I built a memory-bounded, self-improving multi-agent architecture for OpenCode (tree-sitter AST graph, not vector search)

I built a memory-bounded, self-improving multi-agent architecture for OpenCode (tree-sitter AST graph, not vector search)

GitHub - Sdinzsh/PowerHou53: A self-improving, memory-bounded multi-agent AI architecture for OpenCode. Turn static prompts into an autonomous, context-efficient learning loop.

GitHub - Sdinzsh/PowerHou53: A self-improving, memory-bounded multi-agent AI architecture for OpenCode. Turn static prompts into an autonomous, context-efficient learning loop.

GitHub - Sdinzsh/PowerHou53: A self-improving, memory-bounded multi-agent AI architecture for OpenCode. Turn static prompts into an autonomous, context-efficient learning loop.