Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.tryvoss.dev/llms.txt

Use this file to discover all available pages before exploring further.

The Voss harness is a terminal-native agent loop for bounded, inspectable, resumable repo work. It is not a general chat box. Each turn goes through a small set of explicit systems: 
user task
  -> provider plan
  -> confidence gate
  -> permission gate
  -> tool execution
  -> session record

​
Why it exists

AI coding tools are useful, but many hide important decisions in prompts:
  • What can the agent edit?
  • Which commands can it run?
  • What context did it inspect?
  • Which files did it avoid?
  • Can the session be resumed later?
Voss makes those decisions explicit through commands, modes, tool classification, permission prompts, persistent project context, and resumable sessions.

​
Main commands

voss do

Run one natural-language task and exit.

voss chat

Start an interactive harness REPL.

voss edit

Open a scoped edit session around explicit targets.

voss sessions

List and resume prior harness work.

​
Product shape

Voss v0.1 is harness-led. The Python harness is the current behavior source and the npm CLI vendors that Python implementation. The .voss language remains central as the workflow-control layer for confidence, context budgets, semantic routing, memory, tools, agents, and fallbacks.