Hermes Agent

Nous Research. Docs checked 2026-10-12. Do not invent a release pin.

William’s daily agent on wtpai1. Tools, optional multi-agent loop, and provider failover above a local OpenAI-compatible server.

What it’s for

Dedicated agent CLI/desktop on top of local Qwen — not a dozen chat bridges.

Local endpoint

llama-server base: http://127.0.0.1:8080/v1
Strata base: http://127.0.0.1:8083/v1
Model name: model.default (must match llama-server --alias / GET /v1/models id)
API key: optional on custom; OPENAI_API_KEY still honored only for provider openai-api

Tool calling

Native agent tools. Docs require at least 64K context or Hermes rejects the model at startup.

Long context

Set llama-server -c ≥ 65536 (our daily driver is 262144 — flags TODO).

ROCm / Radeon gotchas

Attach to a server you already run. Managed local_runtime.backend auto prefers Vulkan on AMD; hip is an explicit choice. Do not take the CUDA managed download on a Radeon.

Hybrid local + cloud

Yes — Nous Portal / cloud providers plus a custom local endpoint; failover is documented.

This is the same question as the calculator’sfully localversushybridtoggle. This page does not quote cloud prices.

Official links

Sources

Copy-paste

More on the connect page. Prove http://127.0.0.1:8080/v1/models first.

Hermes Agent → llama-server :8080hermes config (custom provider)

# Hermes custom / OpenAI-compatible provider.
# Default probe is :8080. For Strata, set this URL or add detect_ports: [8080].
# Re-check field names on the live providers + local-models pages if a key 404s.
model:
  default: qwen   # must match llama-server --alias / GET /v1/models id
providers:
  custom:
    base_url: http://127.0.0.1:8080/v1
    # api_key is optional on custom; OPENAI_API_KEY is only for provider openai-api
# local_runtime.backend: auto | cuda | metal | vulkan | hip | cpu
# auto prefers Vulkan on AMD. Do not take the CUDA managed download on a Radeon.
# Docs require context ≥ 65536 or Hermes rejects the model at startup.

Exact llama-server flags for our daily driver stay TODO in stacks.yaml. This is the port only. 64K context minimum is documented.

Hermes Agent → Strata :8083hermes config (custom provider)

# Hermes custom / OpenAI-compatible provider.
# Default probe is :8080. For Strata, set this URL or add detect_ports: [8083].
# Re-check field names on the live providers + local-models pages if a key 404s.
model:
  default: qwen   # must match llama-server --alias / GET /v1/models id
providers:
  custom:
    base_url: http://127.0.0.1:8083/v1
    # api_key is optional on custom; OPENAI_API_KEY is only for provider openai-api
# local_runtime.backend: auto | cuda | metal | vulkan | hip | cpu
# auto prefers Vulkan on AMD. Do not take the CUDA managed download on a Radeon.
# Docs require context ≥ 65536 or Hermes rejects the model at startup.

Exact Strata flags for our rig stay TODO in stacks.yaml. This is the port only. 64K context minimum is documented.