Gentleman Programming · Alan Buscaglia and a community of thousands of developers
Open-source tools that turn the AI coding agents you already pay for into disciplined engineers.
Memory, a right-sized workflow, curated skills and evidence-based review for Claude Code, Cursor, OpenCode, Codex, Pi and a dozen more. One binary per machine, no agent lock-in.
macOS
brew install gentleman-programming/tap/gentle-ai
One Homebrew formula.
Linux
brew install gentleman-programming/tap/gentle-ai
The same Homebrew formula as on macOS.
Windows
Windows builds from source with Go, never from an unsigned download. Prerequisites: Node.js 18+ and npm, Git 2.38+, Go 1.25.10+ on Windows, and your AI agent already on your PATH.
The configurator, our own agent, and the memory behind both.
Gentle AI equips the agents you already use, with Engram as their memory. Gentle Shell is our own coding agent on Pi; its installer bundles a pinned Gentle AI and Engram.
gentle-ai · v4.1.1 · MIT · start here
The ecosystem configurator
Equips the agents already on each machine with memory, a workflow, skills, MCP servers, a persona and review guardrails. Never installs an agent for you.
Install on macOS, Linux or Windows
macOS
brew install gentleman-programming/tap/gentle-ai
One Homebrew formula.
Linux
brew install gentleman-programming/tap/gentle-ai
The same Homebrew formula as on macOS.
Windows
Windows builds from source with Go, never from an unsigned download. Prerequisites: Node.js 18+ and npm, Git 2.38+, Go 1.25.10+ on Windows, and your AI agent already on your PATH.
One local Go binary with SQLite and full-text search. Git Sync shares memory across machines; Engram Cloud adds optional, self-hosted, project-scoped replication with a dashboard.
Install on macOS, Linux or Windows
macOS
brew install gentleman-programming/tap/engram
One local Go binary with SQLite and full-text search.
Linux
brew install gentleman-programming/tap/engram
The same Homebrew formula as on macOS.
Windows
Windows steps are in the engram README. Or get it bundled: the Gentle Shell installer for Windows sets up a pinned Gentle AI and Engram.
Explore extensions, themes, skills and prompts for Gentle Shell, alongside community projects built with any tools. Find a resource, visit its repository, or share your own work.
You give the intent; it coordinates, asks only about real decisions and reports honestly. Push, PR and merge stay yours.
Layer 2 · the workflow
ODD
Seven steps from authorize to close. Small work runs inline; large work gets a feature document in your exact words and small commits.
Layer 3 · delegation
Focused agents
A read-only explorer, a writer that never commits and a read-only verifier, used only for a named reason, never by file count.
Layer 4 · the outside view
Native review
It freezes the exact change, rates it by what it touches and asks you first. On by default; only you can turn it off.
Full explainer · the deep dive
Delegation, explained
The whole delegation policy in one sitting: inline by default, the named reasons to hand work off, and verification in proportion to risk.
❯gentle work-with-me# consulting · speaking
When the tools are not enough, bring Alan in.
Alan BuscagliaGentleman Programming
Alan Buscaglia spent 15 years in enterprise architecture before he built these tools, and uses them every day. Teams call when they want developers to adopt AI and it is not working: reluctant devs, everyone prompting their own way, no quality bar.
That is an adoption problem, not a prompting course. The goal is a team that directs the AI, not one that depends on a consultant.
Every install that opts in sends a thin, anonymous usage stream. Instead of keeping it for a private dashboard, the aggregates are published: machines per day, platforms, agents, tokens processed by model and effort, plus the parts we cannot attribute. Downloadable as CSV and JSON.
Snapshot date and figures load with JavaScript; the raw snapshot is at /data/snapshot.jsonSnapshot built loading · aggregated with a privacy floor of ten machines, no code and no identifiers.
—
Machines seen
Distinct installs since the collector started
—
Active on the last complete day
Machines that reported at least one event
—
Tokens in the last 15 minutes
Rolling window, rebuilt every fifteen minutes
—
Tokens processed
Input, output, cache and reasoning across measured runs
The snapshot could not be loaded right now. The dashboard says what it holds and when it was built.
Gentle AI, Gentle Shell, gentle-pi: what is the difference?
Gentle AI configures the coding agents you already use (Claude Code, OpenCode, Cursor, Codex, Pi and more) with memory, the ODD workflow, skills and review guardrails, and it never installs an agent for you. Gentle Shell is a complete workspace built on Pi, with its own Pi runtime, agents and interface (Gentle Changes, Gentle Agents, Gentle Commands and the permission modes); its installer bundles its exact Pi, a pinned Gentle AI and Engram. gentle-pi is not a third product: it is Gentle Shell's npm package and repository name until the migration. In short: Gentle AI improves the agent you already have; Gentle Shell is the full workspace on Pi, with Gentle AI inside.
Does Gentle-AI install AI agents for us?
No. It configures agent runtimes already on the machine. If you select one it cannot detect, it refuses and prints the exact command you would run yourself. It never installs software silently.
Where does our memory live, and who can see it?
Locally, in a SQLite database under ~/.engram that stays authoritative. Git Sync exports chunks you control, and Engram Cloud is optional, self-hosted replication you enrol per project. Gentle-AI does not send your code anywhere.
Will it slow down small tasks with process?
No. Understood, low-risk work runs inline, with no subagents and no task document. In the benchmark a 3-line bug went from 335 s to 77 s and from USD 0.339 to USD 0.105.
How do we roll it out to a team?
Everyone installs the same binary and picks the same preset, so every machine gets the same baseline. Start with a two-week pilot on one team and one measurable question: how much rework, repeated context and review time did it remove?
Show 5 more questions
Which agents does it support?
Full delegation, where focused subagents do the work: Claude Code, OpenCode, Kilo Code, Gemini CLI, Cursor, VS Code Copilot, Kimi Code, Kiro IDE and Qwen Code, plus Pi through Gentle Shell. Solo-agent, everything in one conversation with the same persona, skills, memory and workflow: Codex, Windsurf, Antigravity, OpenClaw and Trae.
Is the evidence-based review step mandatory?
No. It is on by default and you turn it off with gentle-ai review mode disable. A review is only due for high-risk changes, and its outcome is informational: it never blocks a commit or a release.
Why is it so opinionated?
Most agent sessions fail for operational reasons, not model reasons. It ships a working set of opinions (requirements first, tests as evidence, reviewable work units, security defaults) so the team stops re-litigating them; the Custom preset keeps your own persona and settings.
Is it open source, and does it run on Windows?
Yes. gentle-ai, engram, Gentle Shell and Gentleman Guardian Angel are MIT; Gentleman.Dots is Apache-2.0. Gentle-AI is fully tested on Windows and builds from source with Go 1.25.10 or newer; Gentleman.Dots targets Windows through WSL.
How do we update, and what if something breaks?
Run gentle-ai upgrade followed by gentle-ai sync. Every change snapshots your configuration first, keeping the five most recent backups, and gentle-ai doctor is a read-only report you can run any time.
