Agent Terminal
Agent Terminal is a voice-to-agent developer terminal for AI-native coding sessions.
It is built around one simple operating model:
- capture intent — typed or via voice through Agent Wispr
- enrich with semantic memory from Agent Brain
- run the pre-send guard to validate the request
- 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.