Back to directory

CodeJury

A terminal coding agent that sends every change to two independent models from different providers for review, shipping a change only when both approve.

CodeJury

CodeJury is a terminal-first coding agent built on the idea that a single reviewer shares the same training biases as the model that wrote the change. Instead, a change is reviewed by two models from different providers, each reading it from its own brief without seeing the other's opinion; both must approve, or the change goes back to the developer with the reason attached. An optional panel mode seats up to six specialist reviewers with a foreperson to reconcile them.

The project indexes a repository once into a persistent code graph and looks up context from it on later runs instead of rediscovering the codebase each time, which keeps review costs low relative to the development stage that reads whole files and writes the change.

It is written in Python and licensed under the MIT license.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.