value Config Type Port Name Web Dashboard Container Port 9119 Host Port 9119 Default Value 9119 Connection Type TCP Path (just one) Field Value Config Type Path Name Config and Data Container Path /opt/data Host Path /mnt/cache/appdata/hermes-agent Default Value /mnt/cache/appdata/hermes-agent Access Mode Read/Write ⚠️ Use the direct pool path (/mnt/cache/ or /mnt/ssd/), never /mnt/user/. Environment Variables — exactly these, nothing extra Dashboard: Key Value Notes HERMES_DASHBOARD 1 Enable web dashboard HERMES_DASHBOARD_HOST 0.0.0.0 LAN-accessible HERMES_DASHBOARD_PORT 9119 Match the port mapping HERMES_DASHBOARD_TUI 1 In-browser Chat tab API server: Key Value Notes API_SERVER_ENABLED true OpenAI-compat API on 8642 API_SERVER_HOST 0.0.0.0 LAN-accessible API_SERVER_KEY (generate) See below API_SERVER_CORS_ORIGINS * Allow browser apps Generate API key once: openssl rand -hex 32 Paste that into the API_SERVER_KEY field. Local model tuning: Key Value Notes HERMES_STREAM_READ_TIMEOUT 1800 30 min timeout for slow local inference TZ America/New_York Your timezone Click Apply The container will pull the image (~2 GB) if not already cached, then start. Phase 5 — First Boot Verification Watch the startup logs docker logs -f hermes-agent What you should see (in order): Fixing ownership of /opt/data to hermes (10000) Syncing bundled skills into ~/.hermes/skills/ ... Done: 87 new, 0 updated, 0 unchanged. 87 total bundled. (first run) or 0 new, 0 updated, 87 unchanged (subsequent) Starting hermes dashboard on 0.0.0.0:9119 (background) [dashboard] Hermes Web UI → http://0.0.0.0:9119 The gateway banner No errors — specifically: ❌ No esbuild permission denied ❌ No database is locked ❌ No YAML parse errors ❌ No SIGTERM restart loops ❌ No "No user allowlists configured" (if you set up Telegram) Ctrl+C to stop tailing once it settles. Verify ports are mapped docker port hermes-agent Expected: 8642/tcp -> 0.0.0.0:8642 9119/tcp -> 0.0.0.0:9119 Open the dashboard Browser → http://<your-unraid-ip>:9119 You should see: Status page showing gateway running and version Chat tab in the sidebar (the in-browser TUI is working) Config tab with your model and context settings populated Logs tab populating Phase 6 — Smoke Test the Full Stack Test via the GUI Chat tab Send: "hello, what model are you running?" Should reply with model name and respond cleanly. If it errors with "context window below minimum 64,000," your config.yaml has the wrong context_length — go to Config tab and verify it's 65536. Test tool use via Telegram (if configured) Send to your bot: "Run ls -la in the workspace and tell me what's there" Should: Acknowledge the request Run the tool Reply with file listing While it runs, in terminal: docker exec ollama ollama ps docker exec ollama nvidia-smi Expected: ollama ps shows your model loaded with CONTEXT 65536, 100% GPU nvidia-smi shows ~22-24 GB VRAM in use, your model's process listed Set Telegram home channel In your Telegram chat with the bot, send: /sethome This lets Hermes deliver scheduled task results and cross-platform messages to that chat. Troubleshooting Quick Reference Symptom Likely Cause Fix ERR_CONNECTION_REFUSED on :9119 Port not mapped or dashboard crashed Verify docker port hermes-agent shows 9119; check logs for [dashboard] errors Container restart-loops with esbuild error Wrong UID — directory permissions Re-chown appdata to 10000:10000, remove HERMES_UID/HERMES_GID env vars "database is locked" warning Appdata on /mnt/user/ FUSE Move appdata to /mnt/cache/ or /mnt/ssd/ direct pool path YAML parse error line 3 column 6 Hidden characters or \e[A from arrow keys in wizard Delete config.yaml, re-run wizard, type carefully "context window 32,768 below minimum 64,000" context_length in config.yaml too low Dashboard → Config → General → set to 65536 Telegram bot doesn't respond Missing TELEGRAM_ALLOWED_USERS in .env Add TELEGRAM_ALLOWED_USERS=<your_id> to .env, restart container Model loaded but only on one GPU Working as designed (fits on one card) Add OLLAMA_SCHED_SPREAD=1 to Ollama if you want forced split Wizard "leave empty for open access" prompt Don't! Always set explicit allowlist on Telegram/Discord/Slack Optional Improvements Once everything works, these polish steps are worth doing: Add a fallback provider in config.yaml for when local inference is unavailable Install Chrome/Playwright inside the container for browser_navigate tool Configure cron jobs in the dashboard for scheduled agent tasks Bump container memory to 16 GB if you'll do heavy multi-turn agent work Save the Unraid template as a Community Apps XML so you can rebuild quickly Summary of Lessons Learned The four mistakes we made and what to remember: UID matters more than Unraid conventions. I had you set HERMES_UID=99 to match Unraid's "nobody" — but the image's pre-built /opt/hermes/ is owned by UID 10000. The mismatch killed the dashboard TUI build. Don't fight the image — use UID 10000 and chown appdata to match. /mnt/user/ is not safe for SQLite-using containers. Always use the direct pool path. This applies to every Docker container on Unraid with a database (Plex, *arr stack, Nextcloud, Hermes, etc.). The wizard atomic-commits. Ctrl+C loses everything. If you don't have a value for a prompt, enter a placeholder rather than aborting. Hermes' context check reads YOUR config, not the model's max. The 32K error wasn't a model limitation — it was the value we wrote in config.yaml. Always set context_length ≥ 65536 for any model that natively supports it. Follow this guide top to bottom and you'll have a working Hermes Agent on Unraid in 20 minutes instead of 4 hours. Save it somewhere — you may want to rebuild someday. I am not an expert, I know a decent amount but I used Opus 4.7 to add a custom docker and install the latest hermes because I could not find a docker in the app store that had the latest.. of course they will probably be one there in the next hour :) Hope this helps someone.

Help please. I run two 3090's with ollama. Both were working fine yesterday. Today updated to 7.3, now when I load an llm, it only works in one of my gpus. It should span across both like it did before. If I load a second llm, it will load on the other card, but one will not load across like it was yesterday. If I load the one llm, itis crawling, going to system ram. No idea why. the ollama has all gpus tag, and again, it was fine yesterday. both show up in nvidia smi. Both show up and are checked in the nvida plug in.loki-diagnostics-20260518-0110.zip Any thoughts? ideas? is this a 7.3 issue? or? Thanks in advance.

its not the driver, the driver is working fine. both cards show up in the dash, both show up in nvidia smi, anyone else have these issues, please?

I have two 3090's use ollama, openclaw. both worked before the update, now both show in watch -n 1 nvidia-smi but the second one is no longer being used by ollama. How come? What can I do to fix this? Please help loki-diagnostics-20260518-0110.zip

Hi, Can not find an ollama container thread on the forum. Ollama has been updated. my app under docker shows update available. I click update, it does not update. Same version. I can try various ways, force update, it goes through the motions, but does not update. I have to delete the old docker and reinstall, then its updated. Is this a known issue? How can we get it to just update to latest version? Help is appreciated!! Thanks

I am trying to learn more about Ai. I have ollama and webui set up. I attempted to get openclaw, it worked just okay for a few hours then an update of openclaw made it die... about to reinstall. I see a lot of info online but Ai is changing so fast, and containers that are advertised on unraid a few months ago are gone with some new ones arriving. I install something and the info on that docker seems outdated, have to play around a lot to get it to work etc. Can you help a brother out? As of today, July 29, 2026, on unraid, with 2 nvidia 3090 cards, what actually works? Can we install claude code in a docker? codex? Hermes? What sort of works but is a pain? Any dockers you recommend? Any settings to be on the look out for? What is your stack and case use? Can we get a group or sticky just for Ai? One where it lists out all the working containers and suggested stacks? I am not entirely sure of anything here so forgive me if I state something improperly, trying to learn :) Thanks!

I am changing my network around. Currently my unraid has a static ip address listed on my network config file. something like this USE_DHCP="no" IPADDR="192.168.1.100" NETMASK="255.255.255.0" GATEWAY="192.168.1.1" I want to change it to use DHCP and have my firewall router assign the IP. I get you change the use DHCP to yes, but do I leave Ipaddr blank? and do I edit or leave blank the netmask and gateway? If you are wondering, this install has been upgraded many times, there is nothing listed in the settings, no options to change there, its only on the USB drive. Thanks!

I am trying to graduate from Wyze to a much better system. What works best together? I want to be able to access all cameras on an app on phone or computer, automate with home assistant, and have it all 24/7 record to my unraid server. Prefer to have it all on my computers, not on a companies. I am considering Reolink cameras, maybe some Eufy if it can all integrate, but what cameras work best? With that in mind... I understand reolink has its own software that works with home assistant. Can you install the reolink software right onto unraid in a docker? or do you have to install on another windows machine, or in a vpn? Same for Eufy. And how about Blue Iris and Frigate. I was thinking to use that, and use Home assistant. Which one? or neither? So, what am I missing? What is the best practice? and what cameras work best with what I am looking to do? Any up to date install guides? Thank you in advance!

Thanks, I deleted all the db's, had to stop the container and restart, then was able to rebuild the db. Then I saved it as a backup, I never did a back up before. I also had to recreate the settings for news, sab etc. Also, not sure it this caused the issue, but I saved appdata to cache, previously it was on the array and I did not have a cache... everything else worked fine, but just in case I added a cache... if that helps anyone else who has this issue. Thanks again

Thanks, but how do I get to system backup? Sonarr web gui does not load. Just says malformed

Help! I have used Sonarr for a long time, always trouble free until now. " database disk image is malformed database disk image is malformed" "Version 4.0.15.2941" Unraid 7.1.2 had the issue, updated to 7.14 to see if it helped, still had issue. Uninstalled, reinstalled, still had issue. Uninstalled, deleted config folder, worked for that day, rescanned all my shows, still worked then next day trouble came back. Radarr works no problem Lidarr works. How do I fix? Thanks

I think a lot of the people here have large media libraries. I know I do. So many files it is near impossible to manually check to see if they all work. Its frustrating to try to watch something you had on your server for years only to find out it is somehow not working, in the wrong language or not the show you thought it was. Is there a plugin already made, or can we make one that: Goes through each movie or tv show, sees if it will play fully. See if all episodes are there in the series. Check to see if it is the right movie, you might have it mislabeled, so get meta data, was the show you intended it to be 120 minutes, but the file you actually have is only 90 minutes? notify it does not add up. Notify or auto correct if a show is missing or corrupt? Anything like that available? I know VLC can detect and fix corrupt files, so I imagine it is not too hard to make a plug in like that...well not too hard for someone else to do, I certainly cant do it :)

Sorry to butt in, but I was considering switching from XFS to BTRFS. Is the issue here due to the BTRFS? Aside from the power issue that could happen to anyone ( I have had 100's of shut downs in my old now dead server with XFS and I had no issues with drives ), what caused the issue here? Thanks in advance

Thanks Jorge, For NTRFS and ZFS, you mentioned it has checksums that will let you know if there is a corruption issue. Can you let me know how it works? Do you have to run a check every once in a while to see if there is an issue? Is there a plug in for that? Really appreciate the advice. Thanks Neal

I currently have XFS on my array. Just rebuilt my server and adding some more drives. My old server was crashing all the time. I ran a partial parity check, came back with a lot of errors. When searching forums I saw there is no way to figure out what files are in error? That apparently the parity drive just copies the version of the file from the disk and hopes it okay? I saw some comments about various file systems that might be better than others when it comes to data checking. My main focus is media server. What file system should I run to make sure files do not corrupt? and if they do they are corrected? Does encryption do anything in regard to size of files, or speed of reads? What benefit or penalty does encryption have? What other programs or plug ins should I use to protect data? Any plug ins to "test" media files to make sure they are still playable? And... when I move my data around to my new disks and possibly new file format, should I run a full parity first? or will moving it basically accomplish the same result since when you move it recreates the parity from the new drive? Thank you in advance!

I figured it out, for anyone who needs the same info: Unassigned Devices Plugin Unassigned Devices (UD) includes a lot of functionality and has become a bit complex. Please read the first and second post. You will find answers to most of your questions. Note: You will need to install the Unassigned Devices Plus (UD+) plugin to enable HFS+ and APFS (Apple file formats) and exFAT (flash larger than 64MB) disk mounting, and to enable 'Destructive Mode' for formatting of some UD supported disk formats. UD and UD+ are available in Community Applications (CA). Hover your mouse over any active area on the UD page and a tool tip will show you what clicking that area does. UD supports all Unraid native disk formats. You will need to install the 'Unassigned Devices Plus' plugin to mount HFS+, APFS and exFAT file formats. UD has a destructive mode that allows deleting disk partitions and formatting disks. If Destructive Mode is not turned on in the UD Settings, you WILL NOT be able to format a disk. Go the the Settings page and scroll to the bottom to see the UD settings. To format a disk: Destructive Mode must be enabled. You will need to install the 'Unassigned Devices Plus' plugin to enable Destructive Mode. UD Plus will install the 'parted' package needed for formatting and deleting partitions. Disk must have all partitions removed. Unmount the disk, click on the '+' icon next to the serial number, and click on all red-X to delete partitions. You can also click on the red-X next to the disk serial number to delete all partitions. A precelared disk will have a partition without a file system and will show a grayed 'Mount' button. You can assign this disk directly to the array and Unraid will see the disk as 'pre-cleared' and will not clear it again. If you want to format the disk for use in UD, you need to first click on the red-X on the preclear status line to remove the preclear stats and then remove all partitions by clicking on the red-X icon next to the serial number and then you'll be able to format the disk. There are different operations in various active areas (especially the disk serial number) based on whether or not the disk drive is mounted. If the disk is not mounted, click on the '+' icon by the serial number, click on the partition name, you will get a pop-up dialog to change the mount point name. This will now become the mount point and the share name when the disk is shared. In order to share any UD device, sharing needs to be enabled in the UD Settings and the switch turned on to share the particular device. SSD disks formatted with xfs, btrfs, or ext4 will be mounted with 'discard' if the "Mount SSDs with 'discard' option?" is set to "Yes". This includes encrypted disks. Reiserfs does not support discard. This enables TRIM on SSD devices. If you have the trim plugin installed, it is recommended to not mount SSD disks with discard. Disks formatted XFS or BTRFS will be partitioned compatible with the array disks and can be installed in the array without a re-format. SSD devices are now partitioned with a 1MiB offset as of Unraid 6.9 Beta 25 and cannot be installed as a cache or pool device on earlier versions. Because of security issues with samba, the mounting of remote SMB shares with CIFS has become more complicated. The default protocol is now SMB3 and not SMB1; the default security is now ntlmv2 and not ntlm. UD will try to mount SMB shares with SMB3, then SMB2, and then SMB1 to try to get the mount to use the most secure protocol it supports and the ntlmv2 protocol. If you have an older server that only supports SMB v1, you need to update that server so it will support SMB v2 or v3. SMB v1 is being phased out and will probably eventually be removed from samba. You will not be able to mount a remote SMB share using SMBv1 if NetBIOS is disabled in Unraid. It is recommended to disable NetBIOS on Unraid servers.

I believe so. Is there an issue with Unraid 7? or what am I missing? Any help is appreciated.

Hi, I have Unassigned devices and UD plus and UD preclear. Using Unraid 7.1.2 I have 2 white label disks that are already formatted, they show up in UD. Tried to preclear it says "There are no disks that can be precleared. A disk must be cleared of all partitions before it can be precleared. You can use Unassigned Devices to clear the disk." Went into UD, can not figure out how to delete partitions. How do I get it to work? Thanks

Thanks, the trial version worked or at least started up. I am wondering if the USB from my old server is usb2 or something by default since the really old USB1 does boot up. I think I remember something about how sometime the new USB's will not work for boot up? I am going to see what I can do with my MB maker, but if I cant get the old USB to work, can I transfer the info to a new USB, and use that, transfer my license to that one? And when you said : back up current config and rebuild USB? Are you meaning my old one from my old server? or rebuild on a new USB? Any details on how to do that? Really appreciate the help. Thanks

Hi everyone, I built a new server, swapped over my old USB which was a usb sancruiser fit 32gb that worked fine in my old computer for 5 years but it will not in my new one. My old one was a Gigabyte X570 I AORUS PRO WIFI AM4 with a 3700x AMD chip. My new one is a Gigabyte Aorus Z790 Elite AX with a 14900k. I was able to boot to an old USB with memtest86 on it, so maybe its the fact its a USB 2 or 3 Any advice?

Hi, My old server worked great for 5 years, then I upgraded to 7, and maybe its a coincidence, but one thing after another went wrong. I want to move my array to a new server and possibly reinstall everything from scratch. First of all, can I do t hat? Just plug in drives into a new server and have a new unraid USB see them? And two, how do I transfer my unraid to a new USB? Any advice is appreciated.

Hi, I set up an array of 6 disks and when I first set it up, I used an encryption password. I do not want the encryption password on there anymore... So I was planning to set up a second array, starting with 2 disks and have that array not have an encryption password But... can you do that? If you already have an array that has a password, can you create a second without one in the same unraid? Or will it default to the password? I wanted to create a second one, and transfer data over, then take the disks out of the first array and then add to the new one without the password, as well as having the new ones be ZFS. Not sure if ZFS on an array is a benefit if it is not a pool, so any advice on that is appreciated. Thanks Neal

Hi, Sorry for the Newb question. I have an old computer I want to use for another purpose but I would like to keep the old computers HD running in a VM. Its windows 10. How should I convert to a VM? What software to use etc? What format(?) of Vm can be used with unraid? How about promox? and can I swap a VM back and forth from unraid to proxmox? Thank you in advance,

Hi, I had my unraid server up and running for 5 years, then an update crashed all the dockers and I had to reinstall. I reinstalled the binhex versions of the above dockers with emby. Sonar and radarr communicate with SaB and Sab downloads the files... but they stay in the downloaded folder. Sonarr and Radarr are no longer moving them to their appropriate folders and renaming them. It was a while ago I originally set it up all so I am probably forgetting a setting or something. Please help. Thanks