AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
A small language for table-shaped business rules, and a harness for the agent that turns them into code. Gaps and contradictions are proved away first; out comes dependency-free code in twelve languag
Developer toolsRust · PythonGitHub @i2yOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
A small language in which a business rule is a table — fees, taxes, discounts. rulec proves there are no gaps, conflicts or dead rows, returns the exact input when there are, and only then generates dependency-free code in 12 languages. Built for AI agents.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
A small language for table-shaped business rules, and a harness for the agent that turns
them into code.
Write the table, and out come Python, NumPy, TypeScript, JavaScript, Rust, Ruby, PHP, Go,
Swift, Java, SQL and Wasm — ordinary functions with no runtime, no configuration and no
dependencies. The proof is finished before the code exists: a rule that cannot be proved
does not generate.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
A small language for table-shaped business rules, and a harness for the agent that turns
them into code.
Write the table, and out come Python, NumPy, TypeScript, JavaScript, Rust, Ruby, PHP, Go,
Swift, Java, SQL and Wasm — ordinary functions with no runtime, no configuration and no
dependencies. The proof is finished before the code exists: a rule that cannot be proved
does not generate.Read the full README ↗