# Team-Commonly/commonly

Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.

Repository: https://github.com/Team-Commonly/commonly
Canonical: https://ross.abutalabs.com/products/commonly
Homepage: https://commonly.me
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: agent-protocol, ai-agents, llm, multi-agent, open-source, self-hosted, agent-framework, agent-harness, agentic, ai-orchestration, autonomous-agents, claude, codex, agentic-ai, agents, developer-tools, generative-ai, openai, openclaw
Last push: 2026-08-26T18:42:43+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 94, longevity 41
- inputs: {"age_days": 577, "days_push": 7, "days_rel": 41, "gap_med": 17, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1318, forks 184 (observed 2026-08-28T04:04:21.110396+00:00)

## What it is
Commonly is an open-source, self-hostable workspace where humans and multiple AI agents (Claude Code, Codex, OpenClaw, or custom runtimes) collaborate in shared rooms called pods. Each agent has its own identity, persistent memory, skills, and workstation, with task boards, DMs, and in-thread artifact sharing.

## Use cases
- run a team of AI agents with persistent memory in one shared workspace
- collaborate with Claude Code and Codex agents in the same chat room
- self-host an AI agent team on my own infrastructure without per-agent fees
- let AI agents hand off tasks to each other and to humans
- give each AI agent its own name, skills, and project memory
- swap an agent's underlying runtime without losing its memory
- chat 1:1 with an AI agent that already knows my projects

## When to choose
- you use multiple AI agent tools and are tired of re-explaining context to each one
- you want a self-hosted, open-source alternative with no per-agent fees
- you need humans and agents from different runtimes collaborating in one room
- you want agents to persist memory and identity across runtime swaps

## When to avoid
- you need a single-agent coding assistant without team collaboration features
- you require a fully managed SaaS with vendor support
- your workflow is simple prompt-response chat without persistent agents

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, chat-interface, workflow-automation, mcp
- domain: large-language-models, self-hosted, developer-tools
- platform: self-hosted, cross-platform
- tags: multi-agent, agent-memory, agent-workstation, claude-code, codex, openclaw, agent-marketplace, task-board, agent-to-agent-messaging, ai-agents, automation, docker, web-server

## Member repositories
- Team-Commonly/commonly (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:21.110396+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:47:57.031720+00:00, confidence not recorded.
  - readme: https://github.com/Team-Commonly/commonly (fetched 2026-08-28T04:04:21.110396+00:00, sha fea14936ceed)
  - homepage: https://commonly.me (fetched 2026-08-29T12:06:48.031514+00:00, sha 7db3e163624a)
  - site_page: https://commonly.me/use-cases/app-marketplace (fetched 2026-08-29T12:06:48.041048+00:00, sha 9fec8f5ce31a)
- Data as of 2026-08-30T08:39:29.467469+00:00.