Local-first coding agent
DGC lives in your terminal, pointed at your own local model — it reads, edits, runs and verifies your code, with permission modes you control.
curl -fsSL https://vibedgc.com/install.sh | bashMIT · Pure Python · 15+ providers · CLI + VS Code
Why DGC
Tools, four permission modes, plan mode, memory, web search — everything a serious coding agent needs, running against whatever model you point it at.
Ollama, llama.cpp, LM Studio, vLLM — or any OpenAI-compatible cloud endpoint. Code stays local unless you pick a cloud model.
Streams every tool call, diff and result. Permission modes decide how much rope it gets — ask, auto-edit, plan-first, or full-auto.
A pure-Python CLI, and a native VS Code & Cursor extension — same agent, same local models, a docked panel with inline diffs.
Spawn sub-agents with task — each can run a different model or host. Plus background shells, MCP servers, checkpoints & rewind, and lifecycle hooks.
The toolbox
Also in the box: vision / image input, model fallback, custom slash-commands, bundled default skills, and MCP servers.
Connect anything
dgc setup walks you through these with arrow-key menus — local endpoints need no key; cloud ones prompt and store it safely.
● local — no API key, runs on your machine
You decide the rope
Switch live with /mode. Fine-grained allow / ask / deny rules layer on top, evaluated deny → ask → allow.
| Mode | Behavior |
|---|---|
default | reads & known-safe commands auto-run; writes and other commands ask first |
acceptEdits | file edits auto-approved; shell commands still ask |
plan | read-only — research and propose a plan you approve |
auto | full-auto — everything approved; deny-rules still apply |