Interactive TUI to orchestrate AI agents. Give it a PRD, get back architecture, test plan, security assessment, and working code.
██████╗ █████╗ ██████╗ ███████╗███╗ ██╗████████╗ ██╔══██╗██╔══██╗██╔════╝ ██╔════╝████╗ ██║╚══██╔══╝ ██████╔╝███████║██║ ███╗█████╗ ██╔██╗ ██║ ██║ ██╔═══╝ ██╔══██║██║ ██║██╔══╝ ██║╚██╗██║ ██║ ██║ ██║ ██║╚██████╔╝███████╗██║ ╚████║ ██║ ╚═╝ ╚═╝ ╚═╝ ╚═════╝ ╚══════╝╚═╝ ╚═══╝ ╚═╝
From idea to implementation, orchestrated. Input Select PRD or input file > 📁 examples/ README.md examples/sample-prd.md Persona Minimal - MVP focus > Balanced - Standard Production - Enterprise Action > ▶ Run ⚙ Advanced... × Cancel ↑ up · ↓ down · / filter · enter select
When one agent handles everything - architecture, implementation, testing, security - quality suffers. Real teams don't work that way.
Code gets written before API contracts, data models, or error handling strategies are defined. Inconsistent patterns across the codebase.
Generated tests often cover happy paths only. Edge cases, error scenarios, and integration points get missed.
Input validation, rate limiting, and authorization checks are easy to overlook without a dedicated security review pass.
Each agent has a focused role and reads previous outputs as context. The architect defines the system before the implementer writes code.
Each agent receives a focused prompt and produces a specific deliverable. Downstream agents read upstream outputs as context.
REST/GraphQL endpoints, DB schema, error handling patterns, deployment config
Test cases per endpoint, edge cases to cover, integration test scenarios
OWASP checks, auth flow review, input validation requirements, rate limit specs
Reads all specs, writes handlers, services, repos, middleware, Dockerfile
Writes tests from test-plan.md, checks security requirements, validates build
Currently supports Claude Code, with Gemini CLI and Codex CLI coming soon. Uses your existing authentication - no additional API keys required.
QA and security agents run concurrently after architecture completes. Dependency-aware scheduling minimizes total runtime.
Content-hash based change detection. Only affected outputs get regenerated when inputs change.
The primary interface. Auto-discovers PRD files, lets you pick personas and agents visually, with keyboard navigation and file browser.
Point pagent at an existing project and it will respect your patterns, conventions, and directory structure.
Define your preferences once in .pagent/config.yaml. Language, API style, cloud provider, database, CI/CD tooling.
Run as an MCP server for Claude Desktop integration. Supports stdio and HTTP transports with optional OAuth.
Different projects need different levels of thoroughness. Choose the right trade-off between speed and completeness.
POC / hackathon
Default - most projects
Enterprise / regulated
Or use CLI: pagent run ./prd.md -s -v