This is NOT an AI agent installer. Most agents are easy to install. This is an ecosystem configurator -- it takes whatever AI coding agent(s) you use and supercharges them with the Gentleman stack: persistent memory, Spec-Driven Development workflow, curated coding skills, MCP servers, an AI provider switcher, a teaching-oriented persona with security-first permissions, and per-phase model assignment so each SDD step can run on a different model.
Before: "I installed Claude Code / OpenCode / Cursor, but it's just a chatbot that writes code."
After: Your agent now has memory, skills, workflow, MCP tools, and a persona that actually teaches you.
| Agent | Delegation Model | Key Feature |
|---|---|---|
| Claude Code | Full (Task tool) | Sub-agents, output styles |
| OpenCode | Full (multi-mode overlay) | Per-phase model routing |
| Gemini CLI | Full (experimental) | Custom agents in ~/.gemini/agents/ |
| Cursor | Full (native subagents) | 9 SDD agents in ~/.cursor/agents/ |
| VS Code Copilot | Full (runSubagent) | Parallel execution |
| Codex | Solo-agent | CLI-native, TOML config |
| Windsurf | Solo-agent | Plan Mode, Code Mode, native workflows |
| Antigravity | Solo-agent + Mission Control | Built-in Browser/Terminal sub-agents |
| Kiro IDE | Full (native subagents) | Native ~/.kiro/agents/ + steering orchestration |
| Qwen Code | Full (native sub-agents) | Slash commands, ~/.qwen/commands/, auto_edit mode |
Note: This project supersedes Agent Teams Lite (now archived). Everything ATL provided is included here with better installation, automatic updates, and persistent memory.
curl -fsSL https://raw.githubusercontent.com/Gentleman-Programming/gentle-ai/main/scripts/install.sh | bashscoop bucket add gentleman https://github.com/Gentleman-Programming/scoop-bucket
scoop install gentle-aiOr via PowerShell script: irm https://raw.githubusercontent.com/Gentleman-Programming/gentle-ai/main/scripts/install.ps1 | iex
Once your agents are configured, open your AI agent in a project and run these two commands to register the project context:
| Command | What it does | When to re-run |
|---|---|---|
/sdd-init |
Detects stack, testing capabilities, activates Strict TDD Mode if available | When your project adds/removes test frameworks, or first time in a new project |
skill-registry |
Scans installed skills and project conventions, builds the registry | After installing/removing skills, or first time in a new project |
These are not required for basic usage. The SDD orchestrator runs /sdd-init automatically if it detects no context. But if something changed in your project (new test runner, new dependencies), re-running them manually ensures the agents have up-to-date context.
# macOS / Linux
brew tap Gentleman-Programming/homebrew-tap
brew install gentle-ai
# Windows
scoop bucket add gentleman https://github.com/Gentleman-Programming/scoop-bucket
scoop install gentle-aiOther install methods (Go install, PowerShell script, binary download)
go install github.com/gentleman-programming/gentle-ai/cmd/gentle-ai@latestirm https://raw.githubusercontent.com/Gentleman-Programming/gentle-ai/main/scripts/install.ps1 | iexMigrating from PowerShell installer to Scoop? Remove the old binary first:
Remove-Item "$env:LOCALAPPDATA\gentle-ai" -Recurse -Force
# Then install via Scoop as shown aboveDownload the binary for your platform from GitHub Releases.
Every install, sync, and upgrade automatically snapshots your config files. Backups are compressed (tar.gz), deduplicated (identical configs are not re-backed up), and auto-pruned (keeps the 5 most recent). Pin important backups via the TUI (p key) to protect them from pruning.
See Backup & Rollback Guide for details.
Assign different AI models to different SDD phases -- a powerful model for design, a fast one for implementation, a cheap one for exploration. Create multiple profiles and switch between them with Tab in OpenCode.
# Via CLI
gentle-ai sync --profile cheap:openrouter/qwen/qwen3-30b-a3b:free
gentle-ai sync --profile-phase cheap:sdd-design:anthropic/claude-sonnet-4-20250514
# Or via TUI: gentle-ai → "OpenCode SDD Profiles" → CreateAfter creating a profile, open OpenCode and press Tab to switch between sdd-orchestrator (default) and your custom profiles.
Full guide: OpenCode SDD Profiles
Your AI agent automatically remembers decisions, bugs, and context across sessions. You don't need to do anything -- but when you do:
engram projects list # See all projects with memory counts
engram projects consolidate # Fix name drift ("my-app" vs "My-App")
engram search "auth bug" # Find a past decision from the terminal
engram tui # Visual memory browserFull reference: Engram Commands
| Topic | Description |
|---|---|
| Intended Usage | How gentle-ai is meant to be used — the mental model |
| OpenCode SDD Profiles | Create and manage per-phase model profiles for OpenCode |
| Engram Commands | CLI commands, MCP tools, project management, team sharing |
| Agents | Supported agents, feature matrix, config paths, and per-agent notes |
| Components, Skills & Presets | All components, GGA behavior, skill catalog, and preset definitions |
| Usage | Persona modes, interactive TUI, CLI flags, and dependency management |
| Backup & Rollback | Backup retention, compression, dedup, pinning, and restore |
| Kiro IDE | Kiro-specific setup, config paths, native subagents, and SDD behavior |
| Platforms | Supported platforms, Windows notes, security verification, config paths |
| Architecture & Development | Codebase layout, testing, and relationship to Gentleman.Dots |
This project gets better when the community builds on top of it.
- sdd-engram-plugin — manage OpenCode SDD profiles and browse Engram memories directly from OpenCode, with runtime profile activation and no restart required.
Using a tool like this? Gentle AI now supports a safer OpenCode sync compatibility path for external single-active profile managers.
This project exists because of the community. See CONTRIBUTORS.md for the full list.
- Just installed? Read Intended Usage -- the one page that explains the mental model.
- Using OpenCode? Set up SDD Profiles to assign different models per phase.
- Want to share memory across machines? Learn
engram syncin the Engram reference. - Ready to contribute? Check CONTRIBUTING.md and the open issues.
