#toon

Databricks CLI built for AI agents. Compact TOON output, lean default schemas, and errors that say what to try next. Runs on top of the official databricks CLI, following the AXI standard.

The Ruby framework for programming—rather than prompting—language models.

🐍 Community-driven Python implementation of TOON

Agent-ergonomic CLI for task/backlog management with pluggable backends (markdown, sqlite, remote trackers)

MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.

Local memory + orchestration layer for custom LLM agents: SCOPE-style tactical/strategic memory over execution traces, Qdrant-backed, polyglot subprocess tools, agent-as-tool composition.

No repository description published.