Skip to main content

Agent Terminal

Agent Terminal is a voice-to-agent developer terminal for AI-native coding sessions.

It is built around one simple operating model:

  1. capture intent — typed or via voice through Agent Wispr
  2. enrich with semantic memory from Agent Brain
  3. run the pre-send guard to validate the request
  4. delegate bounded coding tasks to Agent Harness workers

What it is not

It is not a general chat UI, a hosted IDE plugin, or a vague "AI assistant."

The current product path is narrower and more useful:

  • standalone OSS desktop app first
  • reliable daily-driver for solo developers
  • voice + memory + execution in one terminal
  • auditable pre-send guard with no side effects

Product priorities

The current roadmap focuses on two phases:

  • Phases 1–18: core backend (Brain integration, History, Harness launch, pre-send guard, Tauri shell, 5-tab UI, Wispr ingestion)
  • Next: Wispr Settings toggle, deeper Brain recall, improved intent classification

Current best-fit user

The first market is solo developer power users who want voice-driven, memory-enriched, delegated coding sessions from one always-open desktop terminal.