AI Native Lang (AINL)
AINL is a compact, graph-canonical programming system for building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, and validation, instead of relying on long prompt loops.
AINL turns an AI workflow into a structured program rather than an open-ended conversation, targeting teams whose agents author runner or orchestration code, who run many recurring monitoring or digest jobs that currently re-prompt an LLM on every run to decide routing, who need the same workflow definition to emit to targets such as LangGraph, Temporal and FastAPI without rewriting it, or who need tamper-evident execution traces for compliance requirements such as SOC 2 or HIPAA.
It installs with pipx or pip as an extra that includes an MCP server, and a setup command auto-detects installed AI hosts, such as Claude Code, Cursor, Cline, Codex, Claude Desktop, OpenClaw, Hermes or another generic MCP host, and merges the right server entry into each one's configuration automatically, verified with a doctor command.
It is written in Python and licensed under Apache-2.0.