Back to directory

opencode-models-discovery

An OpenCode plugin that discovers available models from any OpenAI-compatible provider automatically and injects them into OpenCode's provider configuration.

opencode-models-discovery

opencode-models-discovery queries a configured provider's model-listing endpoint and adds the discovered models into OpenCode's configuration, rather than requiring each model to be listed by hand. It works with any OpenAI-compatible provider and supports provider-level enablement, endpoint overrides, and both regex-based and exact-match model filtering.

It can enrich discovered models with limits and reasoning metadata from provider-specific endpoints, and supports OpenCode's connect credential flow for custom providers. The package includes a beta adapter for OpenCode v2, which uses a different plugin and provider configuration schema than OpenCode v1, alongside continued support for v1's cache and helper slash commands.

It installs with npm or Bun, is written in TypeScript, and is MIT licensed.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.