Valora.ai
VALORA (Versatile Agent Logic for Orchestrated Response Architecture) - The future of software development is not about replacing developers, but amplifying their capabilities with intelligent AI collaboration
Installation
npx valora-aiAsk AI about Valora.ai
Powered by Claude Β· Grounded in docs
I know everything about Valora.ai. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
VALORA
The future of software development is not about replacing developers, but amplifying their capabilities with intelligent AI collaboration.
Features β’ Quick Start β’ Architecture β’ Commands β’ Documentation
ποΈ 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.
Why VALORA?
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.
β¨ Features
π€ Multi-Agent Collaboration11 specialised AI agents with distinct expertise:
|
β‘ Three-Tier ExecutionFlexible execution modes for every use case:
*When available in Cursor **Requires a running local model server (e.g. Ollama) Zero configuration required β works immediately with your Cursor subscription. | |||||||||||||||
π Model OptimisationStrategic AI model assignment for cost efficiency:
31% strategic β’ 31% execution β’ 38% fast |
π Security & ComplianceEnterprise-grade security controls:
| |||||||||||||||
π³ Worktree Dashboard & StatisticsLive visibility into parallel explorations:
|
π External MCP IntegrationConnect to 15 external MCP servers with user approval:
|
π 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: 2.4.0
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:
- Select the appropriate agent (
@lead) - Gather codebase context
- Generate a detailed implementation plan
- 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"
# β Generates structured prompt for Cursor AI
# β 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
ποΈ Architecture
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β VALORA β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ€
β β
β βββββββββββββββ ββββββββββββββββ βββββββββββββββ βββββββββββββββ β
β β CLI Layer β β Orchestrator β β Agent Layer β β LLM Layer β β
β β ββββ ββββ ββββ β β
β β β’ Commands β β β’ Pipeline β β β’ Registry β β β’ Anthropic β β
β β β’ Wizard β β β’ Executor β β β’ Selection β β β’ OpenAI β β
β β β’ Output β β β’ Context β β β’ Loading β β β’ Google β β
β β β β β β β β β’ Local β β
β βββββββββββββββ ββββββββββββββββ βββββββββββββββ βββββββββββββββ β
β β
β βββββββββββββββ ββββββββββββββββ βββββββββββββββ βββββββββββββββ β
β β Session β β Config β β MCP β β Services β β
β β β β β β β β β β
β β β’ State β β β’ Loader β β β’ Server β β β’ Logging β β
β β β’ Context β β β’ Schema β β β’ Tools β β β’ Cleanup β β
β β β’ History β β β’ Providers β β β’ Prompts β β β’ Utils β β
β βββββββββββββββ ββββββββββββββββ βββββββββββββββ βββββββββββββββ β
β β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
Key Design Principles
| Principle | Implementation |
|---|---|
| Modularity | Loosely coupled components with clear interfaces |
| Extensibility | Plugin architecture for agents, commands, providers |
| Testability | Comprehensive test suites (unit, integration, e2e) |
| Observability | Structured logging and session tracking |
| Resilience | Graceful fallbacks and error recovery |
π Commands
Complete Command Reference
| Command | Agent | Description |
|---|---|---|
refine-specs | @product-manager | Collaboratively refine specifications |
create-prd | @product-manager | Generate Product Requirements Document |
create-backlog | @product-manager | Decompose PRD into tasks |
fetch-task | @product-manager | Retrieve next priority task |
refine-task | @product-manager | Clarify task requirements |
gather-knowledge | @lead | Analyse codebase context |
plan | @lead | Create implementation plan |
review-plan | @lead | Validate plan quality |
implement | Dynamic | Execute code changes |
assert | @asserter | Validate implementation |
test | @qa | Execute test suites |
review-code | @lead | Code quality review |
review-functional | @lead | Functional review |
commit | @lead | Create conventional commits |
create-pr | @lead | Generate pull request |
feedback | @product-manager | Capture outcomes |
consolidate | @lead | Consolidate and prune memory stores (experimental) |
Command Categories
βββββββββββββββββββββββ βββββββββββββββββββββββ βββββββββββββββββββββββ
β Planning β β Implementation β β Delivery β
βββββββββββββββββββββββ€ βββββββββββββββββββββββ€ βββββββββββββββββββββββ€
β β’ refine-specs β β β’ implement β β β’ commit β
β β’ create-prd β β β’ assert β β β’ create-pr β
β β’ plan β β β’ test β β β’ feedback β
β β’ review-plan β β β’ review-code β β β
β β’ gather-knowledge β β β’ review-functional β β β
βββββββββββββββββββββββ βββββββββββββββββββββββ βββββββββββββββββββββββ
π Documentation
π€ User GuideGetting started, workflows, |
π» Developer GuideArchitecture, codebase, |
ποΈ ArchitectureSystem design |
Documentation Structure
documentation/
βββ README.md # Documentation entry point
βββ user-guide/ # For users
β βββ quick-start.md # 5-minute getting started
β βββ workflows.md # Common patterns
β βββ commands.md # Command reference
βββ developer-guide/ # For developers
β βββ setup.md # Development environment
β βββ codebase.md # Code structure
β βββ contributing.md # How to contribute
βββ architecture/ # For architects
β βββ system-architecture.md # C4 diagrams
β βββ components.md # Component design
β βββ data-flow.md # Data flow patterns
βββ adr/ # Decision records
βββ 001-multi-agent-architecture.md
βββ ...
βββ 008-pretooluse-cli-enforcement.md
βββ 009-supply-chain-hardening.md
π― 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
π§ Project Structure
valora/ # npm package root
βββ bin/ # CLI entry points
β βββ valora.js # Main CLI
β βββ mcp.js # MCP server
βββ src/ # TypeScript source
β βββ ast/ # AST-based code intelligence (tree-sitter parsing, symbol index)
β βββ cli/ # Command-line interface
β βββ config/ # Configuration management
β βββ executor/ # Pipeline execution
β βββ llm/ # LLM provider integrations
β βββ lsp/ # LSP integration (language server protocol client)
β βββ memory/ # Biologically-inspired memory (exponential-decay stores)
β βββ mcp/ # MCP server implementation
β βββ security/ # Agentic AI security (credential, command, injection guards)
β βββ session/ # Session management
β β βββ worktree-stats-tracker.ts # Worktree usage statistics
β βββ ui/ # Terminal UI (dashboard, panels)
β βββ utils/ # Utilities & path resolution
β βββ ...
βββ data/ # Built-in resources (shipped with package)
β βββ agents/ # Agent definitions (11 agents)
β βββ commands/ # Command specifications (25 commands)
β βββ prompts/ # Structured prompts by phase
β βββ templates/ # Document templates
β βββ hooks/ # Hook scripts
β βββ config.default.json # Default configuration
β βββ hooks.default.json # Default hooks config
β βββ external-mcp.default.json # External MCP server registry
βββ dist/ # Compiled output (gitignored)
βββ tests/ # Test suites
βββ documentation/ # Comprehensive docs
βββ package.json
Project-Level Overrides (.valora/)
When installed in a project, VALORA supports a .valora/ directory for local overrides:
.valora/ # Project-specific configuration
βββ config.json # Project settings (overrides defaults)
βββ agents/ # Custom/override agent definitions
βββ commands/ # Custom/override command specs
βββ prompts/ # Custom/override prompts
βββ templates/ # Custom/override templates
βββ sessions/ # Session state (gitignored)
βββ logs/ # Execution logs (gitignored)
βββ index/ # Codebase symbol index (gitignored)
βββ memory/ # Agent memory stores (gitignored)
β βββ episodic.json # 7-day half-life events and observations
β βββ semantic.json # 30-day half-life patterns and insights
β βββ decisions.json # 21-day half-life architectural decisions
βββ cache/ # Cache data (gitignored)
Resources in .valora/ take precedence over built-in data/ resources.
π Why VALORA?
Traditional Development
|
With AI Orchestration
|
Innovation Highlights
| Innovation | Impact |
|---|---|
| Multi-Agent Orchestration | Specialised agents produce expert-level output |
| Three-Tier Execution | Flexibility from free to fully automated |
| Session Persistence | Context flows naturally between commands |
| Dynamic Agent Selection | Right expert for every task |
| Quality Gates | Multiple checkpoints prevent technical debt |
π οΈ Technology Stack
| Category | Technologies |
|---|---|
| Runtime | Node.js 18+, TypeScript 5.x |
| Package Manager | pnpm 10.x |
| Build | tsc, tsc-alias |
| Testing | Vitest, Playwright |
| LLM SDKs | @anthropic-ai/sdk, openai, @google/generative-ai |
| CLI UI | Ink (React), Chalk, Commander |
| Validation | Zod |
| Code Intelligence | web-tree-sitter |
| MCP | @modelcontextprotocol/sdk |
π Licence
MIT Β© Damien TIVELET
Get Started β’ Contribute β’ Learn More
