Is Agent Terminal open source?

Yes. The current product direction is standalone OSS first, with a Tauri desktop build as the canonical supported path.

What problem does Agent Terminal solve?

It bridges voice input, semantic memory, and AI task delegation into one desktop terminal so you can speak a goal and have it routed to the right tool without leaving your workflow.

Configuration

Agent Terminal is configured via environment variables. No config file is required for the default setup.

Core variables

Variable	Purpose	Default
`BRAIN_API_URL`	Agent Brain MCP server URL	unset (disabled)
`HARNESS_CONTROLLER_URL`	Agent Harness controller URL	unset (disabled)
`HARNESS_TOKEN`	Bearer token for Harness auth	unset
`DATABASE_PATH`	SQLite history database path	`~/.agent-terminal/history.db`

Pre-send guard

The guard is a pure TypeScript function in src/preSendGuard.ts. It runs synchronously before every outgoing message with no side effects and no async calls.

Guard rules are hardcoded. They block:

messages exceeding the configured token budget
requests with no resolved Brain context when Brain is configured
patterns explicitly flagged in the guard rule set

Wispr integration

To enable voice transcript ingestion from Agent Wispr:

Enable the Terminal integration toggle in Agent Wispr Settings
The Wispr app will POST transcripts to POST /api/wispr/ingest on the terminal backend
Transcripts appear in the Transcripts tab for review before sending

◆Guard is immutable at runtime

The pre-send guard cannot be disabled or bypassed at runtime. Modify src/preSendGuard.ts in source and rebuild to change guard behavior.