Automate from your shell
Run coding tasks, use your saved provider profiles, and reuse workspace context from scripts or your normal terminal.
Explore CLIYour models. Your workflow.
One coding agent. No forced workflow.
Plan, edit, and review code with the providers you choose, from local model servers to BYOK cloud accounts, across your shell, terminal, VS Code, and desktop.
$ 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 relearning the agent or rebuilding your model and safety setup.
Meet the clientsClient surfaces
Choose the interface, not a different agent.
One agent across your shell, terminal, editor, and desktop workspace.
Keep your flow in the terminal
Use a full-screen workspace with files, editor, Git diff preview, chat, shell output, approvals, and model controls.
Explore TUIWork where you edit
Get streaming chat, file context, inline completions, agent modes, approvals, and Git commit-message help in VS Code.
Explore VS CodeOpen a dedicated workspace
Use the standalone Electron app for file browsing, diffs, terminal commands, chat, approvals, and a built-in Git workflow.
Explore desktopBuilt for real work
Useful agent work. Clear control.
Choose the model for the job, give the agent useful workspace context, and review what it can do before it acts.
Choose your model
Connect local servers such as Ollama, LM Studio, and llama.cpp, or use a supported cloud provider with your own account.
Keep provider control
Save provider profiles that fit each workspace. Truss does not require one hosted account, a proxy model request, or a one-size-fits-all setup.
State that carries forward
Conversations, implementation plans, workspace memory, Git-aware status, and deterministic commands keep work moving.
Context with intent
Open files, recent edits, Git changes, plans, and workspace memory give the agent useful context without sending the whole repository.
Approvals stay visible
Choose the permission policy that fits the task, then review requested reads, writes, terminal commands, and network work before it runs.
Built to be replaced
Providers, tools, context sources, memory, and clients are separate interfaces, so new capabilities do not rewrite the agent runtime.