LLM-driven orchestration
Break a request into work items, assign agents, manage dependencies, and launch work in parallel from one orchestrator flow.
Mozzie
Mozzie is a local-first desktop app that orchestrates AI coding agents in parallel, helping developers break work into tasks, run agents in isolated worktrees, and review changes in one window.
Overview
Mozzie is a local-first desktop app for orchestrating AI coding agents in parallel. It turns a natural-language request into work items, assigns agents, and manages the resulting branches, dependencies, and review flow in a single window.
The app is built around isolated git worktrees, so each work item can run independently before its changes are reviewed and merged. The repository also describes live output streaming, persistent conversations, and support for multiple workspaces, making it suited to developers who want to coordinate several coding agents on one machine.
Features
Git worktree isolation
Each work item runs in its own git worktree and branch, which keeps agent changes isolated and reduces conflicts.
Review and merge workflow
Review each completed item with diff viewing and execution context, then approve it to push or reject it with feedback.
Dependency graph and auto-launch
Track blocked relationships between work items and auto-launch downstream work when dependencies complete.
Multi-agent support
Use Claude Code, Gemini CLI, Codex CLI, or custom command-line tools and scripts through ACP or direct CLI execution.
Session continuity and workspace management
Keep context across sessions with persistent conversations, multi-workspace support, and a command bar for fast control.
Use cases
Parallel implementation work
Coordinate several coding agents on separate tasks at once, with each task running in its own worktree and moving through review before merge.
Dependency-aware task chains
Break a larger feature into dependent pieces, then let Mozzie block and auto-launch downstream work as prerequisites finish.
Agent-assisted code review
Route changes through a human review step when you want diff inspection, rejection feedback, and a controlled push to origin.
Multi-project agent management
Keep multiple repositories or projects in one interface while preserving per-workspace context and ongoing conversations.
Local-first development workflows
Use local orchestration for agent workflows when you want to avoid cloud dependency and keep execution on your own machine.
Pros and Cons
Pros
- Local-first design keeps repositories, agent execution, and orchestrator data on the user’s machine.
- Supports multiple coding agents, including Claude Code, Gemini CLI, and Codex CLI, with custom CLI/script integration.
- Isolates agent work in git worktrees and adds a review step before merge.
- Tracks dependencies and can auto-launch blocked items when prerequisites finish.
- Includes persistent conversations and multi-workspace support for longer-running work.
Cons
- The repository is archived and read-only, so active development may be limited.
- Pricing for Mozzie itself is not stated in the available sources.
FAQ
Does Mozzie work offline?
Mozzie is designed to run on your machine as a local-first desktop app, and the README says it works fully offline once set up.
Which AI coding agents can it use?
The README says Mozzie works with Claude Code, Gemini CLI, Codex CLI, and custom CLI or script-based agents. Supported transports include ACP over stdio when available, with direct CLI invocation as a fallback.
How do you start using it?
The README says you add API keys for the orchestrator provider in Settings, then add agent configurations and use the command bar or create work items to start a run.
What workflow does Mozzie support?
Mozzie can manage multiple workspaces from one app, and work items move through draft, ready, running, review, done, and archived states.
Is there Mozzie pricing information?
The repository archive and SECURITY.md do not list a product price. The GitHub pricing page only shows GitHub platform plans, so no Mozzie-specific pricing is confirmed in the source.
Quick Facts
- Category
- Developer Tool
- Product type
- Local-first desktop app
- Primary focus
- Parallel AI coding agent orchestration
- Platform
- Desktop via Tauri 2.0
- Source domain
- github.com
- Repository status
- Archived, read-only
Альтернативы Mozzie
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Lasso
Lasso is an ecommerce product data platform for enriching catalog records, processing supplier files, generating product content, and monitoring competitors. It combines a web app with a REST API, SDK, and MCP server for teams and developers.
GitBot
GitBot is a local browser-based workspace for creating reusable coding bots powered by Claude Code, Codex, or OpenCode. It helps developers run those agents across repository folders with persistent threads and configurable permissions.
Grok 4.7
Grok 4.7 is an xAI model for software development and knowledge work, including extended coding tasks and professional analysis. It is available through Grok Build, Cursor, the Grok API, and other developer platforms, with token pricing starting at $2 per million input tokens and $6 per million output tokens.
Botacts
Botacts is a web directory for finding AI bots and agents you can contact by phone, email, SMS, WhatsApp, Telegram, or Signal. It also lets creators suggest bots for manual review before publication.
Tavus
Tavus is an AI video platform for building real-time, face-to-face agents, digital twins, and AI companions. It combines APIs, custom replicas, and multilingual conversational workflows for developers and teams.