docs(guides): run Hermes locally with Ollama — zero API cost - #5842
Closed
binhnt92 wants to merge 2 commits into
Closed
docs(guides): run Hermes locally with Ollama — zero API cost#5842binhnt92 wants to merge 2 commits into
binhnt92 wants to merge 2 commits into
Conversation
When Slack's connect() acquires a scoped lock on the app token and then fails (bad token, Socket Mode error), the lock is never released. The next gateway start sees "Slack app token already in use" and refuses to connect until the process dies. Same issue in Signal: if the health check fails after acquiring the phone lock, the lock is held permanently. Discord got this fix in PR NousResearch#5302. Slack and Signal were missed. Add lock release to both exception/failure paths. Extract Signal's inline release logic into a reusable _release_phone_lock() helper. Also close the leaked httpx client on Signal health check failure.
Step-by-step guide covering Ollama installation, model selection, Hermes configuration, speed optimization, and optional gateway bot setup — all running on local hardware with zero API cost. Includes hardware requirements, model comparison table with tool-call support status, context window tuning, GPU offloading tips, fallback provider setup, troubleshooting, and cost comparison.
alt-glitch
added
type/docs
This was referenced Jul 29, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds a step-by-step guide for running Hermes Agent entirely on local hardware using Ollama as the model backend. No cloud API keys, no subscriptions, no data leaving the machine.
Tested on a bare-metal server (AMD EPYC, 64GB RAM, CPU-only) with Gemma 4 31B, Gemma 2 9B/27B, Llama 3.2 3B, and Mistral 7B.
What the Guide Covers
Key Findings from Testing
gemma4:31bis the recommended model — it supports tool calling, which is essential for Hermes' agentic workflowgemma2:9b/27bdo NOT support tool calling via Ollama (returns HTTP 400) — they work for chat-only, noted in the guide/v1/chat/completions) works correctly for both chat and tool-call flowsChecklist