gpt-all-star

Coordinates a specialized team of 7 autonomous AI agents (Product Owner, Engineer, Architect, Designer, QA Engineer, Project Manager, Copilot) through a centralized Project class that manages execution flow, agent initialization, and inter-agent communication. Each agent has a defined role, system prompt, and expertise profile. The system uses LangGraph/LangChain for agent state management and chains agent outputs sequentially through development phases, with the Copilot agent serving as the user-facing interface that gathers requirements and provides updates throughout the process.

Executes application development through a predefined sequence of steps organized into phases: Specification (requirements gathering, architecture design), Development (backend/frontend implementation, UI design), and Execution/Healing (testing, bug fixing, deployment). Each step is a discrete unit of work with inputs, outputs, and success criteria. The system tracks step completion state, manages dependencies between steps, and allows agents to execute healing steps when initial implementation fails quality checks or tests.

The Project Manager agent coordinates tasks across the agent team, manages dependencies between development phases, tracks progress, identifies blockers, and ensures smooth handoffs between agents. Maintains project state, schedules agent execution, and coordinates communication between specialized agents. Ensures that outputs from one agent are properly formatted and available for the next agent in the workflow.

The Product Owner agent gathers requirements, defines product specifications, creates user stories, and documents acceptance criteria. Translates user intent into structured requirements that guide architecture and implementation. Conducts requirement elicitation through questions, clarifies ambiguities, and produces specification documents that serve as the source of truth for the development team.

Abstracts LLM interactions through a unified interface (gpt_all_star/core/llm.py) that supports multiple providers (OpenAI, Anthropic, Ollama, etc.) with configurable model selection via environment variables. Tracks token usage across all LLM calls for cost monitoring and billing. Implements provider-specific configuration (API keys, model names, temperature, max_tokens) and handles provider-specific response formats, enabling easy switching between GPT-4, GPT-4o, Claude, or local models without code changes.

Manages project files and generated artifacts through a hierarchical storage system with dedicated directories for different artifact types: Root Storage (main project), Docs Storage (specifications and documentation), App Storage (generated application code), and component-specific folders. Implements file I/O operations for reading/writing code, specifications, designs, and test files. Provides a unified interface for agents to access and modify project artifacts without direct filesystem manipulation, enabling version tracking and artifact organization.

Implements a dedicated Copilot agent that serves as the primary user-facing interface, asking clarifying questions about requirements, providing progress updates, gathering user feedback on generated outputs, and iterating based on user input. The Copilot uses natural language interaction to understand user intent, translates user feedback into actionable requirements for other agents, and maintains conversational context throughout the development process. Acts as a bridge between non-technical users and the specialized technical agents.

Defines specialized agent roles (Product Owner, Engineer, Architect, Designer, QA Engineer, Project Manager) with distinct system prompts, expertise areas, and default names/personas. Each agent has a profile that includes its color code, default model selection, and specialized capabilities. Agents can be customized with different prompts, models, or expertise areas via configuration. The system uses role-based routing to direct tasks to appropriate agents based on the type of work (e.g., architecture decisions to Architect, implementation to Engineer).

Generates complete web applications using React for frontend, JavaScript/Node.js for backend, and Chakra UI for component library and styling. The Engineer agent specializes in implementing code using these specific technologies, generating production-ready components, API endpoints, and styling. Supports full-stack development from database schema to UI components, with built-in knowledge of React patterns, hooks, component composition, and Chakra UI theming.

Implements a QA Engineer agent that generates and executes test suites, validates generated code against requirements, and identifies bugs or quality issues. When tests fail or quality checks detect problems, the system triggers healing steps where the Engineer agent re-implements or fixes the problematic code. The healing loop continues until tests pass or quality thresholds are met. Supports unit tests, integration tests, and specification validation.

The Architect agent generates system architecture, technology stack recommendations, database schema design, API structure, and deployment architecture. Analyzes requirements to make informed decisions about frameworks, databases, deployment platforms, and scalability considerations. Produces architecture documentation, technology rationale, and technical specifications that guide the Engineer's implementation. Considers factors like performance, scalability, maintainability, and cost in architecture decisions.

The Designer agent generates UI/UX designs, component specifications, layout designs, and visual design guidelines. Produces design artifacts that guide the Engineer's implementation of frontend components. Considers user experience, accessibility, responsive design, and visual consistency. Generates component libraries, design tokens, and styling specifications that ensure visual coherence across the application.