An efficient AI coding agent. Native Rust TUI. Immediate startup, 60 FPS, low memory. Indexes files instead of reading them, chains tools in a sandbox interpreter. Anthropic, OpenAI, Google, Z.AI, Synthetic, or any OpenAI / Anthropic compatible API.

Lobsters is a community-driven platform for sharing and discussing links to articles, tutorials, and projects related to technology and programming. Readers can learn about a wide range of topics, from software development and system administration to cybersecurity and artificial intelligence. With user submissions, comments, and voting, Lobsters provides a platform for collaborative learning and knowledge sharing among technology enthusiasts.

Lobsters

Maki is an AI coding agent built with a native Rust TUI running at 60 FPS with low memory usage. It optimizes token usage by indexing files into skeletons (imports, type defs, function signatures) using tree-sitter instead of reading full files, saving ~165 tokens per turn. A sandboxed Python interpreter lets the model chain async tool calls so intermediate data never pollutes context. Features include multi-tier subagents (haiku for grep tasks, opus for architecture), automatic context compaction, per-command permission parsing, long-term memory, MCP support, and compatibility with Anthropic, OpenAI, Google, and other APIs.

maki