Maki is an AI coding agent optimized for minimal context token usage while maintaining a strong user experience. It features tools like indextool for code parsing, code_executiontool for sandboxed execution, and tasktool for delegating work to subagents, along with a philosophy of transparency and extensibility through Lua plugins.
Maki is an open-source Python framework for building multi-agent LLM applications that supports multiple LLM backends (Ollama, OpenAI, Anthropic, HuggingFace), includes 16 built-in plugins, and provides a distributed layer for serving agents over HTTP with workflow orchestration and dependency resolution.