Back to directory

IM.codes

A shared context, memory and supervision layer that connects coding agents such as Claude Code, Codex and Gemini CLI to each other and to enrolled machines, which authorized agents can operate directly with scoped commands and remote desktop access.

IM.codes

IM.codes gives coding agents a shared memory layer and a managed Model Context Protocol tool surface across providers such as Claude Code, Codex, Gemini CLI, GitHub Copilot, Cursor, OpenCode, OpenClaw and Qwen, turning completed work into reusable context across sessions. Terminal access, file and Git views, a localhost preview, notifications, multi-agent workflows, an OpenSpec Auto Deliver flow, and cross-provider audit keep human and agent work visible together.

Alongside coding sessions, it can enroll supported computers as restricted Controlled Nodes: an authorized agent then operates one or many of them with scoped commands, file transfer and typed Computer Use, and capable Windows nodes also expose a browser-based remote desktop for a person to view or take over. Each node has independent, revocable credentials and stays separate from normal session lists.

It ships native apps for iPhone, iPad and Apple Watch as well as a web app. The project describes itself as an actively developed personal open-source project with no warranty or stability guarantee.

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.