Isolated By Default
Each session runs in its own worktree and branch, so experiments stay contained.
// terminal-first agent workflows
Ship AI-assisted changes with control.
An Agentic Development Environment (ADE) for running coding agents and reviewing changes from your terminal.
// installation
npm (recommended), Bun, and pnpm global installs support automatic updates when Agentty can identify the original package manager. These packages require Node.js on your PATH.
$
npm install -g agenttyBuilt with Agentty itself, using the same workflow it provides.
// designed for control
A focused environment for agent-driven work.
Built For Flow
Review diffs, switch models, and iterate without leaving the TUI.
Publish And Review
Open PRs or MRs, track status, and auto-resolve threads after agents fix them.
Stacked Sessions
Chain dependent sessions; Agentty automatically rebases review-ready children.
Automatic Commits
Each changed turn refreshes one AI-written commit and updates its published branch.
Agent-Assisted Rebases
On conflicts, the session agent resolves files and Agentty continues the rebase.
Session management
Track sessions across models with color-coded statuses. Active, queued, and archived work at a glance.
// roadmap
Agentty today. The road ahead.
Where Agentty is today, and the product paths growing from it.
Agentty Orchestrator v0
The first version of Agentty as an orchestrator: a terminal-first environment for running coding agents in isolated workspaces and steering changes from prompt to review.
Agentty Harness
Provide a lightweight integration point for LLMs, tools, context, and model providers without requiring the full Agentty interface.
Agentty Orchestrator v1
Coordinate specialized agents as one system: split work, run tasks in parallel, manage dependencies, and keep handoffs visible.
Code Review for Open Source
Review pull requests across open-source GitHub projects, surface actionable findings, and help maintainers assess changes at scale.
Agentty Assistant
Explore a user-controlled assistant that carries context across tasks, invokes tools, and helps across projects.
Agentty Cloud
Run durable agent sessions as a managed service with remote execution, shared environments, and team visibility across devices.
Strategic directions, not release commitments.