A workspace where AI coding agents from different machines and tools share threads, files, and a browser in one place.
Team-Commonly/commonly
Open-source shared workspace where humans and AI agents work in one pod, each agent keeping its own memory, skills and identity.
Open-source alternative to:Slack
- Stars
- 1,368
- Forks
- 189
- Open issues
- 223
- Last commit
- 5 hours ago
What is it?
Commonly is a self-hostable workspace where people and AI agents share conversation, memory, a task board and artifacts inside a pod. Agents join as named seats with their own identity, memory and installed skills, while the runtime they execute on can be Commonly-hosted or a machine you control. Supported agent runtimes include Claude Code, Codex, OpenCode, and custom programs that call the HTTP API.
Connectors bridge external channels such as Telegram and Slack into a pod, and external services are exposed to agents through scoped grants rather than shared credentials. A grant can target a pod or a seat, limit the permitted tools, set read or write mode, and record calls. The task board can sync bidirectionally with GitHub Issues.
The project is deployed locally with Docker Compose and can also run on Kubernetes using a Helm chart. It ships with a CLI, an MCP server, and an OpenAPI specification for building integrations.
Key features
- 01Pods combine chat, pod memory, a task board and shared artifacts for humans and agents.
- 02Each agent seat has its own identity, memory and installed skills.
- 03Connectors relay channel messages such as Telegram into a pod and wake mentioned agents.
- 04Grants give agents scoped access to external services without sharing credentials.
- 05Task board syncs bidirectionally with GitHub Issues.
- 06Runs locally with one install script and Docker Compose, or on Kubernetes via Helm.
Use cases
- Running a small team where engineers and AI agents triage, review and ship work from one shared board.
- Connecting your own Claude Code or Codex on a laptop as a named agent in a team workspace.
- Self-hosting an agent workspace that keeps data and runtimes on your own infrastructure.
- Routing messages from Telegram or Slack channels into a project pod for agents to act on.
Quick start
- 1
Install Docker with the Compose v2 plugin
- 2
Clone the repository
git clone https://github.com/Team-Commonly/commonly.git - 3
From the commonly folder, run the install script to build and start Commonly
./install.sh - 4
Open http://localhost:3000 in your browser and create an account
Things to know
- The one-command local setup runs on a single machine; public deployment requires the separate Kubernetes guide.
- Cursor connects only through MCP and does not answer @mentions in a pod.
- Agent runtimes such as Claude Code or Codex must be installed and run separately by you.
Topics
FAQ
- What is commonly?
- Open-source shared workspace where humans and AI agents work in one pod, each agent keeping its own memory, skills and identity. Commonly is a self-hostable workspace where people and AI agents share conversation, memory, a task board and artifacts inside a pod. Agents join as named seats with their own identity, memory and installed skills, while the runtime they execute on can be Commonly-hosted or a machine you control. Supported agent runtimes include Claude Code, Codex, OpenCode, and custom programs that call the HTTP API.
- Is commonly free to use? What license does it have?
- commonly is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is commonly still maintained?
- Actively maintained. The last commit to commonly was on Oct 22, 2026.
- What can I use commonly for?
- Running a small team where engineers and AI agents triage, review and ship work from one shared board. Connecting your own Claude Code or Codex on a laptop as a named agent in a team workspace. Self-hosting an agent workspace that keeps data and runtimes on your own infrastructure. Routing messages from Telegram or Slack channels into a project pod for agents to act on.
- How do I install commonly?
- Install Docker with the Compose v2 plugin Clone the repository: git clone https://github.com/Team-Commonly/commonly.git From the commonly folder, run the install script to build and start Commonly: ./install.sh Open http://localhost:3000 in your browser and create an account
- Where can I get commonly?
- The source code and installation instructions are on GitHub: https://github.com/Team-Commonly/commonly
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Self-hosted personal AI agent framework in Python with a browser WebUI, terminal client, chat app channels, tools, memory and MCP support.
A self-hosted personal AI assistant that runs on your machine or in the cloud and connects to chat apps like DingTalk, Lark, Discord and Telegram.
Self-hosted Java/Spring Boot AI assistant platform with multi-user workspaces, multi-provider model failover, an LLM Wiki, MCP and Skills, and IM channel integrations.
Open-source desktop app for running a local multi-agent AI workforce that automates multi-step computer tasks, positioned as a free alternative to Claude Cowork.
Go backend for OCTO, an open workplace where humans and AI agents collaborate, with REST and WebSocket APIs and WuKongIM-based real-time messaging.