feat: add ZCode memory integration

CHANGELOG.md

@@ -7,6 +7,21 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 
 ## [Unreleased]
 
+### Added
+
+- `mnemon setup --target zcode` now installs a ZCode-compatible Mnemon skill.
+  With `--global`, setup also registers user-level `SessionStart`,
+  `UserPromptSubmit`, and `Stop` process hooks in
+  `~/.zcode/cli/config.json`; project-local setup intentionally skips hooks
+  because ZCode does not execute project-level hook configuration.
+- `mnemon setup --eject --target zcode` removes Mnemon-owned ZCode files and
+  hook entries while preserving unrelated skills, hook events, and settings.
+
+### Tests
+
+- Added ZCode coverage for embedded artifacts, hook registration, unrelated
+  configuration preservation, and scoped eject cleanup.
+
 ## [0.1.15] - 2026-06-18
 
 ### Added

README.md

@@ -127,6 +127,18 @@ One command deploys the mnemon skill, prompt files, and Cursor lifecycle hooks
 to `.cursor/`. The integration primes new agent sessions with Mnemon guidance
 and memory status, then nudges for durable-memory writeback after responses.
 
+### [ZCode](https://zcode.z.ai/)
+
+```bash
+mnemon setup --target zcode --global --yes
+```
+
+ZCode installs the Mnemon skill under `~/.zcode/skills/` and registers
+user-level lifecycle hooks in `~/.zcode/cli/config.json`. The hooks prime new
+sessions, add recall guidance before model calls, and prompt for durable-memory
+writeback at stop. Without `--global`, setup installs only the project skill;
+ZCode currently ignores project-level hook configuration.
+
 ### [TRAE](https://www.trae.ai/) (TRAE Work)
 
 ```bash
@@ -319,7 +331,7 @@ memory is useful.
 
 - **Zero user-side operation** — install once; supported runtimes can use hooks, minimal runtimes can use persistent rules
 - **LLM-supervised** — the host LLM decides what to remember, update, and forget; no embedded LLM, no API keys
-- **Multi-framework support** — Claude Code, Codex, Cursor, TRAE/TRAE Work, Qoder/QoderWork, CodeBuddy, WorkBuddy, Kimi Code, OpenCode, and Hermes Agent (hooks/plugins), OpenClaw (plugins), Pi (extensions), Nanobot (skills), DeepSeek Harness (via the dsh-mnemon plugin), and more
+- **Multi-framework support** — Claude Code, Codex, Cursor, ZCode, TRAE/TRAE Work, Qoder/QoderWork, CodeBuddy, WorkBuddy, Kimi Code, OpenCode, and Hermes Agent (hooks/plugins), OpenClaw (plugins), Pi (extensions), Nanobot (skills), DeepSeek Harness (via the dsh-mnemon plugin), and more
 - **Runtime-native integration** — runtime-specific `SKILL.md`, shared `guide.md`, and supported hooks or extensions
 - **Four-graph architecture** — temporal, entity, causal, and semantic edges, not just vector similarity
 - **Intent-native protocol** — three primitives (`remember`, `link`, `recall`) map to the LLM's cognitive vocabulary, not database syntax; structured JSON output with signal transparency
@@ -370,7 +382,7 @@ All your local agentic AIs — across sessions and frameworks — sharing one po
 ```
 
 The foundation is in place: a single `~/.mnemon` database that any agent can
-read and write. Claude Code, Codex, Cursor, TRAE/TRAE Work, Qoder/QoderWork,
+read and write. Claude Code, Codex, Cursor, ZCode, TRAE/TRAE Work, Qoder/QoderWork,
 CodeBuddy, WorkBuddy, Kimi Code, OpenCode, and Hermes Agent setup automate hook/plugin installation;
 OpenClaw can use plugin hooks; Pi integrates via native skills and TypeScript
 lifecycle extensions; Nanobot integrates via skill files; NanoClaw integrates

cmd/memory/setup.go

@@ -22,17 +22,18 @@ var setupCmd = &cobra.Command{
 	Short: "Deploy mnemon into LLM CLI environments",
 	Long: `Detect installed LLM CLIs and deploy mnemon integration.
 
-By default, installs to project-local config (.claude/, .codex/, .cursor/, .trae/, .qoder/, .codebuddy/, .workbuddy/, .opencode/, .openclaw/, .nanobot/, .pi/).
-Use --global to install to user-wide config (~/.claude/, ~/.codex/, ~/.cursor/, ~/.trae/, ~/.qoder/, ~/.codebuddy/, ~/.workbuddy/, ~/.config/opencode/, ~/.openclaw/, ~/.nanobot/workspace/, ~/.pi/agent/).
+By default, installs to project-local config (.claude/, .codex/, .cursor/, .zcode/, .trae/, .qoder/, .codebuddy/, .workbuddy/, .opencode/, .openclaw/, .nanobot/, .pi/).
+Use --global to install to user-wide config (~/.claude/, ~/.codex/, ~/.cursor/, ~/.zcode/, ~/.trae/, ~/.qoder/, ~/.codebuddy/, ~/.workbuddy/, ~/.config/opencode/, ~/.openclaw/, ~/.nanobot/workspace/, ~/.pi/agent/).
 Hermes Agent, QoderWork, and Kimi Code use native user config at ~/.hermes/, ~/.qoderwork/, and ~/.kimi-code/.
 
-Supported environments: Claude Code, Codex, Cursor, Trae, Qoder, QoderWork, CodeBuddy, WorkBuddy, Kimi Code, OpenCode, OpenClaw, Nanobot, Pi, Hermes Agent.
+Supported environments: Claude Code, Codex, Cursor, ZCode, Trae, Qoder, QoderWork, CodeBuddy, WorkBuddy, Kimi Code, OpenCode, OpenClaw, Nanobot, Pi, Hermes Agent.
 
 Examples:
   mnemon setup                              # Interactive: project-local install
   mnemon setup --global                     # Interactive: user-wide install
   mnemon setup --target claude-code         # Non-interactive: Claude Code only
   mnemon setup --target cursor              # Non-interactive: Cursor skill only
+  mnemon setup --target zcode --global      # Non-interactive: ZCode skill and user hooks
   mnemon setup --target trae                # Non-interactive: Trae skill and hooks
   mnemon setup --target qoder               # Non-interactive: Qoder skill and hooks
   mnemon setup --target qoderwork           # Non-interactive: QoderWork skill and hooks
@@ -48,16 +49,16 @@ Examples:
 }
 
 func init() {
-	setupCmd.Flags().StringVar(&setupTarget, "target", "", "target environment (claude-code, codex, cursor, trae, qoder, qoderwork, codebuddy, workbuddy, kimi, opencode, openclaw, nanobot, pi, hermes)")
+	setupCmd.Flags().StringVar(&setupTarget, "target", "", "target environment (claude-code, codex, cursor, zcode, trae, qoder, qoderwork, codebuddy, workbuddy, kimi, opencode, openclaw, nanobot, pi, hermes)")
 	setupCmd.Flags().BoolVar(&setupEject, "eject", false, "remove mnemon integrations")
 	setupCmd.Flags().BoolVar(&setupYes, "yes", false, "auto-confirm all prompts (CI-friendly)")
 	setupCmd.Flags().BoolVar(&setupGlobal, "global", false, "install to user-wide config instead of project-local config")
 	rootCmd.AddCommand(setupCmd)
 }
 
 func runSetup(cmd *cobra.Command, args []string) error {
-	if setupTarget != "" && setupTarget != "claude-code" && setupTarget != "codex" && setupTarget != "cursor" && setupTarget != "trae" && setupTarget != "qoder" && setupTarget != "qoderwork" && setupTarget != "codebuddy" && setupTarget != "workbuddy" && setupTarget != "kimi" && setupTarget != "opencode" && setupTarget != "openclaw" && setupTarget != "nanobot" && setupTarget != "pi" && setupTarget != "hermes" {
-		return fmt.Errorf("invalid target %q (must be claude-code, codex, cursor, trae, qoder, qoderwork, codebuddy, workbuddy, kimi, opencode, openclaw, nanobot, pi, or hermes)", setupTarget)
+	if setupTarget != "" && setupTarget != "claude-code" && setupTarget != "codex" && setupTarget != "cursor" && setupTarget != "zcode" && setupTarget != "trae" && setupTarget != "qoder" && setupTarget != "qoderwork" && setupTarget != "codebuddy" && setupTarget != "workbuddy" && setupTarget != "kimi" && setupTarget != "opencode" && setupTarget != "openclaw" && setupTarget != "nanobot" && setupTarget != "pi" && setupTarget != "hermes" {
+		return fmt.Errorf("invalid target %q (must be claude-code, codex, cursor, zcode, trae, qoder, qoderwork, codebuddy, workbuddy, kimi, opencode, openclaw, nanobot, pi, or hermes)", setupTarget)
 	}
 
 	envs := setup.DetectEnvironments(setupGlobal)
@@ -93,7 +94,7 @@ func runInstallFlow(envs []setup.Environment) error {
 
 	if len(detected) == 0 {
 		fmt.Println("\nNo supported LLM CLI environments detected.")
-		fmt.Println("Install Claude Code, Codex, Cursor, Trae, Qoder, QoderWork, CodeBuddy, WorkBuddy, Kimi Code, OpenCode, OpenClaw, Nanobot, Pi, or Hermes Agent, then run 'mnemon setup' again.")
+		fmt.Println("Install Claude Code, Codex, Cursor, ZCode, Trae, Qoder, QoderWork, CodeBuddy, WorkBuddy, Kimi Code, OpenCode, OpenClaw, Nanobot, Pi, or Hermes Agent, then run 'mnemon setup' again.")
 		return nil
 	}
 
@@ -139,6 +140,8 @@ func installEnv(env *setup.Environment) error {
 		err = installCodex(env)
 	case "cursor":
 		err = installCursor(env)
+	case "zcode":
+		err = installZCode(env)
 	case "trae":
 		err = installTrae(env)
 	case "qoder":
@@ -510,6 +513,103 @@ func selectCursorOptionalHooks() setup.HookSelection {
 	return sel
 }
 
+// ─── ZCode ─────────────────────────────────────────────────────────
+
+func installZCode(env *setup.Environment) error {
+	configDir := env.ConfigDir
+	globalInstall := setupGlobal
+
+	if !setupGlobal && !setupYes && setup.IsInteractive() {
+		home := setup.HomeDir()
+		localDir := ".zcode"
+		globalDir := home + "/.zcode"
+		idx := setup.SelectOne("Install scope",
+			[]string{
+				fmt.Sprintf("Local — skill for this project only (%s/)", localDir),
+				fmt.Sprintf("Global — skill and lifecycle hooks (%s/)", globalDir),
+			}, 0)
+		if idx == 1 {
+			configDir = globalDir
+			globalInstall = true
+		} else {
+			configDir = localDir
+		}
+	}
+
+	totalSteps := 2
+	if globalInstall {
+		totalSteps = 4
+	}
+	fmt.Printf("\nSetting up ZCode (%s)...\n", configDir)
+
+	fmt.Printf("\n[1/%d] Skill\n", totalSteps)
+	if path, err := setup.ZCodeWriteSkill(configDir); err != nil {
+		setup.StatusError(0, 0, "Skill", err)
+		return err
+	} else {
+		setup.StatusOK(0, 0, "Skill", path)
+	}
+
+	fmt.Printf("\n[2/%d] Prompts\n", totalSteps)
+	var promptPath string
+	if path, err := setup.WritePromptFiles(); err != nil {
+		setup.StatusError(0, 0, "Prompts", err)
+		return err
+	} else {
+		setup.StatusOK(0, 0, "Prompts", path)
+		promptPath = path
+	}
+
+	if !globalInstall {
+		fmt.Println()
+		fmt.Println("Setup complete!")
+		fmt.Printf("  Skill   %s/skills/mnemon/SKILL.md\n", configDir)
+		fmt.Printf("  Prompts %s/ (guide.md, skill.md)\n", promptPath)
+		fmt.Println()
+		fmt.Println("ZCode currently ignores project-level hooks; use '--global' to install lifecycle hooks.")
+		fmt.Println("Refresh Settings → Skills or start a new ZCode session to activate.")
+		fmt.Println("Run 'mnemon setup --eject --target zcode' to remove.")
+		return nil
+	}
+
+	fmt.Printf("\n[3/%d] Hooks\n", totalSteps)
+	hooks := []struct {
+		label, filename string
+		content         []byte
+	}{
+		{label: "Hook: prime", filename: "prime.sh", content: assets.ZCodePrimeHook},
+		{label: "Hook: remind", filename: "user_prompt.sh", content: assets.ZCodeUserPromptHook},
+		{label: "Hook: nudge", filename: "stop.sh", content: assets.ZCodeStopHook},
+	}
+	for _, hook := range hooks {
+		if path, err := setup.ZCodeWriteHook(configDir, hook.filename, hook.content); err != nil {
+			setup.StatusError(0, 0, hook.label, err)
+			return err
+		} else {
+			setup.StatusOK(0, 0, hook.label, path)
+		}
+	}
+
+	fmt.Printf("\n[4/%d] Config\n", totalSteps)
+	if path, err := setup.ZCodeRegisterHooks(configDir); err != nil {
+		setup.StatusError(0, 0, "Hooks config", err)
+		return err
+	} else {
+		setup.StatusUpdated(0, 0, "Hooks config", path)
+	}
+
+	fmt.Println()
+	fmt.Println("Setup complete!")
+	fmt.Printf("  Skill   %s/skills/mnemon/SKILL.md\n", configDir)
+	fmt.Printf("  Hooks   %s/cli/config.json (SessionStart, UserPromptSubmit, Stop)\n", configDir)
+	fmt.Printf("  Prompts %s/ (guide.md, skill.md)\n", promptPath)
+	fmt.Println()
+	fmt.Println("Start a new ZCode session to activate the mnemon skill and hooks.")
+	fmt.Println("Run 'mnemon setup --eject --target zcode --global' to remove.")
+
+	return nil
+}
+
 // ─── Trae ───────────────────────────────────────────────────────────
 
 func installTrae(env *setup.Environment) error {
@@ -1407,6 +1507,12 @@ func ejectEnv(env *setup.Environment) error {
 			return errs[0]
 		}
 
+	case "zcode":
+		errs := setup.ZCodeEject(env.ConfigDir)
+		if len(errs) > 0 {
+			return errs[0]
+		}
+
 	case "trae":
 		errs := setup.TraeEject(env.ConfigDir)
 		ejectMarkdown("AGENTS.md", "Remove memory guidance from ./AGENTS.md?")

docs/USAGE.md

@@ -33,6 +33,7 @@ mnemon setup --global
 mnemon setup --target claude-code
 mnemon setup --target codex
 mnemon setup --target cursor
+mnemon setup --target zcode --global
 mnemon setup --target trae
 mnemon setup --target qoder
 mnemon setup --target qoderwork
@@ -55,8 +56,8 @@ mnemon setup --eject --target claude-code
 
 | Flag | Default | Description |
 |---|---|---|
-| `--global` | `false` | Install to user-wide config instead of project-local (recommended for Nanobot: installs to `~/.nanobot/workspace/`; Pi installs to `~/.pi/agent/`; Hermes installs to `~/.hermes/`; QoderWork installs to `~/.qoderwork/`; Kimi Code installs to `~/.kimi-code/` or `$KIMI_CODE_HOME/`; OpenCode installs to `~/.config/opencode/`) |
-| `--target <name>` | (auto-detect) | Target environment: `claude-code`, `codex`, `cursor`, `trae`, `qoder`, `qoderwork`, `codebuddy`, `workbuddy`, `kimi`, `opencode`, `openclaw`, `nanobot`, `pi`, or `hermes` |
+| `--global` | `false` | Install to user-wide config instead of project-local (required for ZCode lifecycle hooks; recommended for Nanobot: installs to `~/.nanobot/workspace/`; Pi installs to `~/.pi/agent/`; Hermes installs to `~/.hermes/`; QoderWork installs to `~/.qoderwork/`; Kimi Code installs to `~/.kimi-code/` or `$KIMI_CODE_HOME/`; OpenCode installs to `~/.config/opencode/`) |
+| `--target <name>` | (auto-detect) | Target environment: `claude-code`, `codex`, `cursor`, `zcode`, `trae`, `qoder`, `qoderwork`, `codebuddy`, `workbuddy`, `kimi`, `opencode`, `openclaw`, `nanobot`, `pi`, or `hermes` |
 | `--eject` | `false` | Remove mnemon integrations |
 | `--yes` | `false` | Auto-confirm all prompts |
 

docs/zh/README.md

@@ -107,6 +107,17 @@ mnemon setup
 
 `mnemon setup` 自动检测 Claude Code，交互式部署技能文件、钩子和行为引导。启动新会话 — 记忆自动运作。
 
+### [ZCode](https://zcode.z.ai/)
+
+```bash
+mnemon setup --target zcode --global --yes
+```
+
+ZCode 会将 Mnemon skill 安装到 `~/.zcode/skills/`，并在
+`~/.zcode/cli/config.json` 中注册用户级生命周期 hooks。新会话会注入记忆状态，
+模型调用前会收到 recall 指引，停止时会评估 durable-memory 回写。不加
+`--global` 时只安装项目 skill，因为 ZCode 当前不会执行项目级 hooks 配置。
+
 ### [TRAE](https://www.trae.ai/) (TRAE Work)
 
 ```bash
@@ -283,7 +294,7 @@ store 可见。**Remind** 触发 recall 判断。**Nudge** 触发 writeback 判
 
 - **零用户操作** — 安装一次；支持 hook 的 runtime 可用 hook，minimal runtime 可用持久规则
 - **LLM 监督式** — 宿主 LLM 主动决定记什么、更新什么、遗忘什么；无内嵌 LLM，无 API 密钥
-- **多框架支持** — Claude Code、Codex、Cursor、TRAE/TRAE Work、Qoder/QoderWork、CodeBuddy、WorkBuddy、Kimi Code、OpenCode 和 Hermes Agent（hooks/plugins）、OpenClaw（plugins）、Pi（extensions）、Nanobot（skills）、DeepSeek Harness（通过 dsh-mnemon 插件）等
+- **多框架支持** — Claude Code、Codex、Cursor、ZCode、TRAE/TRAE Work、Qoder/QoderWork、CodeBuddy、WorkBuddy、Kimi Code、OpenCode 和 Hermes Agent（hooks/plugins）、OpenClaw（plugins）、Pi（extensions）、Nanobot（skills）、DeepSeek Harness（通过 dsh-mnemon 插件）等
 - **Runtime 原生集成** — 各 runtime 的 `SKILL.md`、共享 `guide.md`，以及受支持的 hook 或 extension
 - **四图架构** — 时序、实体、因果、语义四种边，不仅仅是向量相似度
 - **意图原生协议** — 三个原语（`remember`、`link`、`recall`）映射到 LLM 的认知词汇而非数据库语法；结构化 JSON 输出，带信号透明度

docs/zh/USAGE.md

@@ -33,6 +33,7 @@ mnemon setup --global
 mnemon setup --target claude-code
 mnemon setup --target codex
 mnemon setup --target cursor
+mnemon setup --target zcode --global
 mnemon setup --target trae
 mnemon setup --target qoder
 mnemon setup --target qoderwork
@@ -55,8 +56,8 @@ mnemon setup --eject --target claude-code
 
 | 标志 | 默认值 | 说明 |
 |---|---|---|
-| `--global` | `false` | 安装到用户级配置而非项目本地（Nanobot 推荐安装到 `~/.nanobot/workspace/`；Pi 安装到 `~/.pi/agent/`；Hermes 安装到 `~/.hermes/`；QoderWork 安装到 `~/.qoderwork/`；Kimi Code 安装到 `~/.kimi-code/` 或 `$KIMI_CODE_HOME/`；OpenCode 安装到 `~/.config/opencode/`） |
-| `--target <name>` | (自动检测) | 目标环境：`claude-code`、`codex`、`cursor`、`trae`、`qoder`、`qoderwork`、`codebuddy`、`workbuddy`、`kimi`、`opencode`、`openclaw`、`nanobot`、`pi` 或 `hermes` |
+| `--global` | `false` | 安装到用户级配置而非项目本地（ZCode 生命周期 hooks 必须使用；Nanobot 推荐安装到 `~/.nanobot/workspace/`；Pi 安装到 `~/.pi/agent/`；Hermes 安装到 `~/.hermes/`；QoderWork 安装到 `~/.qoderwork/`；Kimi Code 安装到 `~/.kimi-code/` 或 `$KIMI_CODE_HOME/`；OpenCode 安装到 `~/.config/opencode/`） |
+| `--target <name>` | (自动检测) | 目标环境：`claude-code`、`codex`、`cursor`、`zcode`、`trae`、`qoder`、`qoderwork`、`codebuddy`、`workbuddy`、`kimi`、`opencode`、`openclaw`、`nanobot`、`pi` 或 `hermes` |
 | `--eject` | `false` | 移除 mnemon 集成 |
 | `--yes` | `false` | 自动确认所有提示 |
 

internal/memory/setup/assets/assets.go

@@ -44,6 +44,18 @@ var CursorStopHook []byte
 //go:embed cursor/compact.sh
 var CursorCompactHook []byte
 
+//go:embed zcode/SKILL.md
+var ZCodeSkill []byte
+
+//go:embed zcode/prime.sh
+var ZCodePrimeHook []byte
+
+//go:embed zcode/user_prompt.sh
+var ZCodeUserPromptHook []byte
+
+//go:embed zcode/stop.sh
+var ZCodeStopHook []byte
+
 //go:embed trae/SKILL.md
 var TraeSkill []byte
 
@@ -163,5 +175,5 @@ var HermesCompactHook []byte
 
 // All returns the embedded filesystem for inspection.
 //
-//go:embed claude codex cursor trae qoder qoderwork codebuddy workbuddy kimi opencode openclaw nanoclaw nanobot pi hermes
+//go:embed claude codex cursor zcode trae qoder qoderwork codebuddy workbuddy kimi opencode openclaw nanoclaw nanobot pi hermes
 var All embed.FS