What problem does Agent Terminal solve?

AI voice-to-agent developer terminal

Speak a goal. Route it to memory and execution. Stay in flow.

Capture voice, classify intent, enrich with semantic memory, and launch bounded coding tasks — all from a single desktop terminal built for AI-native development.

Desktop app optimized for solo developers using voice + local AI in daily coding sessions.

Start Here Read the Docs View GitHub

Pair the terminal with Agent Wispr, Agent Brain, and Agent Harness when you want the complete connected loop.

agent-terminal://sessioncomposer tab

# 1. clone and start the current app
git clone https://github.com/joshl26/agent-terminal.git
cd agent-terminal
npm install
npm run tauri:dev

# 2. open Composer and draft a goal
# the local guard reviews it before dispatch

# 3. optionally configure Brain and Harness
# BRAIN_BASE_URL / HARNESS_BASE_URL

# 4. inspect context, history, and run status

UI tabs: Composer, Runs, History, Transcripts, Context

v0.3.3

current source version

Tauri

Tauri desktop shell; availability follows live release links

Local-first

local-first, scales to team operation

See it in action

Watch a real session, not a script.

Agent Terminal overview

See voice capture, project memory, and bounded task delegation working together in one session.

What it does

Voice, memory, and execution in one terminal — not three tools.

Agent Terminal is a real, shipping desktop application — not a demo. It captures voice through Agent Wispr, can enrich requests with Agent Brain when configured, validates each outgoing request with a pre-send guard, and delegates bounded coding tasks to Agent Harness when that service is configured.

Voice transcript ingestion

Capture speech via Agent Wispr, classify intent, and route transcripts directly into the terminal session without breaking flow.

Semantic memory integration

When Agent Brain is configured, recall relevant project context — facts, decisions, and prior work inform the guard and session context.

Harness task launch

Compose a goal in the terminal, run the pre-send guard, and delegate bounded coding tasks directly to Agent Harness workers.

Persistent session history

Every session and turn is persisted to a local SQLite database. Browse and replay past sessions from the History tab.

Native Tauri desktop shell

Runs as a first-class Tauri desktop application. Platform artifacts are published through the live download manifest — not a browser tab.

Pre-send guard

A pure, side-effect-free guard evaluates every outgoing message before dispatch — blocking risky or malformed requests before they leave.

Single sign-on across the suite

Log in once and stay authenticated across Brain, Terminal, and Harness. Tokens are stored in the OS credential store — no re-login when switching apps.

How it works

Start with a goal. Add memory and execution only where it helps.

Speak or type a goal

Use Agent Wispr to capture voice transcripts, or type directly in the Composer tab. The terminal classifies intent and prepares context.

Enrich with memory

When configured, Agent Brain supplies relevant project facts, prior decisions, and session history before a task is launched.

Run the pre-send guard

Every outgoing message passes through a pure guard function that validates scope, detects risky patterns, and blocks malformed requests.

Launch to Harness, review in Runs

Bounded coding tasks are dispatched to Agent Harness workers. Live run status appears in the Runs tab with full attempt history.

Tauri desktop shell

Voice ingestion via Agent Wispr

Semantic memory via Agent Brain

Pre-send guard (pure, no side effects)

Harness task launcher

SQLite session history

First-run shape

Start with `npm run tauri:dev`, open the Composer tab, and type a goal. Brain enrichment and Harness delegation are optional configured integrations; add Wispr voice input when you want hands-free operation.

Positioning