ling/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-02 00:41:43 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add Vercel AI Gateway as a first-class provider

Browse Source 
Adds AI Gateway (ai-gateway.vercel.sh) as a new inference provider
with AI_GATEWAY_API_KEY authentication, live model discovery, and
reasoning support via extra_body.reasoning.

Based on PR #1492 by jerilynzheng.
This commit is contained in:
jerilynzheng
2026-03-16 23:46:59 -07:00
committed by teknium1
parent e3f9894caf
commit 20f84ae176
10 changed files with 132 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
website/docs/developer-guide/provider-runtime.md
View File

@@ -37,6 +37,7 @@ That ordering matters because Hermes treats the saved model/provider choice as t
Current provider families include:
- AI Gateway (Vercel)
- OpenRouter
- Nous Portal
- OpenAI Codex
@@ -68,11 +69,21 @@ This resolver is the main reason Hermes can share auth/runtime logic between:
- ACP editor sessions
- auxiliary model tasks
## OpenRouter vs custom OpenAI-compatible base URLs
## AI Gateway
Hermes contains logic to avoid leaking the wrong API key to a custom endpoint when both `OPENROUTER_API_KEY` and `OPENAI_API_KEY` exist.
Set `AI_GATEWAY_API_KEY` in `~/.hermes/.env` and run with `--provider ai-gateway`. Hermes fetches available models from the gateway's `/models` endpoint, filtering to language models with tool-use support.
It also distinguishes between:
## OpenRouter, AI Gateway, and custom OpenAI-compatible base URLs
Hermes contains logic to avoid leaking the wrong API key to a custom endpoint when multiple provider keys exist (e.g. `OPENROUTER_API_KEY`, `AI_GATEWAY_API_KEY`, and `OPENAI_API_KEY`).
Each provider's API key is scoped to its own base URL:
- `OPENROUTER_API_KEY` is only sent to `openrouter.ai` endpoints
- `AI_GATEWAY_API_KEY` is only sent to `ai-gateway.vercel.sh` endpoints
- `OPENAI_API_KEY` is used for custom endpoints and as a fallback
Hermes also distinguishes between:
- a real custom endpoint selected by the user
- the OpenRouter fallback path used when no custom endpoint is configured
@@ -80,7 +91,7 @@ It also distinguishes between:
That distinction is especially important for:
- local model servers
- non-OpenRouter OpenAI-compatible APIs
- non-OpenRouter/non-AI Gateway OpenAI-compatible APIs
- switching providers without re-running setup
- config-saved custom endpoints that should keep working even when `OPENAI_BASE_URL` is not exported in the current shell