vtcode 0.136.2

A Rust-based terminal coding agent with modular architecture supporting multiple LLM providers
docs.rs failed to build vtcode-0.136.2
Please check the build logs for more information.
See Builds for ideas on how to fix a failed build, or Metadata for how to configure docs.rs builds.
If you believe this is docs.rs' fault, open an issue.
Visit the last successful build: vtcode-0.21.8

What is VT Code?

VT Code is a Rust coding agent built for long-running autonomous workflows, with OS-native sandboxing, multi-provider LLM support, open protocols, and extensible Skills.

Features

  • Agent runtime - Interactive TUI, slash commands, streaming, ask/exec CLI, session resume
  • Coding tools - Safe file ops, ripgrep search + ast-grep outline symbol maps, fuzzy discovery, code intelligence, project indexing, terminal execution
  • Extensibility - Agent Skills, Model Context Protocol MCP client/server, lifecycle hooks, subagents, custom providers, Agent Client Protocol (ACP).
  • Model providers - 21+ LLM providers: Anthropic, OpenAI, Gemini, OpenRouter, local inference via Ollama, LM Studio, and llama.cpp (managed with the /local command), and more
  • Safety - Restricted shell sandbox, tool guardrails, subprocess isolation, full audit logging
  • Protocols - Open Responses, Agent2Agent (A2A), ATIF, Anthropic Messages API
  • Loop engineering - Worktree isolation for parallel agents, propose/verify sub-agent separation, durable loop state, cost guardrails
  • Planning workflow - Iterate on a build plan with /plan and the plan primary agent, then hand off to build/auto via a structured review gate

Quick start

Install via homebrew

brew install vinhnx/tap/vtcode

One-liner for macOS/Linux (also installs ripgrep + ast-grep)

curl -fsSL https://raw.githubusercontent.com/vinhnx/vtcode/main/scripts/install.sh | bash

Scaffolds vtcode.toml, .vtcode/, and AGENTS.md in your project

vtcode init

Launch VT Code

vtcode

Common commands

vtcode                         # interactive TUI
vtcode init                    # scaffold project config + AGENTS.md
vtcode ask "explain Rc vs Arc" # one-shot question
vtcode exec "refactor main.rs" # headless task with full tool access
vtcode review                  # review uncommitted changes
vtcode update                  # self-update

Documentation

  • Interactive TUI - Primary agents, slash commands (/model, /review, /mcp, /skills, /theme, /compact)
  • Full automation - --full-auto CLI, plan-build-evaluate harness, subagents, scheduled tasks
  • Providers - Setup guides for all 21 providers
  • Configuration - vtcode.toml, tool config, lifecycle hooks
  • Agent Skills - Creating, loading, and sharing skills
  • MCP Integration - Client and server modes
  • Editor guides - Zed ACP, VS Code, Claude Code
  • Safety - Shell sandbox, security hardening, threat model
  • Protocols - Open Responses, ATIF, A2A, Anthropic Messages API
  • Loop engineering - Worktree isolation, propose/verify, loop state, cost guardrails
  • Planning workflow - /plan, review gate, plan handoff to build/auto agents

Providers

VT Code supports 21+ LLM providers out of the box, plus any OpenAI-compatible API via [[custom_providers]].

Category Providers
Cloud LLMs Anthropic · OpenAI · Gemini · Z.AI · Moonshot (Kimi) · StepFun · MiniMax · Mistral · Qwen
Gateways OpenRouter · Evolink · HuggingFace · Atlas Cloud
Local inference Ollama · LM Studio · llama.cpp
Other GitHub Copilot · Anthropic API Compat · Poolside

Read: Provider Guides.

Local models (experimental)

Run models entirely on your machine for privacy, offline use, or zero token cost. VT Code supports three local backends, all managed from the TUI:

  • Ollama (ollama serve) — best-supported local backend; auto-loads pulled models.
  • LM Studio (lms server start) — OpenAI-compatible; select the loaded model in the picker.
  • llama.cpp (llama-server -m model.gguf) — most automated; auto-starts via LLAMACPP_MODEL_PATH.
/local                 # interactive local server manager
/local start ollama   # start a specific backend
/local troubleshoot   # diagnose connection / model issues

Before each generation VT Code verifies the server is up and the model is loaded, and on failure prints the exact recovery command (e.g. ollama pull gpt-oss:20b) instead of a cryptic error. Local inference is experimental and depends on your hardware — see Local Models guide for trade-offs, hardware sizing, and a reliable-setup checklist, and Local Inference Servers for the full /local reference.

Development

git clone https://github.com/vinhnx/vtcode.git
cd vtcode
./scripts/run-debug.sh

Rust stable, edition 2024, MSRV 1.93.0. Workspace of ~30 crates:

Layer Crates
Binary vtcode
Common vtcode-commons, vtcode-exec-events, vtcode-macros, vtcode-utility-tool-specs
Codegen vtcode-core, vtcode-ui, vtcode-config, vtcode-llm, vtcode-skills, vtcode-safety, vtcode-a2a, vtcode-mcp, vtcode-auth, vtcode-acp, vtcode-indexer, vtcode-bash-runner, vtcode-memory, vtcode-eval

Want to use VT Code as a library? See vtcode-battery-pack for a curated set of crates you can add to your own Rust projects.

./scripts/check-dev.sh  # fast quality gate (clippy, fmt, check)
cargo nextest run        # parallel test runner

Contributing

I'd love to have you, bug reports, docs, features, ideas, all welcome. Start with issues or good first issues. AI agents see AGENTS.md. Humans see CONTRIBUTING.md.

Support

VT Code is a labor of love built in my spare time. If it's helped you ship something or learn something, a sponsorship would mean the world.

License

First-party code is licensed under MIT OR Apache-2.0 — choose whichever works best for you. See LICENSE for the full Apache-2.0 text; MIT terms are also granted under the same copyright.

Third-party and inspired-by code remains under its original licenses. See THIRD-PARTY-NOTICES for attributions.