Automate from the shell
Run chat, model discovery, profiles, and durable workspace commands from scripts or your normal terminal.
CLI documentationLocal-first coding agents
Truss
A modular coding-agent runtime for local models with a CLI, full-screen TUI, VS Code extension, and desktop app built on the same tools, safeguards, and workspace state.
$ truss-harness chat "Review the current diff"
model: qwen3-coder | mode: edit | permissions: ask
assistant I found three changed files. I will inspect the diff first.
tool git diff --stat
ready for local execution
One runtime, four ways to work
Bring the agent to your workflow.
Start in a shell, stay in your terminal, work inside VS Code, or open a dedicated desktop workspace without changing your local model setup or safety controls.
Meet the clientsClient surfaces
Choose the interface, not a different agent.
Stay in the terminal
Use a full-screen workspace with files, editor, Git diff preview, chat, shell output, approvals, and model controls.
TUI documentationWork inside the editor
Get streaming chat, file context, inline completions, agent modes, approvals, and Git commit-message help in VS Code.
VS Code documentationOpen a focused workspace
Use the standalone Electron app for file browsing, diffs, terminal commands, chat, approvals, and a built-in Git workflow.
Built for real work
Everything stays under your control.
Local models are more useful when tools, context, and permissions are designed to work together.
Local by default
Discover and connect Ollama, LM Studio, llama.cpp, or another OpenAI-compatible local endpoint—without a cloud account.
Tools with boundaries
Read, write, search, grep, and terminal tools run through agent modes and an explicit approval policy.
State that carries forward
Conversations, implementation plans, workspace memory, Git-aware status, and deterministic commands keep work moving.