Run Hermes on any model

Nous Research's agent framework - register Antseed as a custom provider in config.yaml.

Autonomous agentsOpenAI Chat Completions~3 min

What Hermes is. Hermes Agent is the open-source agent framework from Nous Research. It is designed for autonomous, multi-step workflows and reads provider configuration from ~/.hermes/config.yaml.

How Antseed plugs in. Current Hermes releases store named custom endpoints under the providers: mapping; custom_providers: is legacy and auto-migrated. Use the local AI VPN URL when Hermes runs beside it, or copy the authenticated URL and API key from AI VPN → Agents → Define your internet-accessible Antseed endpoint for a remote Hermes host.

One Hermes-specific gotcha. Some peers serve GPT-style models via the openai-responses protocol, which requires streaming. Hermes' auxiliary calls (title generation, context compression) are non-streaming and will fail against those models with HTTP 400: Stream must be set to true. Pin auxiliary slots to a chat_completions model (config example below).

Run Antseed first

Every integration assumes a buyer proxy at http://localhost:8377. One-time setup, ~2 minutes.

Step 1

Install Hermes

Install or build Hermes
# Follow Nous Research setup at https://github.com/NousResearch/hermes-agent
Hermes is typically run as a long-lived process (often under systemd on a server). The config file ~/.hermes/config.yaml is read at startup - changes require a restart.

Step 2

Point Hermes at Antseed

ANTSEED_BASE_URL	http://127.0.0.1:8377/v1
ANTSEED_API_KEY	antseed-p2p

Show as shell exports

export ANTSEED_BASE_URL="http://127.0.0.1:8377/v1" export ANTSEED_API_KEY="antseed-p2p"

Local setup: keep these defaults. Remote setup: start ngrok or Cloudflare from AI VPN → Agents and replace both values with the displayed public URL and generated antseed_... key.

~/.hermes/config.yaml (merge into your existing config)

model: default: antseed provider: antseed base_url: "" api_mode: chat_completions providers: antseed: name: Antseed api: ${ANTSEED_BASE_URL} api_key: ${ANTSEED_API_KEY} transport: chat_completions extra_headers: originator: hermes default_model: antseed models: antseed: context_length: 200000 deepseek-v4-flash: context_length: 128000 kimi-k2.6: context_length: 256000 minimax-m2.7: context_length: 200000 # Pin auxiliary calls to a chat_completions model so non-streaming # requests (title generation, compression) don't break against # openai-responses peers. auxiliary: title_generation: provider: antseed model: minimax-m2.7 compression: provider: antseed model: minimax-m2.7

Step 3

Pick a model

deepseek-v4-flashkimi-k2.6minimax-m2.7gpt-oss-120b

The special antseed id follows the current AI VPN model picker. Current Hermes expects providers.<name>.models as a mapping, though it still migrates older lists. A local connection accepts any non-empty placeholder api_key; a public endpoint requires the generated antseed_... key from AI VPN → Agents.

The full list is every model on the network. Run curl -s localhost:8377/v1/models, antseed network browse, or open the live network page to see what's available right now.

Verify

Test it

Confirm the proxy advertises the same ids your config references
curl -s "$ANTSEED_BASE_URL/models" -H "Authorization: Bearer $ANTSEED_API_KEY" | jq '.data[].id'
Example response
"deepseek-v4-flash" "glm-5" "gpt-oss-120b" "kimi-k2.6" "minimax-m2.7"
Restart Hermes to pick up the new provider
sudo systemctl restart hermes
Or whatever supervisor you use. Then check the journal: sudo journalctl -u hermes --no-pager -n 30.
After the first request, confirm a channel opened and is being metered
antseed buyer status antseed buyer metering
status shows Active channels: 1 once the first request settles (~5–15s on Base - one on-chain tx to open the channel). metering shows the per-peer token + USDC totals for each channel. To poll: watch -n 1 antseed buyer metering.

How Hermes talks to Antseed

Wire format sent by Hermes: OpenAI Chat Completions (hits /v1/chat/completions on the buyer proxy)
Best-fit services: any service whose protocols array contains openai-chat-completions. That's what the peer advertises as natively-supported - zero translation overhead, no transform edge cases.
How to check a peer: run antseed network peer <peerId> --json and look at providerServiceApiProtocols[provider].services[service]. The browse command exposes the same field per peer.
What happens when protocols don't match: Antseed's @antseed/api-adapter translates between OpenAI Chat Completions and the service's native protocol on the fly. So a request from Hermes can still reach a service that only advertises anthropic-messages - just with a small transform step.
One known caveat: services whose only advertised protocol is openai-responses require streaming. If Hermes sends a non-streaming request and the proxy routes it to one of those services, the call fails with HTTP 400: Stream must be set to true. Pick a service whose protocols includes openai-chat-completions (or another non-responses protocol) to avoid this.

If it goes wrong

Troubleshooting

HTTP 400: Stream must be set to true from auxiliary callsYou're routing through a peer that serves the model via openai-responses (which requires streaming), but Hermes' auxiliaries are non-streaming. Pin the auxiliary.* slots to a chat_completions model (see the config block above). Confirm a model's protocol with antseed network peer <peerId> - look for protocols: openai-chat-completions vs openai-responses.
Hermes loads the provider but every call returns no_peer_pinnedThis error only occurs on buyer proxies older than this release, or when a request carries no model at all. Upgrade the CLI (npm install -g @antseed/cli) and make sure model.default is set - a request that names a model auto-selects a peer. Pin a peer (antseed buyer connection set --peer <peerId> or x-antseed-pin-peer per request) only to force a specific seller.
Hermes runs on a remote host and can't reach 127.0.0.1:8377Open AI VPN → Agents, expand “Define your internet-accessible Antseed endpoint,” and start ngrok or Cloudflare. Put the displayed /v1 URL in ANTSEED_BASE_URL and the generated key in ANTSEED_API_KEY; Hermes sends api_key as a bearer token. Do not expose port 8377 directly.
Want to swap the routed model without restarting AntseedEdit model.default (and models: if needed) in config.yaml, then sudo systemctl restart hermes. The proxy auto-selects a peer serving the new model; the buyer proxy stays up; no contract calls.

Reference

Links

Hermes Agent (Nous Research)Hermes AI-provider docs Antseed skill: hermes-antseed (full walkthrough including systemd, remote hosts, funding)Antseed Agents guide Antseed Public HTTPS Tunnels guide

Same category

OpenClaw All integrations