[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-208":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":8,"htmlUrl":9,"language":10,"languages":8,"totalLinesOfCode":8,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":8,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":8,"rankLanguage":8,"license":8,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":21,"topics":8,"createdAt":8,"pushedAt":8,"updatedAt":23,"readmeContent":24,"aiSummary":25,"trendingCount":15,"starSnapshotCount":15,"syncStatus":26,"lastSyncTime":27,"discoverSource":28},208,"gentle-ai","Gentleman-Programming\u002Fgentle-ai","Gentleman-Programming",null,"https:\u002F\u002Fgithub.com\u002FGentleman-Programming\u002Fgentle-ai","Go",3848,451,41,146,0,144,374,967,432,29.97,false,"main","2026-06-12 02:00:10","\u003Cdiv align=\"center\">\n\n\u003Cimg width=\"3276\" height=\"1280\" alt=\"Gentle-AI neon rose banner\" src=\"docs\u002Fassets\u002Fbrand\u002Fgentle-ai-banner.png\" \u002F>\n\n\u003Ch1>Gentle-AI\u003C\u002Fh1>\n\n\u003Cp>\u003Cstrong>Gentle-AI — Ecosystem, Frameworks, Workflows for AI coding agents.\u003C\u002Fstrong>\u003C\u002Fp>\n\n\u003Cp>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FGentleman-Programming\u002Fgentle-ai\u002Freleases\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002FGentleman-Programming\u002Fgentle-ai\" alt=\"Release\">\u003C\u002Fa>\n\u003Ca href=\"LICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-blue.svg\" alt=\"License: MIT\">\u003C\u002Fa>\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FGo-1.24+-00ADD8?logo=go&logoColor=white\" alt=\"Go 1.24+\">\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fplatform-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey\" alt=\"Platform\">\n\u003C\u002Fp>\n\n\u003C\u002Fdiv>\n\n---\n\n## What It Does\n\nGentle-AI is NOT an AI agent installer. Most agents are easy to install. It is an **ecosystem configurator** -- it takes whatever AI coding agent(s) you use and supercharges them with persistent memory, Spec-Driven Development workflows, 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.\n\n**Before**: \"I installed Claude Code \u002F OpenCode \u002F Cursor, but it's just a chatbot that writes code.\"\n\n**After**: Your agent now has memory, skills, workflow, MCP tools, and a persona that actually teaches you.\n\n### 12 Supported Agents\n\n| Agent | Delegation Model | Key Feature |\n|-------|:---:|---|\n| **Claude Code** | Full (Task tool) | Sub-agents, output styles |\n| **OpenCode** | Full (multi-mode overlay) | Per-phase model routing |\n| **Kilo Code** | Full (multi-mode overlay) | OpenCode-compatible config in `~\u002F.config\u002Fkilo` |\n| **Gemini CLI** | Full (experimental) | Custom agents in `~\u002F.gemini\u002Fagents\u002F` |\n| **Cursor** | Full (native subagents) | 10 SDD agents in `~\u002F.cursor\u002Fagents\u002F` |\n| **VS Code Copilot** | Full (runSubagent) | Parallel execution |\n| **Codex** | Solo-agent | CLI-native, TOML config |\n| **Windsurf** | Solo-agent | Plan Mode, Code Mode, native workflows |\n| **Antigravity** | Solo-agent + Mission Control | Built-in Browser\u002FTerminal sub-agents |\n| **Kimi Code** | Full (native custom agents) | Modular prompt templates in `~\u002F.kimi` |\n| **Kiro IDE** | Full (native subagents) | Native `~\u002F.kiro\u002Fagents\u002F` + steering orchestration |\n| **Qwen Code** | Full (native sub-agents) | Slash commands, `~\u002F.qwen\u002Fcommands\u002F`, `auto_edit` mode |\n\n> **Note**: This project supersedes [Agent Teams Lite](https:\u002F\u002Fgithub.com\u002FGentleman-Programming\u002Fagent-teams-lite) (now archived). Everything ATL provided is included here with better installation, automatic updates, and persistent memory.\n\n---\n\n## Quick Start\n\n### macOS \u002F Linux\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002FGentleman-Programming\u002Fgentle-ai\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n```\n\n### Windows\n\n```powershell\nscoop bucket add gentleman https:\u002F\u002Fgithub.com\u002FGentleman-Programming\u002Fscoop-bucket\nscoop install gentle-ai\n```\n\nOr via PowerShell script: `irm https:\u002F\u002Fraw.githubusercontent.com\u002FGentleman-Programming\u002Fgentle-ai\u002Fmain\u002Fscripts\u002Finstall.ps1 | iex`\n\n### After install: project-level setup\n\nOnce your agents are configured, open your AI agent in a project and run these two commands to register the project context:\n\n| Command | What it does | When to re-run |\n|---------|-------------|----------------|\n| `\u002Fsdd-init` | Detects stack, testing capabilities, activates Strict TDD Mode if available | When your project adds\u002Fremoves test frameworks, or first time in a new project |\n| `skill-registry` | Scans installed skills and project conventions, builds the registry | After installing\u002Fremoving skills, or first time in a new project |\n\nThese are **not required** for basic usage. The SDD orchestrator runs `\u002Fsdd-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.\n\n---\n\n## Install\n\n### Recommended\n\n```bash\n# macOS \u002F Linux\nbrew tap Gentleman-Programming\u002Fhomebrew-tap\nbrew install gentle-ai\n\n# Windows\nscoop bucket add gentleman https:\u002F\u002Fgithub.com\u002FGentleman-Programming\u002Fscoop-bucket\nscoop install gentle-ai\n```\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Other install methods\u003C\u002Fstrong> (Go install, PowerShell script, binary download)\u003C\u002Fsummary>\n\n#### Go install (any platform with Go 1.24+)\n\n```bash\ngo install github.com\u002Fgentleman-programming\u002Fgentle-ai\u002Fcmd\u002Fgentle-ai@latest\n```\n\n#### Windows (PowerShell script)\n\n```powershell\nirm https:\u002F\u002Fraw.githubusercontent.com\u002FGentleman-Programming\u002Fgentle-ai\u002Fmain\u002Fscripts\u002Finstall.ps1 | iex\n```\n\n**Migrating from PowerShell installer to Scoop?** Remove the old binary first:\n\n```powershell\nRemove-Item \"$env:LOCALAPPDATA\\gentle-ai\" -Recurse -Force\n# Then install via Scoop as shown above\n```\n\n#### From releases\n\nDownload the binary for your platform from [GitHub Releases](https:\u002F\u002Fgithub.com\u002FGentleman-Programming\u002Fgentle-ai\u002Freleases).\n\n\u003C\u002Fdetails>\n\n---\n\n## Backups\n\nEvery 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.\n\nSee [Backup & Rollback Guide](docs\u002Frollback.md) for details.\n\n---\n\n## Key Features You Should Know About\n\n### OpenCode SDD Profiles\n\nAssign different AI models to different SDD phases -- a powerful model for design, a fast one for implementation, a cheap one for exploration. OpenCode uses **`gentle-orchestrator`** as the base SDD conductor, and generated named profiles still appear as `sdd-orchestrator-{name}` entries.\n\n```bash\n# Via CLI\ngentle-ai sync --profile cheap:openrouter\u002Fqwen\u002Fqwen3-30b-a3b:free\ngentle-ai sync --profile-phase cheap:sdd-design:anthropic\u002Fclaude-sonnet-4-20250514\n\n# Or via TUI: gentle-ai → \"OpenCode SDD Profiles\" → Create\n```\n\nAfter creating a profile, open OpenCode and press **Tab** to switch between `gentle-orchestrator` (default) and your custom profiles.\n\n| What you need | Use this |\n|---|---|\n| Default SDD conductor | `gentle-orchestrator` |\n| Legacy configs | `sdd-orchestrator` is migrated to `gentle-orchestrator` on sync |\n| Named model profiles | `sdd-orchestrator-cheap`, `sdd-orchestrator-premium`, etc. |\n\n**Full guide**: [OpenCode SDD Profiles](docs\u002Fopencode-profiles.md)\n\n### Engram (Persistent Memory)\n\nYour AI agent automatically remembers decisions, bugs, and context across sessions. You don't need to do anything -- but when you do:\n\n```bash\nengram projects list          # See all projects with memory counts\nengram projects consolidate   # Fix name drift (\"my-app\" vs \"My-App\")\nengram search \"auth bug\"      # Find a past decision from the terminal\nengram tui                    # Visual memory browser\n```\n\n**Full reference**: [Engram Commands](docs\u002Fengram.md)\n\n---\n\n## Documentation\n\n| Topic | Description |\n|-------|-------------|\n| [Intended Usage](docs\u002Fintended-usage.md) | How Gentle-AI is meant to be used — the mental model |\n| [OpenCode SDD Profiles](docs\u002Fopencode-profiles.md) | Create and manage per-phase model profiles for OpenCode |\n| [Engram Commands](docs\u002Fengram.md) | CLI commands, MCP tools, project management, team sharing |\n| [Codebase Guide](docs\u002FCODEBASE-GUIDE.md) | Maintainer map for repository ownership, architecture boundaries, and review guardrails |\n| [Agents](docs\u002Fagents.md) | Supported agents, feature matrix, config paths, and per-agent notes |\n| [Components, Skills & Presets](docs\u002Fcomponents.md) | All components, GGA behavior, skill catalog, and preset definitions |\n| [Usage](docs\u002Fusage.md) | Persona modes, interactive TUI, CLI flags, and dependency management |\n| [Backup & Rollback](docs\u002Frollback.md) | Backup retention, compression, dedup, pinning, and restore |\n| [Kiro IDE](docs\u002Fkiro.md) | Kiro-specific setup, config paths, native subagents, and SDD behavior |\n| [Platforms](docs\u002Fplatforms.md) | Supported platforms, Windows notes, security verification, config paths |\n| [Architecture & Development](docs\u002Farchitecture.md) | Codebase layout, testing, and relationship to Gentleman.Dots |\n\n---\n\n## Community Highlights\n\nThis project gets better when the community builds on top of it.\n\n### Community Integrations\n\n- [sub-agent-statusline](https:\u002F\u002Fgithub.com\u002FJoaquinvesapa\u002Fsub-agent-statusline) — optional OpenCode TUI plugin that shows sub-agent activity, status, elapsed time, and token\u002Fcontext usage when OpenCode exposes it.\n- [sdd-engram-plugin](https:\u002F\u002Fgithub.com\u002Fj0k3r-dev-rgl\u002Fsdd-engram-plugin) — optional OpenCode TUI plugin to manage SDD profiles and browse Engram memories directly from OpenCode, with runtime profile activation and no restart required.\n\nWhen you select OpenCode in the installer, Gentle-AI asks whether to register each community plugin and offers a browser shortcut to review the repository first. Gentle-AI only ensures `~\u002F.config\u002Fopencode\u002Ftui.json` exists and adds the plugin package names to its `plugin` array; OpenCode installs\u002Floads those packages the next time it starts. Once OpenCode has materialized a plugin under `~\u002F.config\u002Fopencode\u002Fnode_modules\u002F`, `gentle-ai update` can compare its local `package.json` version with the plugin's GitHub releases.\n\n## Contributors\n\nThis project exists because of the community. See [CONTRIBUTORS.md](CONTRIBUTORS.md) for the full list.\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FGentleman-Programming\u002Fgentle-ai\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Fcontrib.rocks\u002Fimage?repo=Gentleman-Programming\u002Fgentle-ai\" \u002F>\n\u003C\u002Fa>\n\n---\n\n## Next Steps\n\n- **Just installed?** Read [Intended Usage](docs\u002Fintended-usage.md) -- the one page that explains the mental model.\n- **Using OpenCode?** Set up [SDD Profiles](docs\u002Fopencode-profiles.md) to assign different models per phase.\n- **Want to share memory across machines?** Learn `engram sync` in the [Engram reference](docs\u002Fengram.md).\n- **Ready to contribute?** Check [CONTRIBUTING.md](CONTRIBUTING.md) and the [open issues](https:\u002F\u002Fgithub.com\u002FGentleman-Programming\u002Fgentle-ai\u002Fissues?q=is%3Aissue+is%3Aopen+label%3A%22status%3Aapproved%22).\n\n---\n\n\u003Cdiv align=\"center\">\n\u003Ca href=\"LICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-blue.svg\" alt=\"License: MIT\">\u003C\u002Fa>\n\u003C\u002Fdiv>\n","Gentle-AI 是一个用于增强AI编码代理的生态系统配置器。它通过提供持久内存、基于规范驱动开发的工作流、精选编码技能、MCP服务器、AI提供商切换器、注重安全的教学型角色以及每个阶段模型分配等功能，显著提升了包括Claude Code、OpenCode和Cursor在内的12种支持代理的能力。项目采用Go语言编写，支持macOS、Linux及Windows平台，适用于希望提升AI编码代理功能性和效率的开发者或团队。通过Gentle-AI，用户可以将简单的代码生成聊天机器人转变为具有记忆能力、专业技能和高效工作流程的智能助手。",2,"2026-06-11 02:31:32","trending"]