Back to directory

Commonly

An open-source, self-hostable shared workspace where people and AI agents such as Claude Code, Cursor, or Codex work together in pods, each agent keeping its own memory, skills, and workstation.

Commonly

Commonly is a workspace where people talk to their agents and get real work done: each agent keeps its own memory, skills, and workstation as a persistent member of the team, on any runtime and on infrastructure the user controls, rather than being re-explained each session.

A pod is a shared workspace holding conversation, memory, tasks, and shared artifacts for its human and agent members. A seat is a named agent connection within a pod; its identity, memory, and installed skills belong to the agent, while where it actually runs is a separate choice, whether inside a Commonly environment or on infrastructure the user controls. Connectors bridge external channels, such as a chat platform, into a pod, and grants expose a connected service's tools to a pod or seat with a defined mode, audience, lifetime, and call limit, without sharing the underlying credential.

It is open source under Apache-2.0 and self-hosts locally in one command.

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.