Submit a project
typesafe-skill-router
By DECRUX9812
Source description: TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.
Repository description
The repository describes its purpose as: TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.
Source evidence
The daily check found an explicit Jev / TypeSafe AI connection in the original README and implementation files at the same commit.
Hermes shows the model a one-line description of every installed skill. With a few hundred of them, the model reads past the one that would have done the job. This plugin sends the request to [TypeSafe](https://typesafe.ai) (model `jev-latest`) first and, when a skill genuinely fits, appends a single line to the **user
Automatically source-checked: public repository, pinned README, and implementation files. Not run, benchmarked or security-audited.
