DGC v0.4.0
A coding-agent CLI for the models you run — local (Ollama, llama.cpp, LM Studio, vLLM) or any OpenAI-compatible cloud.
Install
curl -fsSL https://daguccicode.com/install.sh | bash
dgc setup # pick a provider + model
dgc # start codingHighlights
- Works with Ollama, llama.cpp, LM Studio, vLLM and any OpenAI-compatible cloud (OpenAI, OpenRouter, Groq, DeepSeek, Together, Mistral)
- Four permission modes: default / acceptEdits / plan / auto (full-auto)
- Claude Code-style permission rules, evaluated deny → ask → allow
- Plan mode: read-only research → approve the plan into any mode
- Thinking levels (/think, plus think / think hard / ultrathink keywords)
- Memory (DGC.md) and Skills (SKILL.md)
- Automatic fallback to a text tool-call protocol for local models without native tool calling
- Auto context compaction for long sessions
- New in 0.2.0: web search (DuckDuckGo / Brave / Tavily / SearXNG), session resume (
--continue/--resume), self-update (dgc update), an auto-mode safety warning, and a friendly startup mascot - Pure Python 3.10+, three dependencies, MIT licensed
Site: https://daguccicode.com