How I would run support for Hermes Agent and the Nous Portal, measured on the live queue, and a working support console built on public data.
About 2,300 new issues a week and 14,187 open. Bots label and prioritise. In a 196-issue sample, 17% got a team reply and 60 of 90 closes came with no comment.
Be the human loop on top of the bots: first responses, evidence that survives, clean escalations, and the paid surfaces (Portal, billing, Business).
A console that reads the queue live, triages any issue in seconds and writes the reply and the escalation, plus a Portal API error doctor.
| Takeaway | Why it matters for support |
|---|---|
| Response coverage is the gap | Labelling is automated. What moves user trust is a person replying within a day, starting with P0 and P1. |
| Evidence expires | Debug-share links are temporary; capture what matters into the issue on first read. |
| API errors should name the cause | A missing key currently reads as a bad model name. Small error-text fixes remove whole ticket classes. |
| Escalate once, completely | One packet with version, repro, surviving evidence and impact count replaces fifty duplicate pings. |
An open-source agent at very large scale, with a paid inference and tools layer growing on top. Each surface brings its own tickets.
| Surface | What is public | Support read |
|---|---|---|
| Hermes Agent | MIT-licensed agent, launched Feb 2026: 250k stars, 53k forks, releases several times a month. CLI, TUI, desktop (macOS, Windows), 10+ messaging gateways, many providers and backends. | Install, update, gateway and desktop issues dominate. |
| Nous Portal | OpenAI-compatible inference at inference-api.nousresearch.com/v1 plus a tool gateway. Plans Free, Plus $20, Super $100, Ultra $200 a month with credits. | Auth, credits, model availability, upstream incidents. |
| Hermes Business and Enterprise | Managed and self-hosted team offerings (SSO, admin, spend), first rollouts under way. | SLA-shaped tickets arrive with the first customers. |
| Community | Discord with 141k members; GitHub issues (Discussions off); docs site with an FAQ. | Public questions, scams, incident chatter. |
| Research | Hermes models, Psyche decentralised training on Solana, Atropos, DisTrO. | Crypto and token questions need a fixed script. |
GitHub API, 30 September 2026. The demo recomputes these live.
| Measure | Value | Read |
|---|---|---|
| Open issues | 14,187 | Plus about 32,900 open PRs. |
| New issues, last 7 days | 2,302 | 2,120 closed in the same week: close to flat. |
| Issues 2 to 7 days old with any comment | 52% | Half of new reports sit silent for days. |
| Open with no comment | 4,571 | The backlog of unanswered reporters. |
| Team reply (sample of 196, 2 to 15 days old) | 17% | 9% within 24 h; median 19 h when it happens. 83 reporters heard only from other users. |
| Closed with no team comment | 60 of 90 | Fixes land; the reporter is not told what changed. |
| Closes by one account | 69% | Triage is concentrated; a support owner spreads it. |
| Opened vs closed, 8 weeks | net +336 to +1,408 a week | Backlog grew in 7 of 8 weeks; 14 to 20 Sep closed 443 more than it opened. |
| needs-repro open | 967 | Where evidence completeness pays off first. |
| Open P0 / P1 | 11 / 48 | The daily must-touch list. |
| Largest open areas | gateway 2,627 · desktop 1,835 · install-update 976 · auth 806 | Where playbooks and docs fixes go first. |
| Leaked secrets in 300 recent issues | 0 | Debug-share redaction works; keep scanning anyway. |
Open agents compete on community trust as much as features. How peers carry their queues.
| Project | Open issues | Model | Support angle |
|---|---|---|---|
| Hermes Agent | 14,187 | Open agent + paid Portal and Business. | Benchmark. Highest volume in the set. |
| OpenClaw | about 9,000 | Largest open agent community (391k stars). | Same scale problem, no paid inference layer. |
| Cline | about 1,500 | IDE-embedded coding agent with an enterprise tier. | Discussions on; narrower surface. |
| OpenHands | about 900 | Coding agent with a hosted cloud. | Smaller backlog, community chat. |
| Goose | about 400 | Foundation-run desktop and CLI agent. | Discussions + Discord; no bundled inference. |
| OpenRouter | n/a | Model router. | Upstream for many Portal-style questions. |
Issue counts from the GitHub API, 30 Sep 2026.
Each creates a steady ticket class; each has a small fix.
| Finding | Evidence | Suggested fix |
|---|---|---|
| Missing key reads as a bad model name | A model from the live /v1/models list, called without an Authorization header, returns 400 "Unknown model" (3 of 3 tested). With a bad key it returns 401. | Return 401 for a missing header. Until then, one FAQ line. |
| Debug reports expire before triage | The bug template requires hermes debug share links, which are temporary by design. In issues filed 20 to 29 Sep, 26 of 43 links were gone; 19 of 28 issues had none left. | Copy the key lines into the issue at first read (the demo flags expired links), or keep pastes until the issue gets a first response. |
| Hermes models missing from the Portal list | No Hermes or Nous model id in the public list of about 430 models; nousresearch/hermes-4-405b answers "retired". | A retirement note with the recommended replacement in the docs and the error text. |
| No public status page | None found for the Portal or the tool gateway. | A status page cuts "is it down?" tickets during upstream incidents. |
Checked 30 September 2026 against the GitHub API, the live Portal API and hermes_cli/debug.py.
| JD duty | How I would do it | Detailed in |
|---|---|---|
| Own requests from first response to resolution | Daily pass: P0/P1 without a reply, then issues 2 to 7 days old. Every thread gets an owner and a next-update time. | §05, demo 1 |
| Investigate, reproduce bugs | Reproduction environments for the top surfaces (Windows, WSL2, macOS desktop, Telegram and Discord gateways, Portal auth). | demo 2 |
| Implement straightforward fixes and workarounds | Small PRs for docs, error text and config defaults; workarounds documented on the tracking issue. | ★ |
| Partner with engineers on larger fixes | One escalation packet per problem, with surviving evidence and an impact count from duplicate search. | §06, demo 2 |
| Build tools and automation | Extend the existing sweeper bots with evidence checks, duplicate suggestions and first-response drafts; humans post. | §07 |
| Establish metrics and goals | Human-response coverage, evidence completeness, needs-repro age, duplicate and reopen rates, Portal ticket mix. | §05 |
| Recurring issues into product, docs and process | Weekly trend note: top clusters, counts, one proposed fix each. | §05 |
| Shape a growing support organisation | Written playbooks, escalation rubric and on-call handoffs that a second hire can pick up in a week. | §08 |
| Metric | Definition | First goal |
|---|---|---|
| Human first response | New issues with a maintainer or support comment within 24 h, bots excluded. | P0/P1: all within 4 working hours. Everything: 80% within 48 h. |
| Evidence completeness | Bug reports with version, OS, repro and a readable debug report. | Capture evidence at first read. |
| needs-repro age | Median age of open needs-repro issues. | Under 14 days. |
| Duplicate rate | New issues closed as duplicate. | Top clusters get a pinned issue or a docs fix. |
| Reopen rate | Closed issues reopened within 14 days. | Below 5%. |
| Portal ticket mix | Auth, billing, model availability, rate limits, upstream. | Weekly note with one fix per category. |
| Level | When | Action |
|---|---|---|
| P0 | Secret exposure, data loss, security, or a core flow down for most users. | Page engineering now; public status update. |
| P1 | Core flow broken for a platform or provider, no workaround. | Same-day engineering owner. |
| P2 | Broken with a workaround. | Document the workaround; schedule the fix. |
| P3/P4 | Minor or cosmetic. | Batch weekly. |
An escalation is complete when it has the exact version, environment, minimal repro, failing output, evidence that will still be there tomorrow, an impact count and what support already tried.
| Workflow | How | Guardrail |
|---|---|---|
| Evidence check | On open: template gaps, version, debug-link liveness, secrets. | Deterministic; comments only what is missing. |
| Duplicate suggestion | Search by exception text and title terms; link candidates. | A person confirms before closing. |
| First-response draft | Model rewrites from the checks' findings only. | Human posts; never asks for secrets. |
| Trend note | Weekly clusters by label and exception. | Counts from the API; prose reviewed. |
Built from the public job posting (2026), the Hermes Agent repository and GitHub API, the live Portal API and model list, the Hermes docs and public press, all read on 30 September 2026. The demo is my own tool and reads public data only. Unsolicited interview homework; happy to walk through any section.
Repo: NousResearch/hermes-agent · issue templates
Debug share: hermes_cli/debug.py
Portal: /v1/models · docs
Docs: FAQ
Company: TechCrunch, Jul 2026 · careers
Independent support homework for the Nous Research Support Engineer role · 2026 · edwardtay.com