PikkonMG

Wanted to check back, did you figure it out if not please share your config.

That error is a YAML parse error I think, right now I can’t reproduce it from the current template working fine on my end. Please paste your current config.yaml and the full log line showing "did not find expected key" so I can check and see where it might be coming from.

{ "gateway": { "mode": "local", "bind": "lan", "controlUi": { "allowInsecureAuth": true, "allowedOrigins": [ "http://localhost:18789", "http://127.0.0.1:18789", "http://192.168.50.250:18789" ] }, Your request id will show up from you browser like in your post on page before. Please make sure once you figure this out and get it running that you delete and reinstall it dont give out your requestid stuff like that. You can also unauthrize that id and get a new one using commandline inside the container if you wiosh to do that.

If your on chrome or like me edge then edge://flags/#unsafely-treat-insecure-origin-as-secure Enable Insecure origins treated as secure and add your local ip on unraid server running openclaw I.E http://192.168.1.100:18789 In your config dont use wildcard like * edit it to use the ip address of your unraid server And you have to pair you device this has been posted on a few times here now you get pairing request via the browser just take that requestid and run it with openclaw devices approve xxxxxxxx-xxxxxx-xxxxxx-4443434cac61 --token "$OPENCLAW_GATEWAY_TOKEN" inside the container.

Just did another test install on unraid and it installed just fine. Only difference from post on page 6 is you now get your device pairing required requestId via the browser and don't have to run openclaw devices list. Take the requestId via the browser and pair it openclaw devices approve xxxxxxxx-xxxxxx-xxxxxx-4443434cac61 --token "$OPENCLAW_GATEWAY_TOKEN" if openclaw.json is being edited while the container is running openclaw might overwrite or revert those changes. Stop the container first, edit the file, save, then restart. Also confirm /root/.openclaw is properly bind-mounted to persistent Unraid storage (/mnt/user/appdata/openclaw) or changes may be lost during container recreation.

I know this take will probably be unpopular with community here but most will be better off running OpenClaw or Hermes on a Raspberry Pi 5 or Budget VPS with Hetzner/Contabo/OVHCloud. Downside to VPS is local llm usage but you can get around that with wireguard/tailscale.

OpenClaw docker doesn't like trying to use tailscale the way unraid doesnt its container setup. Run tailscale directly on unraid.

This should still work https://forums.unraid.net/topic/196865-support-openclaw-ai-personal-assistant/page/6/#findComment-1614922

🫡 Np.

Template was created a few months ago and probably did what it did based off how openclaw was at the time with workarounds for Unraid permissions ects. But ya docker now should be node UID 1000. If I was an existing user id just leave it like it is as /root/.openclaw` owned by root. Switching users would cause permission errors.

If its related should make live soon I would think https://github.com/openclaw/openclaw/releases/tag/v2026.4.25-beta.2 "Plugins/Bonjour: stop the gateway from crash-looping on CIAO PROBING CANCELLED when the mDNS watchdog cancels a stuck probe. Restores the rejection-handler wiring dropped during the bonjour plugin migration and shares unhandled-rejection state across module instances so plugin-staged copies of openclaw/plugin-sdk/runtime register into the same handler set the host consults. Especially affects Docker on macOS, where mDNS probing reliably hits the watchdog. Thanks @troyhitch."

Running AMP within docker is not a supported setup. Run it in a VM or on a dedicated machine. Its been a min since I bought licence which one do you have?

Template for Serena MCP Server Serena is an MCP (Model Context Protocol) server that lets AI coding tools connect to your code projects. It allows MCP-compatible clients like Claude Code to access your project files, navigate code structure, and provide better context-aware responses. Setup Install via Community Applications Set your Config Directory (default: /mnt/user/appdata/serena-mcp/config/) Set your Project Directory to the folder you want Serena to access Apply and start the container First Start — Required One-Time Configuration Edit /mnt/user/appdata/serena-mcp/config/serena_config.yml and make the following changes: web_dashboard_listen_address: 0.0.0.0 gui_log_window: False web_dashboard_open_on_launch: False Restart the container after saving. Connecting Your MCP Client http://[SERVER_IP]:9121/mcp Web Dashboard: http://[SERVER_IP]:24282 Adding More Projects Click Add another Path in the Unraid template UI for each project: Field Value Host Path /mnt/user/your-project/ Container Path /workspace/your-project/ Projects on Another Machine Share the folder over SMB/NFS, mount it on Unraid via the Unassigned Devices plugin, then add it as a path: Field Value Host Path /mnt/remotes/my-pc-share/your-project/ Container Path /workspace/your-project/ Links GitHub: https://github.com/oraios/serena Docker Docs: https://github.com/oraios/serena/blob/main/DOCKER.md Template Repo: https://github.com/PikkonMG/unraid-docker-templates

Unraid terminal chown -R 99:100 /mnt/user/appdata/your-container If its permissions issue then chmod -R 775 /mnt/user/appdata/your-container

If you really want to use CubeCoders AMP on Unraid to be honest a docker container is by far the worst way to do it. It really needs its on system. If you must run it on Unraid do so within a Debian VM. Trying to run containerized game instances inside an AMP Docker container that’s the problem. You’re stacking container runtimes on top of each other. Im not saying you can't get it running just saying it's wrong way of going about doing it.

Not with a normal image pull alone. The container would need to be built with claude included, or have a startup script that installs it each time. Manually installing it inside the container won’t survive an update/recreate. So the proper fix is either the maintainer adding Claude Code to the image, or you making a custom image based on it. You can do something with User Script Plugin but it would be just a work around and im not even sure how to aproach it. You can also do VPS route. Create a VPS on your Unraid server and install OpenCLaw or Hermes.

What model you you trying to use? Try something small like phi3:mini or gemma thats 2B or lower. Check and make sure you can actually hit ollama curl http://<OLLAMA_IP>:11434/api/tags Also make sure your Ollama instance is setup to use cpu or igpu not passing NVIDIA settings like --gpus=all etc.

Dont use the web gui. Do openclaw onboard via the terminal in docker container. Follow the instruction set ollama and local as provider, pick you model. Use your Unraid or Ollama's IP do not use any forum of localhost or 127.0.0.1 ect example http://192.168.1.50:11434

I dont use tailscale so i can't say 100% I use my own wireguard server at network level. My guess based off OpenClaw Docs is that you probably need to run tailscale on unraid it's self and add your "https://your-tailnet.ts.net" along with your "10.x.x.x" to the allowedOrigins in your openclaw.json.

OpenClaw template already has a Variable for DISCORD_BOT_TOKEN. Just click show more settings and you will see discord, telegram , copilot ect. Start by checking that becuase if you did what you said container config now has duplicate entries for the same env var name.

Was no llama-swap template on CA and needed it so here we go! llama-swap is a lightweight proxy that sits in front of llama-server and allows for hot swap models. You can serve many models from a single OpenAI-compatible endpoint without manually restarting anything. Features Hot model loading and unloading Aliases and groups for multi-model concurrency OpenAI-compatible API GPU Support The template includes tags for NVIDIA (cuda), AMD (rocm), Vulkan (AMD/Intel iGPU), and CPU-only. Each tag description includes the required Extra Parameters for that GPU type. Setup config.yaml Must be manually created example config is linked to below. You can also view llama-swap github for other examples Use Unraid terminal to make edits so filesystem watchers can see files been changed for Hot Reload I.E nano /mnt/user/appdata/llama-swap/config/config.yaml "Waiting for Approval" Community Applications Install Search for llama-swap in the Apps tab Set your Models and Config directory paths Create a config.yaml in your Config directory (example config linked in the Overview) Reference your models in config.yaml as /models/yourmodel.gguf Select the tag matching your GPU and update Extra Parameters accordingly Start the container and access the UI at http://your-server-ip:8080/ui Manual Install Download the template XML from the link below Place the XML file in /boot/config/plugins/dockerMan/templates-user/ on your Unraid server In the Docker tab click Add Container and select llama-swap from the template dropdown Set your Models and Config directory paths Select the tag matching your GPU and update Extra Parameters accordingly Start the container and access the UI at http://your-server-ip:8080/ui Template download: https://raw.githubusercontent.com/PikkonMG/unraid-docker-templates/main/templates/llama-swap.xml Links GitHub: https://github.com/mostlygeek/llama-swap Example config: https://github.com/PikkonMG/unraid-docker-templates/blob/main/examples/llama-swap/example-llama-swap-config.yaml Support: https://github.com/mostlygeek/llama-swap/issues My Unraid Template Repo: https://github.com/PikkonMG/unraid-docker-templates

If your on chrome or like me edge then edge://flags/#unsafely-treat-insecure-origin-as-secure Enable Insecure origins treated as secure and add your local ip on unraid server running openclaw I.E http://192.168.1.100:18789 Edit your openclaw.json in appdata->openclaw->config you will see section like this "allowedOrigins": [ "http://localhost:18789", "http://127.0.0.1:18789" ], Edit it to include your Unraid Servers IP "allowedOrigins": [ "http://localhost:18789", "http://192.168.1.100:18789", "http://host-name-or-whatever:18789", "http://127.0.0.1:18789" ], Start OpenClaw Docker and open the webui. then just close it. Open console terminal for OpenClaw docker and run printenv OPENCLAW_GATEWAY_TOKEN openclaw devices list --token "$OPENCLAW_GATEWAY_TOKEN" It will spit out some stuff like 🦞 OpenClaw 2026.3.24 (unknown) — Say "stop" and I'll stop—say "ship" and we'll both learn a lesson. │ penclaw devices approve --latest --token "$OPENCLAW_GATEWAY_TOKEN"◇ Pending (1) under that you will see your Pending (1) client and you will see a key something like xxxxxxx-xxxx-xxxx-xxxx-xxxxxx3971 copy that key and run openclaw devices approve xxxxxxx-xxxx-xxxx-xxxx-xxxxxx3971 --token "$OPENCLAW_GATEWAY_TOKEN" After that try opening webui should work. If you use a reverse proxy you could set it up at OpnClaw and probaly skip the "Enable Insecure origins treated as secure"

Edit: 4/06/2026 now on CA , how to and guide on using Nexus Orchestrator can be found here https://github.com/PikkonMG/unraid-docker-templates/blob/main/docs/Nexus_UNRAID_GUIDE.md

Release Notes: Nexus v1.1.9 This update covers all major changes since v1.1.3. The biggest highlights are live reasoning display, multiple local provider support, a full security hardening pass, and a much cleaner UI. Thinking / Reasoning Display (v1.1.9) Nexus now shows live reasoning for models that support it. For Ollama models, the server sends think: true through the native API and streams reasoning token-by-token as it generates. Models like DeepSeek R1 and QwQ that natively emit <think> tags are also supported. Reasoning appears in a collapsible purple section above the response and stays visible until you manually close it. There are two levels of control: Global default: System → Settings → Show Model Thinking (enabled by default) Per-chat override: Brain icon in the chat input bar Models that do not support thinking fall back silently to a normal response. The FAST category always skips thinking. Multiple Local Providers (v1.1.5) Nexus can now connect to multiple local backends at the same time, including Ollama, llama-swap, llama.cpp, LM Studio, Open WebUI, and other OpenAI-compatible endpoints. Model discovery aggregates across all configured providers. Category assignments now store the provider URL alongside the model name so routing always hits the correct backend. Fallback chains also work across providers. Existing single-provider setups migrate automatically with no manual action required. Provider Compatibility Improvements (v1.1.6) Provider health checks and model discovery now correctly handle endpoints whose base URL ends with /v1, such as llama-swap and LM Studio. Other compatibility improvements: llama-swap display names now appear correctly in the UI the proper routing key is still used in API requests per-attempt chat timeout increased from 60s to 300s timeout remains configurable via CHAT_TIMEOUT_MS model-loading retries increased to 5 attempts with 30-second intervals to better support slow model swaps Web Search Sources (v1.1.4) After a web search completes, Nexus now shows a collapsible Sources section below the response. This includes: title URL snippet for each SearXNG result that was used. UI Improvements (v1.1.7 and v1.1.8) Several quality-of-life improvements landed across the interface: Collapsible settings sections: All Models tab sections now collapse and expand Persistent section state: Collapse state survives page refresh Persistent active tab: The selected tab (Chat, Models, or System) is remembered across refreshes Discovered Models redesign: The old dense card grid was replaced with a provider-grouped collapsible list Better model readability: Models are grouped by source, size pills are color-coded by parameter tier, and the active router model is highlighted Copy code button: Every code block now gets a hover copy button with 2-second success feedback Security Hardening (v1.1.8) A full server-side security audit was performed. Major improvements include: CORS: Origin is now echoed explicitly, and credentials are only allowed when a matching origin is present SSRF protection: Cloud metadata endpoints such as AWS IMDS, GCP metadata, and the Kubernetes API are blocked LAN access preserved: Private LAN IPs remain allowed by design so local providers still work Security headers: Added CSP, X-Frame-Options, X-Content-Type-Options, HSTS, Referrer-Policy, and Permissions-Policy Session cleanup: Expired sessions are swept hourly Session caps: Maximum 10 concurrent sessions per user, with oldest eviction on overflow Password complexity: New passwords now require at least one uppercase letter, one lowercase letter, and one digit Body limits: Global body limit reduced to 1 MB; chat and conversation routes keep 20 MB for vision/image use API key decoupling: Changing the admin login password no longer breaks API clients using x-admin-key Rate limiting: Password-change endpoint is now rate-limited alongside login protections Docker Image Size Reduction (v1.1.9) Production images are now smaller because build-time dependencies are excluded from the runtime image. Image size dropped from about 127 MB to about 86 MB. Bug Fixes Since v1.1.3 Fixed Ollama being misidentified as a generic OpenAI-compatible provider, which prevented reasoning/thinking from being sent Fixed the localThinkingEnabled is not defined scope bug introduced during the thinking-toggle work Fixed mixed content warnings on HTTPS deployments caused by a hardcoded http://localhost:11434 in the frontend bundle Fixed FAST category routing so it no longer grabs prompts that actually need real answers Fixed session state not being fully cleared on logout in some edge cases

This is the support thread for the Nexus Orchestrator. 🔗 GitHub Repo🔗 Docker Hub🔗 Unraid Template What is Nexus Orchestrator? Nexus Orchestrator is a self-hosted orchestration layer that routes each LLM request to the best local or cloud model automatically. This started as something I personally wanted for my own setup. I used AI tools along the way to help design, iterate, and refine parts of it — but the goal and overall system came from solving my own use case. It’s not perfect, but it works. At its core, a lightweight router model classifies each prompt’s intent (CODING, REASONING, CREATIVE, VISION, DOCUMENT, or GENERAL) and dispatches it to whichever model you’ve configured for that category. You can freely mix local Ollama models with cloud providers in any combination. Quick Install (Unraid) Copy the template to your flash drive: /boot/config/plugins/dockerMan/templates-user/nexus-orchestrator.xml Go to your Unraid Docker tab → Add Container Search for Nexus Orchestrator or select the template manually Set your Admin API Key (required) Set your Local Provider URL — e.g. http://YOUR_SERVER_IP:11434 for Ollama. Do not use localhost, it resolves inside the container. Optionally set a cloud provider URL and API key for hybrid routing Set a Router Model — something small works fine: gemma3:4b, qwen2.5:3b, or nemotron-mini:4b 100% Local Setup Set LOCAL_URL to your Ollama instance IP Set ROUTER_MODEL to a small local model In the UI under the Models tab, assign local models to each category Nothing will leave your network. Environment Variables Variable Required Description ADMIN_API_KEY Yes Password for the web UI and API ENCRYPTION_SECRET No Encrypts stored data — derives from Admin key if blank LOCAL_URL No Local provider base URL (default: http://localhost:11434) LOCAL_KEY No API key for local provider if required CLOUD_URL No OpenAI-compatible base URL for cloud provider CLOUD_API_KEY No API key for cloud provider ROUTER_MODEL No Model used for intent classification ROUTER_URL No Custom router URL — defaults to LOCAL_URL if blank ROUTER_KEY No API key for the router if different from local Completed: 4/6/2026 ✅ CORS configuration ✅ Cookie-based auth ✅ SSRF protection ✅ LaTeX/KaTeX rendering ✅ Stop generation button ✅ SQLite migration ✅ Category Mappings cloud filter ✅ Model fallback ✅ Chat input UX improvements ✅ Input validation (Zod schemas) ✅ Rate limiting ✅ Tests (Vitest) ✅ Conversation pagination ✅ Router result caching (opt-in toggle) ✅ FAST category ✅ SECURITY category ✅ Error boundaries ✅ Projects (organize chats into folders) ✅ Multi-user support (per-user accounts, isolated config, conversations & projects) ✅ Request queuing (per-user FIFO queue, up to 5 pending per user) ✅ Web search via tool calling (SearXNG integration, LLM decides when to search) Planned: Multiple local providers (Ollama + llama-swap + llama.cpp simultaneously) URL fetch/browse tool (companion to web search — read a specific page) Ollama backend abort Configuration Guide This guide covers the basic configuration needed to get Nexus Router working with local and optional cloud models. LOCAL MODEL / API PROVIDER This should point to your local LLM backend, usually Ollama. Set the Provider URL to your machine’s IP address Example: http://192.168.1.100:11434 Do not use localhost, as that refers to the container itself Leave the API Key blank for standard Ollama setups Nexus will automatically detect Ollama and handle the connection CLOUD MODEL / API PROVIDER (Optional) This is for OpenAI-compatible providers such as OpenAI or OpenRouter. Set the Provider URL Enter your API key If left unconfigured, any categories set to Cloud will show a warning Local-only setups will still function normally INTENT ROUTER The router determines which category handles each request. A small model is sufficient Recommended: gemma3:4b, qwen2.5:3b Leave the Router URL blank to reuse your local provider Only set a custom URL if you want a separate routing endpoint DISCOVERED MODELS Nexus will list all models available from the Local Provider. If models do not appear: Verify the Provider URL is correct Ensure the status shows Online Models can be selected and assigned to categories from this list CATEGORY MAPPINGS Categories define how requests are routed. Each category includes: A provider (Local or Cloud) A pool of models A fallback order (first model is primary, others are used if it fails) Default categories: GENERAL — general conversation CODING — programming and debugging REASONING — math, logic, and analysis CREATIVE — writing and brainstorming VISION — triggered by image input DOCUMENT — triggered by file input FAST — simple, low-latency responses SECURITY — security research and testing Custom categories can be added from the Models tab View Changelog here for patch notes. https://github.com/FaqFirebase/Nexus-Orchestrator/blob/master/CHANGELOG.md Bugs are expected. GitHub: https://github.com/FaqFirebase/Nexus-Orchestrator Docker Hub: https://hub.docker.com/r/pikkonmg/nexus-orchestrator Template repo: https://github.com/PikkonMG/unraid-docker-templates Screenshots