@techwavedev/agi-agent-kit 1.1.7 → 1.2.1

package/CHANGELOG.md

@@ -5,10 +5,91 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.2.1] - 2026-02-09
+
+### Added
+
+- **Platform-Adaptive Multi-Agent Orchestration** (`parallel-agents` v2.0):
+  - **Strategy A: Claude Code Agent Teams** — True parallel multi-agent orchestration via tmux/in-process sessions. Requires `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`.
+  - **Strategy B: Claude Code Subagents** — Background/foreground task orchestration via `Task()` tool with `context: fork`.
+  - **Strategy C: Sequential Personas** — Universal fallback for Gemini, Opencode, and other platforms using `@agent` persona switching.
+  - **Strategy D: Kiro Autonomous Agent** — Async parallel task execution in sandboxed environments with PR-based delivery and cross-repo coordination.
+  - Automatic platform detection and strategy selection.
+  - Subagent configuration reference (frontmatter, tools, permissions, model, memory).
+  - Full Claude Code subagent lifecycle documentation (create, configure, invoke, manage).
+
+- **Kiro IDE Powers & Autonomous Agent Support**:
+  - Full Kiro Powers documentation: `POWER.md` anatomy, frontmatter keywords activation, onboarding sections, steering files, `mcp.json` configuration with auto-namespacing.
+  - Kiro Hooks system (`.kiro/hooks/`) with JSON structure and automated behaviors.
+  - Kiro Autonomous Agent: sandboxed execution, PR-based reviews, cross-repo coordination, learning from code reviews.
+  - 12 curated launch partner Powers documented (Figma, Supabase, Stripe, Neon, Netlify, Postman, Strands, Datadog, Dynatrace, AWS CDK, Terraform, Aurora).
+  - **Antigravity ↔ Kiro mapping guide**: Skill-to-Power conversion workflow, directory mapping, frontmatter translation.
+
+- **Plugin & Extension Auto-Discovery** (`plugin-discovery` v1.1.0 — NEW SKILL):
+  - Cross-platform extension auto-discovery for Claude Code, Kiro IDE, Gemini, and Opencode.
+  - Claude Code: Plugin marketplace guide (official + custom), LSP plugins by language, service integrations, scopes, subagent/skill discovery.
+  - Kiro: Full Powers discovery, installation guide (IDE, kiro.dev, GitHub, local path), setup checklist.
+  - Gemini/Opencode: Skills catalog discovery, MCP server detection.
+  - Cross-platform compatibility map (11 features × 4 platforms).
+
+- **One-Shot Platform Setup Wizard** (`platform_setup.py`):
+  - Auto-detects platform: Claude Code, Kiro IDE, Gemini, Opencode.
+  - Scans project tech stack: languages (JS/TS/Python/Go/Rust/Ruby), frameworks (Next.js/React/Vue/Express/Angular/Svelte/Astro/React Native), services (GitHub/GitLab/Docker/Vercel/Netlify/Stripe/Supabase/Firebase/Terraform).
+  - Generates prioritized recommendations with `🔴 High` / `🟡 Medium` / `🟢 Low` indicators.
+  - Auto-applies configurable settings (Agent Teams, directory creation, hook setup) with single `Y/n` confirmation.
+  - Shows manual instructions for platform-only actions (plugin installs, Power installs).
+  - 4 modes: interactive, `--auto`, `--dry-run`, `--json`.
+  - New `/setup` workflow with `// turbo` annotation for auto-run.
+
+- **Intelligent Routing v2.0** (`intelligent-routing` v2.0):
+  - Platform detection at session start (Claude Code, Kiro IDE, Gemini, Opencode).
+  - Proactive capability announcements per platform.
+  - Team Leader mode for Claude Code with Agent Teams enabled.
+  - Powers-driven orchestration mode for Kiro IDE.
+  - Proactive feature recommendations: suggests Agent Teams, plugins, Powers, Autonomous Agent when not enabled.
+  - Multi-domain task routing adapts to best available parallelism strategy.
+
+- **Memory System Integration** (`session_boot.py` — NEW SCRIPT):
+  - `execution/session_boot.py` — Single entry point for session initialization. Checks Qdrant, Ollama, embedding models, and collections in one command. `--auto-fix` flag auto-pulls missing models and creates collections.
+  - **Session Boot Protocol** added as the **first section** in `AGENTS.md` — agents run `python3 execution/session_boot.py --auto-fix` before any work begins.
+  - `AGENTS.md` Memory-First section rewritten with explicit CLI commands: `memory_manager.py auto`, `store`, `cache-store` with decision tree table.
+  - `platform_setup.py` now detects full memory system: Qdrant status, Ollama status, embedding model presence, collection existence, point counts.
+  - Memory recommendations engine: suggests starting Qdrant/Ollama, pulling embedding model, or initializing collections when issues are detected.
+  - Memory report section (🧠) in platform setup output shows live system status.
+
+### Changed
+
+- **`parallel-agents`**: Rewritten from v1.0 to v2.0 — now platform-adaptive with 4 orchestration strategies instead of 1.
+- **`intelligent-routing`**: Rewritten from v1.0 to v2.0 — now includes platform detection, proactive recommendations, and Kiro support.
+- **Cross-Platform Compatibility Map**: Updated with 2 new rows (Dynamic MCP Loading, Cross-Repo Tasks) and accurate Kiro feature coverage.
+- **`package.json`**: Added `kiro`, `opencode`, and `platform-adaptive` keywords for NPM discoverability.
+- **Templates**: All modified skills (`parallel-agents`, `intelligent-routing`, `plugin-discovery`) and scripts (`platform_setup.py`) synced to `templates/skills/knowledge/` for NPX distribution.
+- **SKILLS_CATALOG.md**: Regenerated with 56 skills, including the new `plugin-discovery` skill.
+- **`bin/init.js`**: NPX init now copies `execution/` scripts (session_boot.py, session_init.py, memory_manager.py) and `directives/` (memory_integration.md) to scaffolded projects. Update function also refreshes these files.
+- **Post-install message**: Now shows `session_boot.py --auto-fix` as step 3 after installation.
+- **`/setup-memory` workflow**: Fixed stale references, now uses correct scripts (session_init.py, memory_manager.py).
+- **`/setup` workflow**: Added memory system troubleshooting section with Docker/Ollama/collection init commands.
+
+### Fixed
+
+- **Stale script references**: `/setup-memory` workflow referenced non-existent `init_memory_system.py` and `memory_middleware.py` — now correctly uses `session_init.py` and `memory_manager.py`.
+- **Memory system unused**: Despite being installed, no agent instructions explicitly told agents WHEN to call the memory scripts. Now enforced via Session Boot Protocol at top of AGENTS.md.
+- **`platform_setup.py` missing memory**: Setup wizard reported platform features but ignored Qdrant/Ollama status — now detects and recommends fixes.
+- **`info` action missing**: Platform setup wizard didn't handle informational recommendations (e.g., "collections are empty") — added `info` action type with ℹ️ status icon.
+- **Templates missing execution scripts**: NPX init created the `execution/` directory but didn't copy any scripts into it — now ships session_boot.py, session_init.py, and memory_manager.py.
+
 ## [1.1.7] - 2026-02-07
 
 ### Added
 
+- **NotebookLM RAG Skill** (EC Scoped): New `notebooklm-rag` skill providing deep-search RAG capabilities powered by Google NotebookLM + Gemini 2.5. Complementary to `qdrant-memory` for explicit, document-grounded research.
+  - **B.L.A.S.T. Protocol**: Structured research workflow (Browse → Load → Ask → Synthesize → Transfer).
+  - **4 Research Modes**: Quick (single query), Deep (3-5 iterative), Cross-Ref (multi-notebook), Plan (doc-grounded planning).
+  - **Confidence Classification**: Automatic HIGH/MEDIUM/LOW categorization with source attribution.
+  - `scripts/research_query.py` — Generates structured research questions by mode.
+  - `scripts/research_report.py` — Formats findings into Markdown/JSON reports with confidence levels and knowledge gap analysis.
+  - `scripts/preflight_check.py` — Pre-flight validation checklist for MCP server, auth, and library.
+  - `references/research_patterns.md` — Workflow templates, query optimization, rate limit strategies.
 - **Auto-Update in Skill Creator**: `init_skill.py` now auto-runs `update_catalog.py` and `sync_docs.py` after creating a new skill.
   - Default ON — use `--no-auto-update` to skip.
   - New `--skills-dir` flag for specifying catalog update target directory.
@@ -20,7 +101,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **Skill Creator Documentation** (`SKILL_skillcreator.md`):
   - Step 3: Documents new auto-update behavior and `--no-auto-update` / `--skills-dir` flags.
   - Step 6: Notes that manual catalog update is now only needed for modifications/deletions.
-- **SKILLS_CATALOG.md**: Regenerated with 45 public skills.
+- **SKILLS_CATALOG.md**: Regenerated with 55 skills including `notebooklm-rag`.
 
 ### Fixed
 

package/README.md

@@ -7,6 +7,8 @@
 
 `@techwavedev/agi-agent-kit` is a modular, deterministic framework designed to bridge the gap between LLM reasoning and reliable production execution. It scaffolds a "3-Layer Architecture" (Intent → Orchestration → Execution) that forces agents to use tested scripts rather than hallucinating code.
 
+**v1.2.1** — Now with platform-adaptive orchestration and integrated semantic memory across Claude Code, Kiro IDE, Gemini, and Opencode.
+
 ---
 
 ## 🚀 Quick Start
@@ -23,18 +25,61 @@ You'll be prompted to choose a pack:
 - **knowledge** - Core + 36 specialized skills (API, Security, Design, Architecture)
 - **full** - Complete suite with `.agent/` structure (agents, workflows, rules)
 
+After installation, run the **one-shot setup wizard** to auto-configure your environment:
+
+```bash
+python3 skills/plugin-discovery/scripts/platform_setup.py --project-dir .
+```
+
+This detects your platform, scans the project stack, and configures everything with a single confirmation.
+
+Then **boot the memory system** for automatic token savings:
+
+```bash
+python3 execution/session_boot.py --auto-fix
+```
+
+This checks Qdrant, Ollama, embedding models, and collections — auto-fixing any issues.
+
 ---
 
 ## ✨ Key Features
 
-| Feature                     | Description                                                                |
-| --------------------------- | -------------------------------------------------------------------------- |
-| **Deterministic Execution** | Separates business logic (Python scripts) from AI reasoning (Directives)   |
-| **Modular Skill System**    | Plug-and-play capabilities that can be added or removed instantly          |
-| **Semantic Memory**         | Built-in Qdrant-powered memory with 95% token savings via caching          |
-| **Universal Compatibility** | Works with Claude, Gemini, and OpenAI via standardized context files       |
-| **Self-Healing Workflows**  | Agents read error logs, patch scripts, and update directives automatically |
-| **Self-Update**             | Update to the latest version with a single command                         |
+| Feature                       | Description                                                                 |
+| ----------------------------- | --------------------------------------------------------------------------- |
+| **Deterministic Execution**   | Separates business logic (Python scripts) from AI reasoning (Directives)    |
+| **Modular Skill System**      | 56 plug-and-play skills that can be added or removed instantly              |
+| **Platform-Adaptive**         | Auto-detects and optimizes for Claude Code, Kiro IDE, Gemini, and Opencode  |
+| **Multi-Agent Orchestration** | Agent Teams, subagents, Powers, or sequential personas — adapts to platform |
+| **Semantic Memory**           | Built-in Qdrant-powered memory with 95% token savings via caching           |
+| **Self-Healing Workflows**    | Agents read error logs, patch scripts, and update directives automatically  |
+| **One-Shot Setup**            | Platform detection + project stack scan + auto-configuration in one command |
+
+---
+
+## 🌐 Platform Support
+
+The framework automatically detects your AI coding environment and activates the best available features:
+
+| Platform        | Orchestration Strategy              | Key Features                                 |
+| --------------- | ----------------------------------- | -------------------------------------------- |
+| **Claude Code** | Agent Teams (parallel) or Subagents | Plugins, marketplace, LSP, hooks             |
+| **Kiro IDE**    | Powers + Autonomous Agent (async)   | Dynamic MCP loading, hooks, cross-repo tasks |
+| **Gemini**      | Sequential personas via `@agent`    | Skills, MCP servers, execution scripts       |
+| **Opencode**    | Sequential personas via `@agent`    | Skills, MCP servers, providers               |
+
+Run `/setup` to auto-detect and configure your platform, or use the setup script directly:
+
+```bash
+# Interactive (one Y/n question)
+python3 skills/plugin-discovery/scripts/platform_setup.py --project-dir .
+
+# Auto-apply everything
+python3 skills/plugin-discovery/scripts/platform_setup.py --project-dir . --auto
+
+# Preview without changes
+python3 skills/plugin-discovery/scripts/platform_setup.py --project-dir . --dry-run
+```
 
 ---
 
@@ -43,16 +88,25 @@ You'll be prompted to choose a pack:
 ```
 your-project/
 ├── AGENTS.md              # Master instruction file (symlinked to GEMINI.md, CLAUDE.md)
-├── skills/                # Pre-built tools
+├── skills/                # 56 pre-built tools
 │   ├── webcrawler/        # Documentation harvesting
 │   ├── pdf-reader/        # PDF text extraction
 │   ├── qdrant-memory/     # Semantic caching & memory
 │   ├── documentation/     # Auto-documentation maintenance
-│   └── self-update/       # Framework self-update capability
+│   ├── plugin-discovery/  # Platform detection & setup wizard
+│   ├── parallel-agents/   # Multi-agent orchestration
+│   ├── intelligent-routing/ # Smart agent selection & routing
+│   ├── self-update/       # Framework self-update capability
+│   └── ...                # 48 more specialized skills
 ├── directives/            # SOPs in Markdown
+│   └── memory_integration.md  # Memory protocol reference
 ├── execution/             # Deterministic Python scripts
+│   ├── session_boot.py    # Session startup (Qdrant + Ollama check)
+│   ├── session_init.py    # Collection initializer
+│   └── memory_manager.py  # Store/retrieve/cache operations
 ├── skill-creator/         # Tools to create new skills
 └── .agent/                # (full pack) Agents, workflows, rules
+    └── workflows/         # /setup, /deploy, /test, /debug, etc.
 ```
 
 ---
@@ -68,6 +122,7 @@ The system operates on three layers:
 ├─────────────────────────────────────────────────────────┤
 │  Layer 2: ORCHESTRATION (Agent)                         │
 │  └─ LLM reads directive, decides which tool to call     │
+│  └─ Platform-adaptive: Teams, Subagents, or Personas    │
 ├─────────────────────────────────────────────────────────┤
 │  Layer 3: EXECUTION (Code)                              │
 │  └─ Pure Python scripts (execution/) do the actual work │
@@ -78,6 +133,45 @@ The system operates on three layers:
 
 ---
 
+## 🧠 Semantic Memory
+
+Built-in Qdrant-powered memory with automatic token savings:
+
+| Scenario              | Without Memory | With Memory | Savings  |
+| --------------------- | -------------- | ----------- | -------- |
+| Repeated question     | ~2000 tokens   | 0 tokens    | **100%** |
+| Similar architecture  | ~5000 tokens   | ~500 tokens | **90%**  |
+| Past error resolution | ~3000 tokens   | ~300 tokens | **90%**  |
+
+**Setup** (requires [Qdrant](https://qdrant.tech/) + [Ollama](https://ollama.com/)):
+
+```bash
+# Start Qdrant
+docker run -d -p 6333:6333 -v qdrant_storage:/qdrant/storage qdrant/qdrant
+
+# Start Ollama + pull embedding model
+ollama serve &
+ollama pull nomic-embed-text
+
+# Boot memory system (auto-creates collections)
+python3 execution/session_boot.py --auto-fix
+```
+
+Agents automatically run `session_boot.py` at session start (first instruction in `AGENTS.md`). Memory operations:
+
+```bash
+# Auto-query (check cache + retrieve context)
+python3 execution/memory_manager.py auto --query "your task summary"
+
+# Store a decision
+python3 execution/memory_manager.py store --content "what was decided" --type decision
+
+# Health check
+python3 execution/memory_manager.py health
+```
+
+---
+
 ## ⚡ Prerequisites
 
 ```bash
@@ -100,6 +194,12 @@ pip install ollama sentence-transformers
 npx @techwavedev/agi-agent-kit init --pack=full
 ```
 
+### Auto-detect platform and configure environment
+
+```bash
+python3 skills/plugin-discovery/scripts/platform_setup.py --project-dir .
+```
+
 ### Update to latest version
 
 ```bash
@@ -108,6 +208,12 @@ npx @techwavedev/agi-agent-kit@latest init --pack=full
 python3 skills/self-update/scripts/update_kit.py
 ```
 
+### Boot memory system
+
+```bash
+python3 execution/session_boot.py --auto-fix
+```
+
 ### System health check
 
 ```bash
@@ -128,17 +234,89 @@ python3 skill-creator/scripts/update_catalog.py --skills-dir skills/
 
 ---
 
+## 🎯 Activation Reference
+
+Use these keywords, commands, and phrases to trigger specific capabilities:
+
+### Slash Commands (Workflows)
+
+| Command         | What It Does                                     |
+| --------------- | ------------------------------------------------ |
+| `/setup`        | Auto-detect platform and configure environment   |
+| `/setup-memory` | Initialize Qdrant + Ollama memory system         |
+| `/create`       | Start interactive app builder dialogue           |
+| `/plan`         | Create a structured project plan (no code)       |
+| `/enhance`      | Add or update features in existing app           |
+| `/debug`        | Activate systematic debugging mode               |
+| `/test`         | Generate and run tests                           |
+| `/deploy`       | Pre-flight checks + deployment                   |
+| `/orchestrate`  | Multi-agent coordination for complex tasks       |
+| `/brainstorm`   | Structured brainstorming with multiple options   |
+| `/preview`      | Start/stop local dev server                      |
+| `/status`       | Show project progress and status board           |
+| `/update`       | Update AGI Agent Kit to latest version           |
+| `/checkup`      | Verify agents, workflows, skills, and core files |
+
+### Agent Mentions (`@agent`)
+
+| Mention                | Specialist              | When To Use                               |
+| ---------------------- | ----------------------- | ----------------------------------------- |
+| `@orchestrator`        | Multi-agent coordinator | Complex multi-domain tasks                |
+| `@project-planner`     | Planning specialist     | Roadmaps, task breakdowns, phase planning |
+| `@frontend-specialist` | UI/UX architect         | Web interfaces, React, Next.js            |
+| `@mobile-developer`    | Mobile specialist       | iOS, Android, React Native, Flutter       |
+| `@backend-specialist`  | API/DB engineer         | Server-side, databases, APIs              |
+| `@security-auditor`    | Security expert         | Vulnerability scanning, audits, hardening |
+| `@debugger`            | Debug specialist        | Complex bug investigation                 |
+| `@game-developer`      | Game dev specialist     | 2D/3D games, multiplayer, VR/AR           |
+
+### Skill Trigger Keywords (Natural Language)
+
+| Category           | Trigger Words / Phrases                                                | Skill Activated                     |
+| ------------------ | ---------------------------------------------------------------------- | ----------------------------------- |
+| **Memory**         | "don't use cache", "no cache", "skip memory", "fresh"                  | Memory opt-out                      |
+| **Research**       | "research my docs", "check my notebooks", "deep search", "@notebooklm" | `notebooklm-rag`                    |
+| **Documentation**  | "update docs", "regenerate catalog", "sync documentation"              | `documentation`                     |
+| **Quality**        | "lint", "format", "check", "validate", "static analysis"               | `lint-and-validate`                 |
+| **Testing**        | "write tests", "run tests", "TDD", "test coverage"                     | `testing-patterns` / `tdd-workflow` |
+| **Architecture**   | "design system", "architecture decision", "ADR", "trade-off"           | `architecture`                      |
+| **Security**       | "security scan", "vulnerability", "audit", "OWASP"                     | `red-team-tactics`                  |
+| **Performance**    | "lighthouse", "bundle size", "core web vitals", "profiling"            | `performance-profiling`             |
+| **Design**         | "design UI", "color scheme", "typography", "layout"                    | `frontend-design`                   |
+| **Deployment**     | "deploy", "rollback", "release", "CI/CD"                               | `deployment-procedures`             |
+| **API**            | "REST API", "GraphQL", "tRPC", "API design"                            | `api-patterns`                      |
+| **Database**       | "schema design", "migration", "query optimization"                     | `database-design`                   |
+| **Planning**       | "plan this", "break down", "task list", "requirements"                 | `plan-writing`                      |
+| **Brainstorming**  | "explore options", "what are the approaches", "pros and cons"          | `brainstorming`                     |
+| **Code Review**    | "review this", "code quality", "best practices"                        | `code-review-checklist`             |
+| **i18n**           | "translate", "localization", "RTL", "locale"                           | `i18n-localization`                 |
+| **AWS**            | "terraform", "EKS", "Lambda", "S3", "CloudFront"                       | `aws` / `aws-terraform`             |
+| **Infrastructure** | "Consul", "service mesh", "OpenSearch"                                 | `consul` / `opensearch`             |
+
+### Memory System Commands
+
+| What You Want                | Command / Phrase                                                                 |
+| ---------------------------- | -------------------------------------------------------------------------------- |
+| **Boot memory**              | `python3 execution/session_boot.py --auto-fix`                                   |
+| **Check before a task**      | `python3 execution/memory_manager.py auto --query "..."`                         |
+| **Store a decision**         | `python3 execution/memory_manager.py store --content "..." --type decision`      |
+| **Cache a response**         | `python3 execution/memory_manager.py cache-store --query "..." --response "..."` |
+| **Health check**             | `python3 execution/memory_manager.py health`                                     |
+| **Skip cache for this task** | Say "fresh", "no cache", or "skip memory" in your prompt                         |
+
+---
+
 ## 📚 Documentation
 
 - **[AGENTS.md](./AGENTS.md)** - Complete architecture and operating principles
-- **[skills/SKILLS_CATALOG.md](./skills/SKILLS_CATALOG.md)** - All available skills
+- **[skills/SKILLS_CATALOG.md](./skills/SKILLS_CATALOG.md)** - All 56 available skills
 - **[CHANGELOG.md](./CHANGELOG.md)** - Version history
 
 ---
 
 ## 🛡️ Security
 
-This package includes a pre-flight security scanner (`verify_public_release.py`) that checks for private terms before publishing. All templates are sanitized for public use.
+This package includes a pre-flight security scanner that checks for private terms before publishing. All templates are sanitized for public use.
 
 ---
 

package/bin/init.js

@@ -248,6 +248,24 @@ function copyBaseFiles(targetPath, templatesPath, options) {
     }
   }
   
+  // Copy execution scripts (memory system)
+  const srcExecution = path.join(templatesPath, 'base', 'execution');
+  const destExecution = path.join(targetPath, 'execution');
+  
+  if (fs.existsSync(srcExecution)) {
+    copyDirSync(srcExecution, destExecution);
+    log.success('Installed execution/ (memory system scripts)');
+  }
+  
+  // Copy directives
+  const srcDirectives = path.join(templatesPath, 'base', 'directives');
+  const destDirectives = path.join(targetPath, 'directives');
+  
+  if (fs.existsSync(srcDirectives)) {
+    copyDirSync(srcDirectives, destDirectives);
+    log.success('Installed directives/');
+  }
+  
   // Copy skill-creator
   const srcSkillCreator = path.join(templatesPath, 'base', 'skill-creator');
   const destSkillCreator = path.join(targetPath, 'skill-creator');
@@ -355,8 +373,10 @@ Next steps:
   1. Review ${colors.cyan}AGENTS.md${colors.reset} for architecture overview
   2. Install Python dependencies:
      ${colors.yellow}pip install requests beautifulsoup4 html2text lxml qdrant-client${colors.reset}
-  3. Check ${colors.cyan}skills/${colors.reset} for available capabilities
-  4. Create ${colors.cyan}.env${colors.reset} with your API keys
+  3. Boot the memory system (optional, requires Qdrant + Ollama):
+     ${colors.yellow}python3 execution/session_boot.py --auto-fix${colors.reset}
+  4. Check ${colors.cyan}skills/${colors.reset} for available capabilities
+  5. Create ${colors.cyan}.env${colors.reset} with your API keys
   
 Happy coding! 🎉
 `);
@@ -430,6 +450,14 @@ async function update(options) {
       console.log(`  ${colors.green}✔${colors.reset} Updated skill-creator/`);
   }
 
+  // 3b. Update Execution Scripts (memory system)
+  const srcExec = path.join(templatesPath, 'base', 'execution');
+  const destExec = path.join(options.path, 'execution');
+  if (fs.existsSync(srcExec)) {
+      copyDirSync(srcExec, destExec);
+      console.log(`  ${colors.green}✔${colors.reset} Updated execution/ (memory system scripts)`);
+  }
+
   // 4. Update Core Documentation if needed
   // We generally respect user's AGENTS.md, but maybe we update GEMINI.md/CLAUDE.md symlinks?
   if (options.symlinks) {

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@techwavedev/agi-agent-kit",
-  "version": "1.1.7",
-  "description": "Enterprise-Grade Agentic Framework - Modular skill-based AI assistant toolkit with deterministic execution and semantic memory.",
+  "version": "1.2.1",
+  "description": "Enterprise-Grade Agentic Framework - Modular skill-based AI assistant toolkit with deterministic execution, semantic memory, and platform-adaptive orchestration.",
   "bin": {
     "agi-agent-kit": "./bin/init.js"
   },
@@ -17,9 +17,12 @@
     "skills",
     "claude",
     "gemini",
+    "kiro",
+    "opencode",
     "llm",
     "semantic-cache",
-    "qdrant"
+    "qdrant",
+    "platform-adaptive"
   ],
   "author": "Elton Machado@techwave",
   "license": "Apache-2.0",

package/templates/base/AGENTS.md

@@ -1,6 +1,20 @@
 # Agent Instructions
 
-> `CLAUDE.md` and `GEMINI.md` are symlinks to this file, so the same instructions load in any AI environment.
+> `CLAUDE.md`, `GEMINI.md`, and `OPENCODE.md` are symlinks to this file, so the same instructions load in any AI environment.
+
+---
+
+## ⚡ Session Boot Protocol (MANDATORY)
+
+**Run this ONCE at the start of every session, before any other work:**
+
+```bash
+python3 execution/session_boot.py --auto-fix
+```
+
+This single command checks Qdrant, Ollama, embedding models, and collections. If anything is missing, `--auto-fix` repairs it automatically. If the output shows `"memory_ready": true`, proceed normally. If it shows issues, follow the printed instructions.
+
+**Why this matters:** The memory system provides 80-100% token savings on repeated work. Skipping this step means every query pays full token cost.
 
 ---
 
@@ -151,34 +165,51 @@ python execution/scrape_single_site.py \
 
 **All operations use the Qdrant-powered memory system by default.**
 
+#### Session Start (MANDATORY — run once per session)
+
+```bash
+python3 execution/session_boot.py --auto-fix
+```
+
+If `"memory_ready": true`, proceed. If false, follow the printed instructions.
+
+#### Before Every Complex Task
+
+```bash
+python3 execution/memory_manager.py auto --query "<one-line summary of the task>"
 ```
-┌─────────────────────────────────────────────────────────────┐
-│  QUERY RECEIVED                                              │
-│  ↓                                                           │
-│  1. Check for opt-out flags ("no cache", "fresh", etc.)     │
-│  ↓                                                           │
-│  2. SEMANTIC CACHE CHECK (similarity > 0.92)                │
-│     └─ Hit? → Return cached response (100% token savings)   │
-│  ↓                                                           │
-│  3. CONTEXT RETRIEVAL (top 5 relevant memories)             │
-│     └─ Inject decisions, patterns, solutions (80-95% saved) │
-│  ↓                                                           │
-│  4. EXECUTE QUERY with enriched context                      │
-│  ↓                                                           │
-│  5. STORE RESPONSE for future cache hits                    │
-└─────────────────────────────────────────────────────────────┘
+
+**Decision tree based on output:**
+
+| Result               | Action                                                                    |
+| -------------------- | ------------------------------------------------------------------------- |
+| `"cache_hit": true`  | Use cached response directly. Inform user: "Retrieved from memory cache." |
+| `"source": "memory"` | Inject `context_chunks` into your reasoning. Cite them.                   |
+| `"source": "none"`   | Proceed normally. Store the result when done.                             |
+
+#### After Key Decisions or Solutions
+
+```bash
+python3 execution/memory_manager.py store \
+  --content "Description of what was decided/solved" \
+  --type decision \
+  --project <project-name> \
+  --tags relevant-tag1 relevant-tag2
 ```
 
-**Opt-out:** User says "don't use cache", "no cache", "skip memory", or "fresh"
+Memory types: `decision`, `code`, `error`, `technical`, `conversation`
+
+#### After Completing a Complex Task
 
-**Auto-stored memories:**
+```bash
+python3 execution/memory_manager.py cache-store \
+  --query "The original user question" \
+  --response "The complete response that was generated"
+```
 
-- `decision` — Architecture choices, design decisions
-- `code` — Script patterns, reusable implementations
-- `error` — Bug resolutions with root cause
-- `technical` — Documentation, API knowledge
+**Opt-out:** User says "don't use cache", "no cache", "skip memory", or "fresh"
 
-> See `directives/memory_integration.md` for full details.
+> See `directives/memory_integration.md` for full protocol and token savings reference.
 
 ### 2. Check for Existing Tools First