Generates hierarchical, agent-executable project plans optimized for solo AI development workflows.
Kitt Project Planner transforms high-level requirements into actionable PLAN.md files that serve as direct prompts for AI agents. It utilizes 'aggressive atomicity' to break down complex phases into small, high-quality tasks, preventing the performance degradation typical of large context windows. By integrating human-in-the-loop checkpoints, automated CLI execution, and smart deviation rules for self-healing, it streamlines the software development lifecycle for solo developers using agentic tools like Claude Code.
Key Features
01Aggressive atomicity that splits phases into 2-3 task units to maintain LLM quality.
02Context-aware monitoring with automatic handoffs to prevent quality crashes.
03Agent-optimized hierarchical planning where PLAN.md acts as the primary prompt.
04Automated deviation rules for self-correcting bugs and blockers during execution.
050 GitHub stars
06Human-in-the-loop checkpoints for aesthetic verifications and architectural decisions.
Use Cases
01Decomposing complex software features into small, verifiable agent tasks.
02Executing long-running development phases with automated bug-fixing and logging.
03Structuring greenfield project roadmaps with clear milestone boundaries.
