skills.rest
GoogleDevRelExplorations
GoogleDevRelExplorationsOFFICIAL
Explore all skills by this author →
GitHub

cercano-local

Route prompts to local Cercano and Ollama servers for private AI inference.

Updated Mar 20, 2026
Search Tags:#mcp#ollama#code-validation#local-inference#cercano#agentic-generation
One-click install
npx skills add https://github.com/GoogleDevRelExplorations/cercano --skill cercano-local-googledevrelexplorations
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cercano-local
Source: https://github.com/GoogleDevRelExplorations/cercano/tree/main/.agents/skills/cercano-local
Command: npx skills add https://github.com/GoogleDevRelExplorations/cercano --skill cercano-local-googledevrelexplorations

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Run prompts against local AI models via Cercano and Ollama to enable private, fast inference without relying on cloud services.

Core Features & Use Cases

  • Local inference via Cercano and Ollama
  • Agentic code generation with automatic validation
  • MCP-powered chat-style prompts and multi-turn conversations

Quick Start

Run a prompt against a locally running Cercano/Ollama setup to start inference.

Frequently Asked Questions about cercano-local

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run local AI inference for agentic code generation without cloud services?▼

Local AI inference for agentic code generation is achieved by routing prompts to a running Cercano server connected to an Ollama instance, enabling private, fast processing without relying on cloud services. This setup supports iterative refinement and automatic code validation.

What is a Cercano and Ollama MCP workflow for multi-turn chat conversations?▼

A Cercano and Ollama MCP workflow enables local multi-turn chat conversations by processing context and prompts through a local server. It routes queries to local models instead of cloud APIs, ensuring private inference and supporting chat-style prompt interactions.

Do I need a running Cercano server and Ollama instance to perform local inference?▼

Yes, you need a running Cercano server connected to an Ollama instance to perform local inference. This local environment is a prerequisite for routing prompts, handling context, and executing agentic generation loops without external cloud dependencies.

Can I use local inference for automatic code validation in agentic generation loops?▼

Yes, local inference supports agentic code generation with automatic validation. By utilizing a Cercano and Ollama setup, you can execute iterative refinement loops and validate generated code locally within your MCP workflow.

Does local inference with Cercano support context handling for iterative refinement?▼

Local inference with Cercano fully supports context handling for iterative refinement. It processes multi-turn conversations and prompts locally through Ollama, allowing you to iteratively refine agentic code generation outputs within an MCP workflow.

Related Skills

Explore More Software Engineering Skills→
bryancostanichbryancostanich
8

cercano-local

Route prompts to local AI models via Ollama through an MCP interface.

Community
Intermediate
bryancostanichbryancostanich
8

cercano-summarize

Summarize large text, files, logs, or diffs using local Cercano inference.

Community
Intermediate
findinfinitelabsfindinfinitelabs

llm-ollama-integration

Run local Chuukese translation and text generation with Ollama.

Community
Advanced
yo-stevenyo-steven

nemoclaw-user-configure-inference

Configure NemoClaw to route agent inference to local model servers.

Community
Advanced