A Python experiment where Jev picks each actor's next legal move, and the simulation applies it.
@narwhalishusSwarm Lookahead runs a small world of synthetic actors. Jev chooses each actor's next action from a list of legal moves. Ordinary code applies the move, records what happened, and steps the simulation forward.
A run stops at an ending, a depth limit, a deadline, or a budget. There is no website to open. You run it from the command line.
It was built at the San Francisco Jev hackathon.
Scores each action an agent wants to take against the job it was given: allow, ask a person, or block.
Jev
Python
Claude Code
CodexAsk a repository's history a plain question and it points at the commit that did it.
JevPythonA compiler driver that asks Jev whether to inline each function call, aiming to beat clang -Oz on binary size.
JevPython
LLVMClangA bring-your-own-key AI PR reviewer that runs as a GitHub Action, combining deterministic analysis with model reasoning and a Jev-driven behaviour check before it lets a merge through.
JevPythonTeach Jev what good and bad look like for your app by labelling a handful of examples.
JevPythonTyped decisions from the command line: jev yes, jev pick and jev score, each with a calibrated probability.
JevPython
CodeRabbit participant
