Issue Station
Sign In
Tools hereToolbox

hermes - 💡(How to fix) Fix [Feature]: Easy support for adding OpenCode Go models into Hermes Agent

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
RAW_BUFFERClick to expand / collapse

Problem or Use Case

Currently, integrating new models (such as OpenCode Go models) into Hermes Agent is not straightforward.

As a developer, I want to experiment with different model backends, especially lightweight or self-hosted ones like OpenCode Go, but there is no simple or documented way to plug them into Hermes.

This creates friction for:

testing alternative LLM providers running local or custom inference stacks adapting Hermes to specific performance or cost constraints

Right now, adding a new model requires digging into internal code instead of using a clear extension mechanism.

Proposed Solution

Introduce a simple and extensible way to register custom models (including OpenCode Go) in Hermes Agent.

This could work as:

A configuration-based system (e.g. YAML or JSON) where users can declare a new model: model name endpoint URL (local or remote) API format (OpenAI-compatible or custom adapter) authentication method A standardized adapter interface so Hermes can communicate with different backends: OpenAI-compatible API custom HTTP endpoints (like OpenCode Go) local inference runtimes Optional CLI support: hermes models add hermes models list hermes models test Clear documentation with examples for integrating OpenCode Go as a first-class use case.

The goal is to make adding a new model take minutes instead of requiring internal code changes.

Alternatives Considered

Hardcoding support for OpenCode Go directly in Hermes → Not scalable and does not generalize to other providers Using only OpenAI-compatible APIs → Too limiting, as some backends (including OpenCode Go) may not fully comply Forking Hermes → Breaks maintainability and prevents easy updates

The proposed plugin/config-based approach is more flexible and future-proof.

Feature Type

Configuration option

Scope

Small (single file, < 50 lines)

Contribution

  • I'd like to implement this myself and submit a PR

Debug Report (optional)

extent analysis

TL;DR

Introduce a configuration-based system and a standardized adapter interface to enable easy registration of custom models, such as OpenCode Go, in Hermes Agent.

Guidance

  • Define a clear configuration format (e.g., YAML or JSON) to declare new models, including model name, endpoint URL, API format, and authentication method.
  • Develop a standardized adapter interface for Hermes to communicate with different backends, supporting OpenAI-compatible APIs and custom HTTP endpoints.
  • Consider adding CLI support for managing models, such as hermes models add, hermes models list, and hermes models test.
  • Create documentation with examples for integrating OpenCode Go as a first-class use case to facilitate easy adoption.

Example

# Example configuration file (YAML)
models:
  - name: OpenCode Go
    endpoint: http://localhost:8080
    api_format: custom
    auth_method: api_key

Notes

The proposed solution aims to make adding new models more straightforward, but the implementation details may vary depending on the specific requirements of Hermes Agent and the target models.

Recommendation

Apply a configuration-based workaround by introducing a simple configuration file or interface to register custom models, as this approach is more flexible and future-proof compared to hardcoding support for specific models or forking Hermes.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#cache issue#memory leak#API versioning

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

hermes - 💡(How to fix) Fix [Feature]: Easy support for adding OpenCode Go models into Hermes Agent