Enterprise-Grade Agentic Framework - Modular skill-based AI assistant toolkit with deterministic execution, semantic memory, and platform-adaptive orchestration.
npm install @techwavedev/agi-agent-kitEnterprise-Grade Agentic Framework & Scaffolding Tool


@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 ā Orchestration ā Execution) that forces agents to use tested scripts rather than hallucinating code.
v1.2.2 ā Now with platform-adaptive orchestration and integrated semantic memory across Claude Code, Kiro IDE, Gemini, and Opencode.
---
Scaffold a new agent workspace in seconds:
``bash`
npx @techwavedev/agi-agent-kit init
You'll be prompted to choose a pack:
- core - Essential skills (webcrawler, pdf-reader, qdrant-memory, documentation)
- 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 ā auto-fixing any issues.
---
| 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 ā 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 |
---
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 |@agent
| Opencode | Sequential personas via | Skills, MCP servers, providers |
Run /setup to auto-detect and configure your platform, or use the setup script directly:
`bashInteractive (one Y/n question)
python3 skills/plugin-discovery/scripts/platform_setup.py --project-dir .
---
š¦ What You Get
`
your-project/
āāā AGENTS.md # Master instruction file (symlinked to GEMINI.md, CLAUDE.md)
āāā skills/ # 56 pre-built tools
ā āāā webcrawler/ # Documentation harvesting
ā āāā pdf-reader/ # PDF text extraction
ā āāā qdrant-memory/ # Semantic caching & memory
ā āāā documentation/ # Auto-documentation maintenance
ā āāā plugin-discovery/ # Platform detection & setup wizard
ā āāā parallel-agents/ # Multi-agent orchestration
ā āāā intelligent-routing/ # Smart agent selection & routing
ā āāā self-update/ # Framework self-update capability
ā āāā ... # 48 more specialized skills
āāā directives/ # SOPs in Markdown
ā āāā memory_integration.md # Memory protocol reference
āāā execution/ # Deterministic Python scripts
ā āāā session_boot.py # Session startup (Qdrant + Ollama check)
ā āāā session_init.py # Collection initializer
ā āāā memory_manager.py # Store/retrieve/cache operations
āāā skill-creator/ # Tools to create new skills
āāā .agent/ # (full pack) Agents, workflows, rules
āāā workflows/ # /setup, /deploy, /test, /debug, etc.
`---
š Architecture
The system operates on three layers:
`
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā Layer 1: DIRECTIVES (Intent) ā
ā āā SOPs written in Markdown (directives/) ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¤
ā Layer 2: ORCHESTRATION (Agent) ā
ā āā LLM reads directive, decides which tool to call ā
ā āā Platform-adaptive: Teams, Subagents, or Personas ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¤
ā Layer 3: EXECUTION (Code) ā
ā āā Pure Python scripts (execution/) do the actual work ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
`Why? LLMs are probabilistic. 90% accuracy per step = 59% success over 5 steps. By pushing complexity into deterministic scripts, we achieve reliable execution.
---
š§ 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% |
`bash
Start Qdrant
docker run -d -p 6333:6333 -v qdrant_storage:/qdrant/storage qdrant/qdrantStart Ollama + pull embedding model
ollama serve &
ollama pull nomic-embed-textBoot 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 decisionHealth check
python3 execution/memory_manager.py health
`---
ā” Prerequisites
The
npx init command automatically creates a .venv and installs all dependencies. Just activate it:`bash
source .venv/bin/activate # macOS/Linux
.venv\Scripts\activate # Windows
`If you need to reinstall or update dependencies:
`bash
.venv/bin/pip install -r requirements.txt
`---
š§ Commands
$3
`bash
npx @techwavedev/agi-agent-kit init --pack=full
`$3
`bash
python3 skills/plugin-discovery/scripts/platform_setup.py --project-dir .
`$3
`bash
npx @techwavedev/agi-agent-kit@latest init --pack=full
or use the built-in skill:
python3 skills/self-update/scripts/update_kit.py
`$3
`bash
python3 execution/session_boot.py --auto-fix
`$3
`bash
python3 execution/system_checkup.py --verbose
`$3
`bash
python3 skill-creator/scripts/init_skill.py my-skill --path skills/
`$3
`bash
python3 skill-creator/scripts/update_catalog.py --skills-dir skills/
`---
šÆ Activation Reference
Use these keywords, commands, and phrases to trigger specific capabilities:
$3
| 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 |$3
| 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 |$3
| 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 |$3
| 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` |---
- AGENTS.md - Complete architecture and operating principles
- skills/SKILLS_CATALOG.md - All 56 available skills
- CHANGELOG.md - Version history
---
This package includes a pre-flight security scanner that checks for private terms before publishing. All templates are sanitized for public use.
---
Apache-2.0 Ā© Elton Machado@TechWaveDev