Query or update Cercano runtime configuration without restarting the server.
npx skills add https://github.com/bryancostanich/Cercano --skill cercano-config
Please help me install this Agent Skill. Skill: cercano_config Source: https://github.com/bryancostanich/Cercano/tree/main/plugins/skills/cercano-config Command: npx skills add https://github.com/bryancostanich/Cercano --skill cercano-config
Cercano's runtime configuration often requires changes to the local model, Ollama endpoint URL, or cloud provider and model. This Skill solves the need to adjust these settings without restarting the Cercano server, reducing downtime and friction during development and deployment.
Run the cercano_config tool to switch the local model to qwen2.5-coder:32b and set the Ollama URL to http://mac-studio.local:11434 in a single operation.
High-intent search queries and answers about installing and using this skill.
You can change the local model without restarting the Cercano server by running the cercano_config tool with the action parameter and specifying the desired local_model field. It validates and applies the update instantly to reduce downtime.
Yes, you can update the Ollama endpoint URL on the fly by passing the ollama_url parameter to the configuration tool. This allows you to point Cercano at a different Ollama instance without requiring a server restart.
The best way to switch cloud providers and models in a running Cercano instance is to use the configuration tool with the cloud_provider and cloud_model parameters. It performs safe updates and validation without interrupting your production environment.
To query the current runtime configuration of Cercano, use the configuration tool with the appropriate action parameter. It retrieves the active local model, Ollama URL, and cloud provider settings currently applied to the server.
Yes, Cercano supports switching from a small local model to a larger one in production environments. The configuration tool applies the local_model change safely while the server is running, eliminating downtime during model upgrades.
MakisuoInstall and configure a local ClickHouse environment with clickhousectl.
yangwhaleInstall, configure, and run vLLM on NVIDIA GPUs with CUDA.
GoogleDevRelExplorationsQuery and update Cercano runtime configuration for local models and endpoints.
joyz0Parse JSON5 config files, substitute environment variables, and validate with Zod schemas.
