Loomix Agent

Local-first AI coding agent for VS Code, powered by Ollama.

Features

Chat in the VS Code side bar (Activity Bar → Loomix Agent → Chat)
Read and search files in your workspace
Propose file edits with confirmation
Run terminal commands with confirmation (optional)
Switch between Plan (no tools) and Build (tools allowed) modes
Quickly pick the Ollama model from the status bar
Use local Ollama or external providers: OpenAI, Anthropic, Gemini, and OpenRouter
Keep editable project memory in LOOMIX.md, CLAUDE.md, AGENTS.md, or .loomix/memory.md
Run built-in slash workflows such as /review, /fix-ci, /write-tests, /commit, and /pr
Inspect plugin/MCP manifests and use Git/CI workflow helpers

ollama pull llama3.1:8b

Start Ollama.
Open the side bar: Activity Bar → Loomix Agent → Chat.
Click the $(robot) model indicator in the status bar to select the main model.

This extension exposes these settings under llamaAgent.*:

llamaAgent.ollamaBaseUrl (default: http://127.0.0.1:11434)
llamaAgent.provider (default: ollama)
llamaAgent.model (default: granite4.1:8b)
llamaAgent.codingModel (default: granite4.1:8b)
llamaAgent.visionModel (default: ibm/granite3.3-vision:2b)
llamaAgent.fallbackProviders (default: [])
llamaAgent.openaiBaseUrl (default: https://api.openai.com/v1; can point to an OpenAI-compatible RAG/gateway endpoint)
llamaAgent.openrouterBaseUrl (default: https://openrouter.ai/api/v1)
llamaAgent.openaiApiKey
llamaAgent.anthropicApiKey
llamaAgent.geminiApiKey
llamaAgent.openrouterApiKey
llamaAgent.allowTerminal (default: true)
llamaAgent.ollamaKeepAlive (default: 5m)
llamaAgent.ollamaOptions (default: {})
llamaAgent.autoApproveEdits (default: false)

File writes require confirmation (unless llamaAgent.autoApproveEdits=true).
Terminal commands require confirmation and can be disabled via llamaAgent.allowTerminal=false.
“Always allow” choices are stored per-workspace in .code-loom/settings.local.json.

npm install
npm run build

Press F5 in VS Code to open the Extension Development Host.