Back to directory

Monet

A native desktop app that gives a unified control room for Claude Code and Codex sessions: browse and search session history across projects, drive several parallel sessions from one workbench, and race the same prompt across different engines, models or channels side by side.

Monet

Monet reads Claude Code's JSONL session files and Codex's rollout files read-only and keeps its own added data, such as titles, tags and favorites, in a separate local store, so installing it does not touch the underlying CLI tools' own history format. Its workbench view lays out an unlimited number of parallel sessions with a monitoring track showing live status, tail output and token usage, with permission requests appearing as cards that can be approved or denied directly; a race mode broadcasts one question to multiple engines, models or channels and compares the answers and cost side by side.

Other features include a file ledger showing which files a session touched and why, natural-language scheduled tasks that can wake the app from sleep to run and then let it sleep again, a menu-bar view of subscription usage per provider, and a built-in MCP server so a session's own model can search session history, create scheduled tasks or check runner logs. Monet does not bundle its own AI models or charge for AI use; all model calls go through the user's own provider accounts and channels, and it supports 12 interface languages.

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.