Turno — AI skill for Claude Code
Desktop app to schedule and run AI agent routines on your PC: Claude Code (your subscription) or local models via Ollama, with a live chat per run, approval cards and split terminals.
How to install Turno
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open eurafaeldecarvalho/turno and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Turno does
Desktop app to schedule and run AI agent routines on your PC: Claude Code (your subscription) or local models via Ollama, with a live chat per run, approval cards and split terminals. Electron + TypeScript.
Alternatives in AI
- Deepreasoning — A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthr 5.4k ★
- Chat Ollama — ChatOllama is an open source agentic app for running AI agents across local and hosted models 3.5k ★
- Blender AI MCP Addon — AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows 531 ★
README
Turno: scheduled AI agent routines on your own PC
**A Windows and Linux desktop app that runs your AI agents on a schedule, unattended, with Claude Code (your subscription) or a local model through Ollama. Every routine is a folder with a `ROUTINE.md`. You can open any run as a live chat with the agent, approve its tool calls from a card, and keep working next to it in split terminals. Local, free, MIT.**
[](https://github.com/eurafaeldecarvalho/turno/releases/latest) [](https://github.com/eurafaeldecarvalho/turno/releases/latest) [](https://www.electronjs.org) [](https://www.typescriptlang.org) [](./LICENSE)

# ~/rotinas/daily-standup/ROUTINE.md
---
name: Daily standup notes
schedule:
days: [mon, tue, wed, thu, fri]
times: ["09:00"]
profile: claude-max # or qwen-local (Ollama)
model: sonnet
effort: medium
permission_mode: manual # ask me: approval card in the app + phone push
---
Read the project folder and write standup.md with a three-line summary.
Turno does not implement an agent. It schedules and supervises the CLIs you already use: every run is `claude -p` speaking stream-json in both directions. That keeps the full Claude Code feature set (tools, skills, MCP servers, subagents, Claude in Chrome) and lets the same routine run on a local model by swapping the profile.
**Why this one:**
- Runs when you are not looking. Cron schedules with time zones, catch-up after sleep or reboot, timeouts, an idle watchdog, a clean
interruptbefore any kill, and named locks so two routines never fight over
Related Skills
Covo
Open-source alternative to Claude Duet: a self-hosted autonomous AI agent that runs tasks end to end — tools,
Umwelten
CLI tool for evaluating and comparing AI models across Google, Ollama, OpenRouter, LM Studio, LlamaBarn, and G
Zenith
Self-hosted, local-first AI workspace on your own Ollama models — chat, a Claude-Code-class coding agent, deep
Nectra
One chat for every AI model you have. Nectra routes each message to the best-fit model across Claude Code, Cod
Aparte
Private AI chat that runs entirely in your browser: your own keys or on-device models (WebLLM, Ollama), MCP to
Aurao
Your friendly, safe desktop GUI for autonomous AI agents (Claude Code, OpenAI Codex CLI, Google Antigravity) —
Related Agents
Perf Deep Audit
Use this agent when you need a deep performance review of Electron, React, or Vite-related code — especially f
Desktop Uiux Developer
Desktop UI/UX development expert who establishes design philosophy based on PRD and UX specs, and generates de
Senior Desktop Engineer
Senior desktop engineer specializing in cross-platform desktop applications, with deep PySide6 (Qt for Python)