Local model discovery
Find Ollama, LM Studio, llama.cpp, and compatible local servers, then save the model setup that works for each workspace.
Current capabilities
One local agent platform, ready in every workspace.
Truss keeps the runtime independent from its interfaces. Its CLI, terminal UI, VS Code extension, and desktop app share the same local-model discovery, tools, permissions, and durable workspace state.
Available today
Four clients. One runtime.
CLI for automation, TUI for terminal-native work, VS Code for editor workflows, and a desktop app for a dedicated local workspace.
CLI and service mode
Run coding tasks from the shell, automate repeatable workspace commands, or provide the JSON-lines service used by editor clients.
Full-screen terminal UI
Stay in a keyboard-first workspace with files, Git diffs, agent chat, shell output, model settings, and approvals close at hand.
VS Code extension
Bring streaming chat, focused file context, inline completions, approvals, agent modes, and Git-aware actions into your editor.
Standalone desktop app
Open a focused workspace for files, diffs, terminal commands, persistent chat, model controls, approvals, and everyday Git work.
Durable agent workflow
Save workspace memory, implementation plans, Git-aware status, task notes, and conversation history—then resume with useful context.
Controlled tool execution
Give the agent the tools it needs while keeping Chat, Plan, Edit, and approval policies explicit.
Streaming and interruption
See responses and tool activity as they happen, stop a run when needed, and recover cleanly when a session is interrupted.
Replaceable foundations
Swap providers, tools, memory, context sources, and clients without rebuilding the runtime around one vendor or editor.
Implementation details