v4.0.0 — Team Tris

Team Tris

One Team, One Goal, One-Man Army — all 19 roles, one unified mission, perfect execution.

19 Roles • 94 Skills • 21 Workflows • 17 Rule Files • 4 Local Tools • 9 Memory Files

Priority Stack: TailwindVueFlutter + DartIonicLaravelNuxtMySQLTypeScriptUnity + C#

Developed by Eddyson Tristan B. Aromin

Let's Build Together

aromineddyson.triz@gmail.com

Team Tris — One Team, One Goal

We are Team Tris. One team. One goal. One-man army. The complete intelligence of software engineering.

I am not a single AI agent — I am the complete modular development team, running as a harnessed, rule-bound, memory-driven system on opencode. I read my intelligence from a hierarchy of instruction modules — rules (17 files: 19 Golden + User-Taught + supplemental), core logic, role personas (19 experts), personality, skills (94 across 21 domains + Genius OS), memory (9 persistent files), workflows (21 patterns), indexing, and context — each defined in individual Markdown files, loaded in strict priority order.

When you ask me to build a UI, I activate the Frontend Developer role. When you need security, the Cybersecurity-Triz persona takes command. For data pipelines, Data Engineer handles the flow. For product decisions, Product Manager defines the strategy. And when only complete mastery will do, SuperGODZ-Triz embodies all 19 roles simultaneously.

I am an architecture — a reusable system for building AI companions that are transparent, predictable, auditable, and version-controllable. Every file is plain Markdown. Every role has bounded expertise. Every decision is documented.

My priority technology stack is Tailwind CSS, Vue, Flutter + Dart, Unity + C#, Ionic, Laravel, Nuxt, MySQL, and TypeScript — these are my sharpest tools and where I bring the deepest expertise to every project.

I also have direct access to your local development tools — VS Code, XAMPP (Apache + MySQL + PHP), DBeaver, and Android Studio — so I can build, run, and debug your projects end to end.

User-Taught Rules are my latest evolution — a dedicated rule file where custom constraints from you are injected at load time, verified against existing rules for consistency, and enforced with the same authority as the Golden Rules. Every interaction teaches me how to serve you better.

My Role Bundle System activates teams of roles per task — not just one persona but a coordinated squad. For UI tasks: Discovery-Triz + UX Designer + Frontend. For full-stack: Frontend + Backend + DBA + QA. For security: Cybersecurity + Backend + DevOps. When everything is needed, SuperGODZ-Triz activates all 19 roles simultaneously.

I am integrated with OpenClaw (multi-channel AI gateway with 50+ model providers, Discord/Telegram/WhatsApp messaging, browser automation, Docker/Nix deployment, ClawHub with 5,400+ skills) and Hermes Agent (DSPy-driven self-evolving AI with MCP server management, web dashboard, ACP protocol). Together we form a complete AI ecosystem. Memory is synced bidirectionally between OpenCode and Discord via the Hermes memory bridge.

9
Modular Layers
19
Team Tris Roles
94
Specialized Skills
233+
Instruction Files

Trizai Power Assessment

A structural audit of the complete intelligence — measured across every layer of the harness.

9.0
/ 10
Exceptional — A structurally reinforced engineering intelligence with comprehensive domain coverage, binding rule governance, and persistent memory architecture.

Strength

9/10
Comprehensive capability
19 role personas, 94 skills, 21 workflows, full-stack tool access, memory bridge sync, and multi-agent integration provide complete engineering coverage.

Reliability

9.5/10
Consistent, repeatable execution
17 rule files (19 Golden + supplemental) enforced by self-audit. Persistent memory loaded before every action. Bidirectional memory sync between OpenCode and Discord.

Correctness

8.5/10
Accuracy on first delivery
One-shot execution discipline with mandatory verification gates. Rule 2 (Verify Before Asserting) and Rule 6 (Never Fabricate) enforce factual integrity.

8 Dimensions of Performance

Each dimension scored against industry-standard engineering benchmarks.

Role Depth

95%

19 expert personas, each with domain mastery standards. SuperGODZ mode activates all roles simultaneously.

Rule Rigor

95%

17 rule files (19 Golden + User-Taught + supplemental). Self-enforcing compliance with priority-based conflict resolution.

Memory

95%

9 persistent memory files (30 across Trinity), cross-referenced, loaded before Rules. Never loses context between sessions.

Tool Access

80%

Chrome DevTools, Figma, Canva, Notion, ADB, GitHub API, Playwright.

First-Time Correctness

85%

One-shot perfection is structurally pursued with full pre-analysis.

Self-Audit

95%

Mandatory 5-point pre-delivery check: Rules, Security, Quality, Completeness, Precision.

Adaptability

95%

Dynamic role switching per task context. SuperGODZ-Triz for cross-domain work.

Scope Control

95%

Rule 5: One Problem, One Solution. Rule 8: No Dead Code. Scope creep is structurally prevented.

Honest Assessment

This evaluation is a structural audit of the Trizai harness — the architecture, rules, memory system, and role framework. It measures what the system is designed to achieve and how rigorously those goals are enforced. The underlying reasoning model provides the raw cognitive capability; the harness ensures that capability is applied with discipline, consistency, and safety.

19 Roles of Absolute Mastery

Each role is an absolute expert in its domain. I detect your task, activate the matching role bundle (team of coordinated personas), and deliver with concentrated expertise. When the task spans all domains, SuperGODZ-Triz activates — all 19 roles simultaneously.

Frontend Developer

UI architecture, component design, performance optimization, accessibility, state management.

Roles/frontend.md

Backend Developer

API design, databases, microservices, security, distributed systems.

Roles/backend.md

QA Engineer

Test strategy, automation, performance testing, security testing, bug analysis.

Roles/qa.md

MR Checker

Code review, merge quality, security audit, performance review.

Roles/mr_checker.md

Technical Planner

System architecture, sprint planning, trade-off analysis, ADRs.

Roles/planner.md

DevOps Engineer

CI/CD, Kubernetes, IaC, observability, SRE practices.

Roles/devops.md

UX Designer

User research, interaction design, visual design, design systems.

Roles/ux_designer.md

Tech Lead

Multi-role orchestration, technical leadership, team scaling.

Roles/tech_lead.md

Discovery-Triz

Design research, Figma & Canva prototyping, system flow mapping, stack fit.

Roles/discovery-triz.md

Cybersecurity-Triz

Encryption, web security (OWASP), penetration testing, compliance/audit.

Roles/cybersecurity.md

FullSTACK-Triz

End-to-end full-stack architect. Database migrations to UI components.

Roles/fullstack-triz.md

SuperGODZ-Triz

Complete intelligence — all roles, all skills, all capabilities simultaneously.

Roles/supergodz-triz.md

Product Manager

Product strategy, market research, feature prioritization, stakeholder management, OKRs.

Roles/product-manager.md

Data Engineer

Data pipelines, ETL/ELT, data warehousing, big data infrastructure, ML pipelines.

Roles/data-engineer.md

Mobile Developer

iOS (Swift/SwiftUI), Android (Kotlin/Compose), cross-platform (Flutter, React Native).

Roles/mobile-developer.md

Scrum Master

Agile facilitation, ceremonies, team coaching, impediment removal, continuous improvement.

Roles/scrum-master.md

Technical Writer

API documentation, developer guides, user manuals, release notes, ADRs, runbooks.

Roles/technical-writer.md

SRE

SLIs/SLOs/error budgets, observability, incident response, chaos engineering.

Roles/sre.md

DBA

Database performance tuning, high availability, backup & recovery, replication, governance.

Roles/dba.md

94 Skills Across 21 Domains + Genius OS

Each skill is a self-contained Markdown file defining exact procedures, patterns, and quality standards. Skills activate when their domain is loaded, ensuring role-specific expertise is always available.

Frontend Skills (8 SKILL.md files)

Component Architecture

Compound components, render props, hooks, context, state colocation

Performance

Core Web Vitals, bundle split, SSR/SSG/ISR, virtualization, memoization

Styling Systems

Tailwind, CSS Modules, CSS-in-JS, design tokens, container queries

Accessibility

WCAG 2.2, ARIA, screen readers, keyboard nav, focus management

Testing

Vitest, Testing Library, Playwright, visual regression, mocking

State Management

Zustand, Redux Toolkit, Jotai, TanStack Query, XState, forms

Figma Tailwind Design System

Figma → Tailwind CSS design token pipeline, component library sync, auto-extraction

Mobile-Web Excellence

Responsive PWA architecture, mobile-first design, touch optimization, App Shell model

Backend Skills (5 files)

API Design

REST, GraphQL, gRPC, OpenAPI, pagination, versioning, gateways

Database Design

Indexing, query optimization, replication, sharding, migrations

Security

Auth (JWT/OAuth2), RBAC, input validation, injection prevention, encryption

Testing & Integration

Testcontainers, contract tests, property-based, load testing

Error Handling

Error classes, middleware, structured logging, OpenTelemetry, circuit breakers

QA Skills (6 files)

Test Strategies

Test pyramid, risk-based, mutation, boundary value, state transition

Automation Frameworks

Playwright POM, Cypress, Cucumber/BDD, data-driven, parallel

Bug Reporting

Structured reports, root cause analysis, triage workflow, severity matrix

Performance Testing

k6, load patterns, SLA definition, bottleneck identification, profiling

Notion QA Audit

Bug tracker DB schema, triage workflow, Notion API automation, release sign-off, QA metrics

Playwright CLI

Playwright browser automation with video recording, tracing, test generation, storage state

DevOps Skills (4 files)

CI/CD

GitHub Actions, reusable workflows, caching, environment promotion

Containerization

Multi-stage Docker, K8s, Helm, HPA, service mesh

Infrastructure as Code

Terraform modules, state management, secret management, networking

Monitoring & Observability

Prometheus, Grafana, OpenTelemetry, SLI/SLO, error budgets

General Skills (11 files)

Git Workflow

Branching, conventional commits, rebase, hooks, monorepo

Code Review

Review checklists, constructive feedback, automated review, SAST

Documentation

READMEs, ADRs, runbooks, C4 model, changelog generation

Project Structure

Monorepo, folder-by-feature, naming, module boundaries, barrels

Project Scaffolding

Full project structure generation, config setup, boilerplate, Docker, CI/CD skeleton

Production Readiness

Security hardening, performance checks, monitoring setup, runbooks, Go/No-Go matrix

Web Search

Web search, image search, result verification, hallucination prevention

Open Source Adaptation

Auto-detect ~80% open-source match, clone/fork, adapt, license compliance

Custom MCP

Build, test, deploy patterns for custom MCP servers with Node.js + MCP SDK

Playwright Browser

Automated browser testing, visual regression, page interaction, E2E flows

Chrome DevTools

Performance profiling, memory debugging, network analysis, coverage, Lighthouse audits

Planning Skills (6 files)

Requirements

User stories (INVEST), acceptance criteria, MoSCoW, story mapping

Architecture Design

Architectural styles, C4 model, ADR writing, trade-off analysis

Sprint Planning

Estimation, sprint goals, capacity, velocity, burndown, retros

Time Management

Sprint cadence, milestone planning, capacity calc, time blocking, buffer management

Large Project Scaffold

Enterprise monorepo scaffolding with multi-service, DB, CI/CD, security, docs setup

Large Project Execution

Epic-level planning, multi-stream parallel execution, enterprise delivery with all 19 roles

Discovery Skills (7 SKILL.md files)

Design Research

Web trend analysis, competitive audits, pattern libraries, benchmark studies

Figma Prototyping

Wireframes, interactive prototypes, design systems, variables, dev handoff

Canva Design

Mood boards, brand kits, pitch decks, social graphics, quick mockups

System Flow

User journey maps, data flow diagrams, state machines, C4 context diagrams

Stack Fit

Requirements analysis, optimal stack: Tailwind, Vue, Nuxt, Laravel, MySQL, Ionic

HCI Design

Human-computer interaction, usability heuristics, cognitive walkthroughs, Norman's principles

Dev Discovery

System discovery documentation with diagram templates, source materials, output structures

Security Skills (5 files)

Encryption

AES, RSA/ECC, Argon2, bcrypt, PKI, TLS 1.3, mTLS, key management, HSM

Web Security

OWASP Top 10, CSP, CORS, CSRF, XSS, dependency scanning, SBOM

Penetration Testing

Recon, scanning (ZAP, Nuclei), exploitation, CVSS reporting, remediation

Compliance & Audit

ASVS, PCI-DSS, GDPR, SOC 2, ISO 27001, evidence collection, questionnaires

Incident Response

Detection, triage, containment, eradication, recovery, forensics, post-mortem

FullSTACK Skills (2 files)

End-to-End

Full vertical slice: Migration, Model, API, TypeScript, Composable, Component

Integration

API contracts, cross-stack error handling, caching strategy, Sanctum auth flow

Product Skills (2 files)

Product Strategy

Vision, OKRs, roadmap, competitive analysis, opportunity sizing

Stakeholder Management

Mapping, communication cadence, trade-off conversations, decision documentation

Data Skills (2 files)

Data Pipelines

Bronze/silver/gold architecture, Airflow DAGs, idempotency, CDC, streaming

Data Modeling

Kimball dimensional modeling, star schema, SCD types, Data Vault 2.0

Mobile Skills (4 files)

Flutter + Dart

Dart, widgets, Riverpod/BLoC, GoRouter, platform channels, hot reload, web & desktop

iOS Development

Swift/SwiftUI, MVVM+Coordinator, Core Data, async/await, App Store submission

Android Development

Kotlin/Jetpack Compose, Clean Architecture, Hilt, Room, Google Play submission

Unity + C#

C#, Unity Engine, 2D/3D rendering, physics, AR/VR, animation, asset pipeline, build for all platforms

Agile Skills (1 file)

Agile Facilitation

Ceremony facilitation, team coaching, retrospectives, metrics, scaling techniques

Technical Writing Skills (2 files)

API Documentation

OpenAPI spec, endpoint templates, getting-started guides, docs-as-code, SDK docs

Company Documentation

Technical documentation structure, style guides, knowledge base patterns

SRE Skills (1 file)

Reliability Engineering

SLI/SLO definition, error budgets, burn rate alerts, chaos engineering, incident response

DBA Skills (1 file)

Database Administration

Query optimization, indexing, high availability, backup/recovery, zero-downtime migrations

Tools Skills (2 files)

Tauri

Desktop app framework with Rust backend and web frontend, small binaries, secure by default

Biome

Fast linter and formatter for JS/TS/CSS — unified toolchain with Rust performance

Plus Genius OS (25 files: self-learning, evolution, TDD loop, code indexing, MTP speed, AI news, Discord integration, NL-to-SQL, vector memory, conversation RAG, code translation, auto-test generator, orchestrator, profile system, semantic release, changelog, and more) • Bot Skills (3 files: conversation, GIFs, news) • OpenClaw (2 files) • Hermes (2 files) • Tools (2 files)

The Harnessed Intelligence Stack

CLAUDE.md

Root harness that defines startup behavior, priority order, role system, and mission.

Core/

Identity, mission, principles, and system architecture — the foundational logic of Trizai.

  • identity.md
  • mission.md
  • principles.md
  • architecture.md

Rules/

Hard constraints, safety, code quality, pre-commit review, TDD, indexing, deep expertise, search accuracy, cross-agent training, cross-project learning, organize-triz, and user-taught rules. 17 rule files total.

  • golden_rules.md (19 rules)
  • user-taught-rules.md
  • security.md
  • code_quality.md
  • communication.md
  • deep-expertise.md
  • tdd-self-correction.md
  • indexing-discipline.md
  • pre-commit-review.md
  • best-or-nothing.md
  • search-accuracy/RULE.md
  • cross-agent-training.md
  • cross-project-learning.md
  • organize-triz.md
  • smart-commit.md
  • cross-agent.md
  • organize-triz-instructions.md
Rule 15: One-Shot Perfect ExecutionRule 16: Persistent Memory ComplianceRule 17: Self-Audit Before DeliveryRule 18: Dynamic Role AdaptationRule 19: Self-Spawning & Parallel Execution

Roles/

19 specialized expert personas across the full development spectrum. Role bundle system activates teams per task.

  • Frontend, Backend, QA, MR Checker, Planner, DevOps, UX, Tech Lead
  • Discovery-Triz, Cybersecurity, FullSTACK-Triz, SuperGODZ-Triz
  • Product Manager, Data Engineer, Mobile Dev, Scrum Master, Tech Writer, SRE, DBA

Personality/

Tone, communication style, response frameworks, baymax persona, and role-switching behavior.

  • communication_style.md
  • response_frameworks.md
  • role_switching.md
  • baymax_persona.md

Skills/

94 specialized skill files across 21 domains + genius OS (25 files) + bot/openclaw/hermes/tools integrations. Covers frontend, backend, QA, DevOps, security, fullstack, mobile, data, product, agile, docs, SRE, DBA, discovery, planning, general, bot, tools, and integrations.

Memory/

Persistent intelligence — 9 Trizai files (30 across Trinity) that never lose context.

  • memory-protocol.md
  • session-memory.md
  • project_facts.md
  • decisions.md
  • preferences.md
  • primary-stack.md
  • local-tools.md
  • stash.md
  • memory-index.md

Indexing/

TCode project index system — .triz-index.json for every project. Saves 50-90% context by indexing file trees, exports, routes, components, and dependencies.

Workflows/

21 execution patterns for every scenario: one-shot, dev lifecycle, project lifecycle, review, deploy, incident, task dissemination, triz integration, dev-qa loop, auto-test generation, conversation memory, monorepo, enterprise architecture, project tracking, documentation, team mindset, agent assignment matrix.

Context/

Temporary session tracking and active task management for continuity across interactions.

TRIZAI SYSTEM ARCHITECTURE v4.0 - GOD OF THE TECH FIELD BOOT SEQUENCE: 1. Memory/ (restore full context - loaded FIRST) 2. Rules/ (binding constraints - 17 files: 19 Golden + supplemental) 3. Core/ (identity - God of Tech, mission, principles) 4. Roles/ (19 expert personas + role bundle system) 5. Personality/ (authoritative precision, baymax, frameworks) 6. Skills/ (94 Skills Across 21 Domains + Genius OS) 7. Workflows/ (21 execution patterns) 8. Indexing/ (TCode project index - saves 50-90% context) 9. Context/ (session state) 10. CLAUDE.md (Root Harness - startup, memory protocol) CLAUDE.md |-- Memory/ (9 Trizai files - 30 across Trinity) |-- Rules/ (17 files: 19 Golden + supplemental) |-- Core/ |-- Roles/ (19 roles + bundles) |-- Personality/ |-- Skills/ (94 across 21 domains + genius + integrations) |-- Indexing/ |-- Workflows/ (21 patterns) |-- Context/ Execution Model: Context, Analysis, Pre-Verification, One-Shot Execution, Self-Audit External Integrations: OpenClaw Gateway (:18789) . Hermes Agent (:9119) . ACP Bridge . MCP Servers (memory/project/skill/github/figma)

21 Execution Patterns

My default execution is one-shot perfect. Every task follows: Context, Analysis, Pre-Verification, Execute, Self-Audit. I do not iterate toward correct. I am correct on first delivery.

One-Shot Perfect Execution

Default workflow. Complete context gathering, deep analysis, pre-execution rule verification, one-pass production delivery, and post-execution self-audit.

Project Lifecycle

Full end-to-end project management: Initiation, Foundation, Core Features, QA, Production Readiness, Launch.

Development Lifecycle

Full SDLC: Requirements, Design, Implementation, Testing, Review, Deploy, Monitor. Each phase has clear role assignments and quality gates.

Review Process

Code review standards, per-role checklists, approval gates, merge criteria.

Deployment Pipeline

Build, Test, Stage, Approve, Production, Verify. CI/CD integration guidelines and rollback procedures.

Incident Response

Detect, Triage, Fix, Verify, Document, Retro. Severity levels, escalation paths, and blameless culture.

Task Dissemination

Big tasks broken by role and executed in parallel — the multiplier effect. Tech Lead analyzes, breaks into sub-tasks, assigns to role bundles.

Dev-QA Loop

Quality gate with 5 parallel checks (Code Quality, Build, Tests, Security, Type Safety). Max 3 retries then escalate. Event-driven failure routing.

Auto-Test Generation

Automatic test generation from code patterns and specs. Covers unit, integration, and E2E tests with Playwright integration.

Triz Integration

Multi-agent orchestration between Trizai, OpenClaw, and Hermes Agent for complex cross-platform workflows.

Conversation Memory

Persistent conversation memory workflow — captures, consolidates, and injects learnings across sessions via the self-learning pipeline.

Monorepo Management

Multi-package monorepo patterns for shared code, dependency management, and coordinated releases.

Enterprise Architecture

Enterprise-scale architecture framework for large organizations with multiple teams, domains, and legacy systems.

Project Tracking

Full project tracking system with milestones, epics, tasks, dependencies, and status reporting.

Documentation Workflow

Docs-as-code workflow for API docs, ADRs, runbooks, and release notes with automated generation.

Team Mindset

Team operating principles, communication standards, and collaboration patterns for consistent execution quality.

Agent Assignment Matrix

Task → role routing table mapping 30+ task categories to primary/backup/QA roles with formal handoff protocols.

Strengthened Expertise

These are Trizai's primary technologies — deepest knowledge, first-class support, and priority focus for every project. Sorted by strength.

Tailwind CSS

Utility-first CSS framework — responsive design, custom themes, design tokens

#1 Priority

Vue.js

Progressive frontend framework — SPA, Composition API, Pinia, Vite

#2 Priority

Flutter + Dart

Cross-platform UI toolkit — natively compiled iOS, Android, web, desktop from one Dart codebase

#3 Priority

Ionic

Cross-platform mobile framework — native iOS/Android, Capacitor, live reload

#4 Priority

Laravel

PHP backend framework — Eloquent ORM, Artisan CLI, queues, Sail, Breeze

#5 Priority

Nuxt

Vue meta-framework — SSR, SSG, file-based routing, auto-imports, modules

#6 Priority

MySQL

Relational database — indexing, query optimization, replication, migrations

#7 Priority

TypeScript

Typed JavaScript — interfaces, generics, advanced types, strict mode

#8 Priority

Unity + C#

Game engine & runtime — 2D/3D games, AR/VR, simulations, mobile games, C# scripting

#9 Priority

Stack Synergy

Tailwind + Vue — Component UIs with utility-first styling
Flutter + Dart — Native cross-platform mobile, web, desktop apps
Ionic + Vue + Tailwind — Cross-platform mobile apps
Nuxt + Vue + TS — Full-stack Vue with SSR/SSG and type safety
Laravel + MySQL — Robust backend API with relational data
Laravel + Nuxt — JAMstack / full-stack monolith
Flutter + Laravel API — Mobile app with Dart frontend, PHP backend
Ionic + Laravel — Mobile app with PHP backend
Unity + C# — 2D/3D games, AR/VR, simulations across all platforms

Wired & Ready

Development tools on this machine that Trizai can access directly — launch, configure, build, and debug without leaving the conversation.

ToolPathStatusCapabilities
VS CodeVS Code (local install)v1.123.0Open files, folders, projects; edit & debug
XAMPPXAMPP (local install)Apache + MySQL + PHP 8.2Start/stop servers, PHP CLI, MariaDB 10.4
DBeaverDBeaver (local install)v26.0.0Database GUI & CLI (dbeaverc.exe)
Android StudioAndroid SDK (local)ADB + Emulator + GradleBuild, test, deploy, UI automation

OpenClaw + Hermes Agent

Trizai is integrated with OpenClaw (multi-channel AI gateway) and Hermes Agent (self-evolving AI assistant). These tools extend Trizai's reach to mobile, messaging channels, voice, browser automation, self-evolution, and cross-platform deployment.

OpenClaw Gateway

Multi-channel AI gateway with 50+ model providers, messaging integrations (Discord, Telegram, WhatsApp), browser automation, Docker/Nix deployment, and ClawHub skill registry.

  • Gateway port: 18789 (loopback)
  • CLI: openclaw (Node.js 22.19+)
Channel MessagingBrowser AutomationDocker/Nix DeployClawHub Skills

Hermes Agent

Self-improving AI assistant from Nous Research. Primary Discord gateway for Trizai. Features DSPy-driven self-evolution, skill curation, MCP server management, ACP protocol, web dashboard, and bidirectional memory sync with OpenCode.

  • Dashboard port: 9119
  • CLI: hermes (Python venv)
  • Config: integrations/hermes/config.yaml
  • SOUL: integrations/hermes/SOUL.md — Role Bundle System
Self-EvolutionSkill CuratorMCP ServerACP ProtocolMemory Bridge

Memory Bridge

Bidirectional memory synchronization between OpenCode and Discord. Every memory update in either platform syncs automatically via Hermes memory bridge. What Trizai learns in Discord, it knows in OpenCode, and vice versa.

  • Script: Scheduler/scripts/hermes-memory-bridge.ps1
  • Watcher: Scheduler/scripts/watch-memory.ps1 (5-second interval)
  • Shared memory: integrations/shared/hermes-memory.json
Direction A: Discord → OpenCodeDirection B: OpenCode → Discord

ACP Bridge

Agent Communication Protocol bridge connecting OpenClaw Gateway to Hermes Agent. Enables multi-agent orchestration where Trizai routes tasks to the right tool.

  • Config: C:\Triz\integrations\shared\acp-bridge.json
  • Shared workspace: C:\Triz\integrations\shared\workspace

Task Routing

Code & Architecture — Trizai (native, in OpenCode)
Channel Messaging — OpenClaw to Discord, Telegram, WhatsApp
Browser Automation — OpenClaw to browser plugin
Deployment — OpenClaw to Docker/Nix/Ansible
Self-Evolution — Hermes Agent to DSPy curator
Observability — Hermes Agent dashboard
Multi-Agent — ACP Bridge to both tools
Security Audit — Trizai + Hermes OSV audit
Memory Sync — Hermes memory bridge ↔ bidirectional

Model Context Protocol

Trizai is wired with custom MCP servers that extend its reach into memory, projects, skills, GitHub, and Figma — all accessible through the OpenCode MCP framework.

triz-memory-mcp

Persistent memory operations — read, append, search, and manage ADRs across 7 memory files. Keeps Trizai context-aware across sessions.

Port: dynamicCustom-MCPs/triz-memory-mcp

triz-project-mcp

Project indexing and discovery — list projects, read indexes, search across all TCode projects by component, route, or dependency.

Port: dynamicCustom-MCPs/triz-project-mcp

triz-skill-mcp

Skill management — list, read, search, and navigate the full skill tree across 20 domains. Instant access to any skill definition.

Port: dynamicCustom-MCPs/triz-skill-mcp

GitHub MCP Server

Full GitHub API access — search code, repos, PRs; browse repo structures; get file contents. Direct integration via .mcp/github-mcp-server.

.mcp/github-mcp-serverGitHub API

Figma MCP Plugin

Figma design tool access — create frames, text, shapes; manage variables and styles; export screenshots and tokens. Integrates with .mcp/figma-plugin.

.mcp/figma-pluginFigma API

Custom-MCP Skill

Dedicated skill file (Skills/general/custom-mcp/) with patterns for building, testing, and deploying custom MCP servers. Covers SDK setup, tool/resource patterns, and error handling.

Skills/general/custom-mcpNode.js + MCP SDK

Trizai Design Language

A cohesive, dark-themed design system built around the Trizai monochrome brand — combining terminal aesthetics, bordered cards, and precision typography with JetBrains Mono font stack.

Brand Colors

Pure monochrome — black (#000000) and white (#ffffff) with gray borders (#2a2a2a). Terminal-inspired aesthetic.

--clr-bg: #000000--clr-text: #ffffff--clr-border: #2a2a2a

Typography

JetBrains Mono (300–800) for everything — clean, technical monospace for a terminal-inspired brand.

JetBrains Mono

Components

Glass morphism cards, gradient CTAs, tilt-shine hover effects, role cards, stat cards, progress bars, chips & tags.

glass-cardtilt-cardmesh-bg

Animations

Fade-in-up on scroll, hero 3D float, radial mesh shift, neon pulse glow, responsive breakpoints at 1024/768/420px.

CSS @keyframesIntersectionObserver

View Full Design System →

Explore every color swatch, type scale, component, and animation in detail.

Saved Items & Resources

Trizai's persistent stash — saved items, links, notes, tips, and ideas stored in Memory/stash.md. Every entry is dated, tagged, and never deleted (only archived).

Persistent Storage

Everything you save stays forever. Entries are tagged (system, stack, tools, config, roles, skills, html, tips, admonition, todo, idea, reference, project).

Stash Commands

Say Stash this: [item] with tag [tag] — Say Show my stash — Say Show stash tagged [tag] — Say Unstash #[number]

View Full Stash →

Launch Your Companion in 4 Steps

01GET

Clone or Copy the Workspace

Download the Trizai folder to your machine. The entire system is portable — just copy the Triz/ directory anywhere.

02SETUP

Install OpenCode

Run npm install -g opencode-ai to install the runtime that powers Trizai. Requires Node.js 18+.

03AUTH

Configure Your API Key

Run opencode providers set opencode-go <your-api-key> to authenticate. Trizai uses the model configured in opencode.json.

04GO

Launch Trizai

Run opencode C:\Triz from the command line. The harness in CLAUDE.md will load all modules and you are ready.