# VTCode

> VT Code is an open-source Rust terminal coding agent.

- **Website:** https://github.com/vinhnx/VTCode
- **Pricing:** open source
- **Categories:** Developer Tools, Design
- **Tags:** developer-tools, design, ai-agents
- **Platforms:** Web, macOS, Linux, VS Code, CLI
- **Last verified:** 2026-09-10
- **Canonical page:** https://linkrena.com/tools/vtcode

## About

VT Code is an open-source Rust terminal coding agent for interactive and long-running autonomous workflows. It combines a responsive TUI, safe terminal tools, multi-provider LLM support, open protocols, and extensible Skills in one tool, so you can move from a question to a reviewed change without leaving your terminal.

Project status: Active development. Local inference and some automation workflows are experimental, and interfaces and configuration may change between releases.

Harness, not a wrapper : the model reasons; the harness enforces progress with tools, sandbox, evals, and state.

Safety-first : sandboxed shell, command policies, per-workspace approvals, adversarial regression tests.

Built for long runs : durable session memory, spooled tool output, auto-compaction; "done" only when verification passes.

Parallel loop engineering : worktree isolation, propose/verify sub-agents, cost guardrails.

Runs anywhere : 30 providers plus local Ollama, LM Studio, and llama.cpp.

The WebMCP browser bridge is a first-class, opt-in VT Code integration.

## Related tools

- [Mulmoterminal](https://linkrena.com/tools/mulmoterminal): Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you.
- [Termux Dev](https://linkrena.com/tools/termux-dev): ⚡ Ultra-fast terminal AI coding agent & vibe-coding assistant built for Android (Termux), Windows, macOS & Linux.
- [Google Antigravity](https://linkrena.com/tools/google-antigravity): Experience liftoff with the next-gen agent platform
- [Kit](https://linkrena.com/tools/kit): Kit is a coding agent runtime.
- [Coder Eval](https://linkrena.com/tools/coder-eval): Test that your Claude Code skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, activation checks, A/B experiments, CI…
- [Meclaw](https://linkrena.com/tools/meclaw): Where agents build agents.