Valora.ai

🏛️ About VALORA

VALORA (Versatile Agent Logic for Orchestrated Response Architecture) is a next-generation TypeScript-based platform designed to orchestrate a sophisticated network of AI agents to automate the complete software development lifecycle. By moving beyond simple "code generation", VALORA manages the delicate interplay between requirements, architecture, and deployment. VALORA provides intelligent automation while maintaining human oversight.

Intelligent Orchestration: VALORA coordinates 11 specialised AI agents, from @lead technical oversight to @secops-engineer compliance, ensuring the right expert is assigned to every task.

Three-Tier Flexibility: The engine adapts to your resources, offering MCP Sampling, Guided Completion, or API Fallback modes.

Phased Governance: Every project follows a rigorous 8-phase lifecycle, moving from initialisation and planning through implementation to validation and PR creation.

Strategic Optimisation: To balance depth and speed, VALORA assigns specific LLMs (like GPT-5 for planning or Claude Haiku for validation) based on the task's complexity.

VALORA is not a replacement for the developer; it is the high-fidelity instrument through which the developer conducts a full symphony of AI agents.

✨ Features

🤖 Multi-Agent Collaboration

11 specialised AI agents with distinct expertise:

• @lead — Technical oversight & architecture
• @product-manager — Requirements & prioritisation
• @software-engineer-* — Implementation specialists
• @platform-engineer — Infrastructure & DevOps
• @qa — Testing & quality assurance
• @secops-engineer — Security & compliance
• @ui-ux-designer — Design & accessibility

⚡ Three-Tier Execution

Flexible execution modes for every use case:

*When available in Cursor **Requires a running local model server (e.g. Ollama)

Zero configuration required — works immediately with your Cursor subscription.

💎 Model Optimisation

Strategic AI model assignment for cost efficiency:

31% strategic • 31% execution • 38% fast

🔒 Security & Compliance

Enterprise-grade security controls:

• Credential Guard — Env var redaction, output scanning, sensitive file blocking
• Command Guard — Blocks exfiltration, network, eval, and remote access patterns
• Prompt Injection Detection — Risk-scored scanning of tool results with quarantine/redaction
• MCP Hardening — Tool definition validation, tool-set drift detection, approval workflows
• Supply Chain Hardening — Frozen lockfile, blocked install scripts, vulnerability overrides
• Audit Logging — Complete operation trail with security event tracking

🧩 Plugin System

Extend Valora with self-contained plugin directories:

Plugins are discovered from four locations (later takes precedence): data/plugins/ (built-in), ~/.valora/plugins/ (user), .valora/plugins/ (project), node_modules/@windagency/valora-plugin-* (npm). Install an official plugin with valora plugin add <name> and add its short name to plugins.enabled in .valora/config.json. No restart required. See Plugins guide.

To create a plugin — from a minimal data plugin to a full code plugin with LLM providers, memory backends, and CLI subcommands — see the Plugin Authoring Guide.

35 built-in compression strategies ship as three code plugins and are the canonical example of the code contribution type. See Strategies by plugin for the full list.

🔌 External MCP Integration

Connect to 15 external MCP servers with user approval:

🌳 Worktree Dashboard & Statistics

Live visibility into parallel explorations:

• Worktree Diagram Panel — Real-time tree view of git worktrees in the valora dash dashboard
• Exploration Status — Colour-coded branches with status icons (▶ running, ✓ completed, ✗ failed)
• Session-Exploration Linking — Explorations create linked sessions; the dashboard shows exploration details (task, worktrees, status) in the session details view
• Worktree Usage Stats — Per-session tracking of worktree creation, concurrency, and duration

┌─ Git Worktrees (3) ──────────┐
│ ● main  abc1234              │
│ ├── exploration/exp-abc-jwt  │
│ │   def5678  ▶ RUNNING       │
│ └── feature/new-api          │
│     ghi9012                  │
└──────────────────────────────┘

🚀 Quick Start

Prerequisites

• Node.js 18+

Installation

# Install globally
pnpm add -g @windagency/valora          # pnpm
yarn global add @windagency/valora      # yarn
npm install -g @windagency/valora       # npm

# Verify installation
valora --version
# Should output: 2.5.0

Project Setup

Initialise VALORA in your project:

cd your-project
valora init         # Minimal setup (.valora/config.json)
valora init --full  # Full setup with override directories

Your First Command

# Create an implementation plan
valora plan "Add user authentication with OAuth"

The engine will:

1. Select the appropriate agent (@lead)
2. Gather codebase context
3. Generate a detailed implementation plan
4. Provide step-by-step guidance

Zero-Config Usage with Cursor subscription

No API keys? No problem. The engine works immediately using Guided Completion Mode:

valora plan "Add dark mode toggle"
# → Generates structured prompt for Cursor AI
# → Uses your Cursor subscription (free)

Optional: API Configuration

For fully autonomous execution with cloud providers:

valora config setup --quick

# Or set environment variables
export ANTHROPIC_API_KEY=sk-ant-...
export OPENAI_API_KEY=sk-...

Optional: Local Models (No API Key)

Run fully offline with Ollama or any OpenAI-compatible server:

# Install and start Ollama
ollama pull llama3.1
ollama serve

# Use it directly
valora plan "Add auth" --provider local --model llama3.1

# Or configure as default
export LOCAL_BASE_URL=http://localhost:11434/v1
export LOCAL_DEFAULT_MODEL=llama3.1

🏗️ Architecture

┌─────────────────────────────────────────────────────────────────────────┐
│                                 VALORA                                  │
├─────────────────────────────────────────────────────────────────────────┤
│                                                                         │
│   ┌─────────────┐  ┌──────────────┐  ┌─────────────┐  ┌─────────────┐   │
│   │ CLI Layer   │  │ Orchestrator │  │ Agent Layer │  │ LLM Layer   │   │
│   │             │──│              │──│             │──│             │   │
│   │ • Commands  │  │ • Pipeline   │  │ • Registry  │  │ • Anthropic │   │
│   │ • Wizard    │  │ • Executor   │  │ • Selection │  │ • OpenAI    │   │
│   │ • Output    │  │ • Context    │  │ • Loading   │  │ • Google    │   │
│   │             │  │              │  │             │  │ • Local     │   │
│   └─────────────┘  └──────────────┘  └─────────────┘  └─────────────┘   │
│                                                                         │
│   ┌─────────────┐  ┌──────────────┐  ┌─────────────┐  ┌─────────────┐   │
│   │ Session     │  │ Config       │  │ MCP         │  │ Services    │   │
│   │             │  │              │  │             │  │             │   │
│   │ • State     │  │ • Loader     │  │ • Server    │  │ • Logging   │   │
│   │ • Context   │  │ • Schema     │  │ • Tools     │  │ • Cleanup   │   │
│   │ • History   │  │ • Providers  │  │ • Prompts   │  │ • Utils     │   │
│   └─────────────┘  └──────────────┘  └─────────────┘  └─────────────┘   │
│                                                                         │
└─────────────────────────────────────────────────────────────────────────┘

Key Design Principles

📋 Commands

Complete Command Reference

Command Categories

┌─────────────────────┐  ┌─────────────────────┐  ┌─────────────────────┐
│ Planning            │  │ Implementation      │  │ Delivery            │
├─────────────────────┤  ├─────────────────────┤  ├─────────────────────┤
│ • refine-specs      │  │ • implement         │  │ • commit            │
│ • create-prd        │  │ • assert            │  │ • create-pr         │
│ • plan              │  │ • test              │  │ • feedback          │
│ • review-plan       │  │ • review-code       │  │                     │
│ • gather-knowledge  │  │ • review-functional │  │                     │
└─────────────────────┘  └─────────────────────┘  └─────────────────────┘

📚 Documentation

Documentation Structure

documentation/
├── README.md                    # Documentation entry point
├── user-guide/                  # For users
│   ├── quick-start.md           # 5-minute getting started
│   ├── workflows.md             # Common patterns
│   └── commands.md              # Command reference
├── developer-guide/             # For developers
│   ├── setup.md                 # Development environment
│   ├── codebase.md              # Code structure
│   └── contributing.md          # How to contribute
├── architecture/                # For architects
│   ├── system-architecture.md   # C4 diagrams
│   ├── components.md            # Component design
│   └── data-flow.md             # Data flow patterns
└── adr/                         # Decision records
    ├── 001-multi-agent-architecture.md
    ├── ...
    ├── 008-pretooluse-cli-enforcement.md
    └── 009-supply-chain-hardening.md

🎯 Use Cases

New Feature Development

valora refine-specs "User authentication with OAuth"
valora create-prd
valora create-backlog
valora fetch-task && valora plan
valora implement
valora review-code && valora commit
valora create-pr

Bug Fix Workflow

valora plan "Fix: Login timeout issue"
valora implement
valora test --type=all
valora commit --scope=fix

Code Review

valora review-code --focus=security
valora review-functional --check-a11y=true

🔧 Project Structure

valora/                          # npm package root
├── bin/                         # CLI entry points
│   ├── valora.js                # Main CLI
│   └── mcp.js                   # MCP server
├── src/                         # TypeScript source
│   ├── ast/                     # AST-based code intelligence (tree-sitter parsing, symbol index)
│   ├── cli/                     # Command-line interface
│   ├── config/                  # Configuration management
│   ├── executor/                # Pipeline execution
│   ├── llm/                     # LLM provider integrations
│   ├── lsp/                     # LSP integration (language server protocol client)
│   ├── memory/                  # MemoryProvider registry + bootstrap glue (the bundled vault lives in packages/valora-plugin-memory-vault/; ADR-016 — replaceable via plugin)
│   ├── mcp/                     # MCP server implementation
│   ├── security/                # Agentic AI security (credential, command, injection guards)
│   ├── session/                 # Session management
│   │   └── worktree-stats-tracker.ts  # Worktree usage statistics
│   ├── ui/                      # Terminal UI (dashboard, panels)
│   ├── utils/                   # Utilities & path resolution
│   └── ...
├── data/                        # Built-in resources (shipped with package)
│   ├── agents/                  # Agent definitions (11 agents)
│   ├── commands/                # Command specifications (25 commands)
│   ├── prompts/                 # Structured prompts by phase
│   ├── templates/               # Document templates
│   ├── hooks/                   # Hook scripts
│   ├── config.default.json      # Default configuration
│   ├── hooks.default.json       # Default hooks config
│   └── external-mcp.default.json # External MCP server registry
├── dist/                        # Compiled output (gitignored)
├── __tests__/                   # Test suites
├── documentation/               # Comprehensive docs
└── package.json

Project-Level Overrides (.valora/)

When installed in a project, VALORA supports a .valora/ directory for local overrides:

.valora/                         # Project-specific configuration
├── config.json                  # Project settings (overrides defaults)
├── agents/                      # Custom/override agent definitions
├── commands/                    # Custom/override command specs
├── prompts/                     # Custom/override prompts
├── templates/                   # Custom/override templates
├── sessions/                    # Session state (gitignored)
├── logs/                        # Execution logs (gitignored)
├── index/                       # Codebase symbol index (gitignored)
├── memory/                      # Agent memory vault (gitignored — ADR-013; layout owned by the active memory plugin per ADR-016)
│   ├── version                  #   Vault schema version stamp
│   ├── meta.json                #   Last-written / last-consolidated timestamps
│   ├── episodic/<id>.md         #   7-day half-life events and observations
│   ├── semantic/<id>.md         #   30-day half-life patterns and insights
│   ├── decisions/<id>.md        #   21-day half-life architectural decisions
│   ├── embeddings.bin           #   Packed Float32Array of all embedding vectors
│   ├── embeddings.index.json    #   id → byte-offset index pinned to model + dim
│   └── _legacy/                 #   Archived JSON files from auto-migration
└── cache/                       # Cache data (gitignored)

Resources in .valora/ take precedence over built-in data/ resources.

🌟 Why VALORA?

Traditional Development

• ❌ Context switching between tools
• ❌ Manual documentation
• ❌ Inconsistent code reviews
• ❌ Repetitive commit messages
• ❌ Time-consuming PR creation

With AI Orchestration

• ✅ Unified workflow automation
• ✅ Auto-generated documentation
• ✅ Comprehensive AI-powered reviews
• ✅ Intelligent commit messages
• ✅ One-command PR creation

Innovation Highlights

🛠️ Technology Stack

🛡️ Compliance

Valora operates at the Limited Risk tier of the EU AI Act (Regulation (EU) 2024/1689).

Audit export: valora security audit-export --out audit.json

📄 Licence

MIT © Damien TIVELET