Set up private and free code search with GrepAI and Ollama. Your code never leaves your machine. There are no API costs or usage limits. This gives you fast, local, and offline embeddings.
You can choose from several Ollama models. Each model offers different size, speed, and quality. For most codebases, nomic-embed-text works great. For multilingual projects, use nomic-embed-text-v2-moe. For maximum accuracy, pick mxbai-embed-large. You can also tune memory and use GPU acceleration.
Getting started is simple. Install Ollama, download a model, and add a configuration file. Then GrepAI uses your local embeddings for lightning-fast code search.
Global
mkdir -p ~/.claude/skills/grepai-embeddings-ollamaProject
mkdir -p .claude/skills/grepai-embeddings-ollamaSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly