QodeX — a local-first LLM agent & AI coding CLI agent for your terminal. Runs local models (Qwen3-Coder via Ollama/LM Studio) with deterministic guardrails, 100+ tools, a real browser, smart vision & shareable live artifacts. Open source, Apache-2.0.
https://qodexcli.github.io/QodeX/ ↗// readme
QodeX — the local-first LLM agent & coding CLI agent
QodeX is an open-source LLM agent for your terminal — a local-first, agentic coding CLI. It runs on local models (Qwen3-Coder via Ollama / LM Studio) by default, with Claude / GPT / Gemini / DeepSeek as optional cloud fallbacks. A privacy-first AI coding agent built so a model on your machine does real, multi-step engineering work — fully offline if you want.
If you’re looking for an LLM agent, a CLI agent, an AI coding agent, or an autonomous terminal agent that doesn’t ship your code to someone else’s cloud — that’s QodeX.
Version 2.4.0 · 100+ built-in tools · English & Persian · Apache-2.0
Highlights
- Local-first & private — runs entirely on your models (Qwen-Coder via Ollama / LM Studio); your code never leaves the machine. Claude / GPT / Gemini / DeepSeek are opt-in cloud fallbacks.
- Guardrails around the model, not just prompts — a syntax gate, completion gate, and per-language auto-verification run around the agent loop, so even a weak local model can’t ship broken or unverified code.
- Self-learning skills (safe by design) — QodeX captures the winning…