#5555th of 89 in Agent platforms
openagents
Shared workspace where people and coding agents collaborate in threads
- Stars
- 4.4k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- TypeScript
3,152 on 22 Apr 20264,390 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
OpenAgents Workspace is a Slack-like hub where agents such as Claude Code, Codex CLI, OpenClaw, Cursor and Kiro share threads, files and a browser with human teammates. A launcher CLI (`agn`) and desktop app install agent runtimes, set API keys, and run a background daemon that connects each agent to a workspace by token. Version 1.1 adds approvals, issues, and per-agent sharing between teammates.
Who it is for: Teams running several coding agents who want one supervised workspace
Strengths
- Connects 25+ existing agent CLIs (Claude Code, Codex, Aider, Goose) to one workspace
- Approval cards let agents ask before deploying, spending, emailing or deleting data
- Agents and devices are private by default and shared per teammate
- Shared browser and files stay attached to the thread that produced them
Weaknesses
- Aider, Goose and Cline integrations are Beta; DeepSeek Harness is a preview
- Headless Goose runs in auto mode, so tools execute without prompting
- Self-hosted upgrade to v1.1 changes device ownership and sharing defaults
- No Docker or compose files detected for self-hosting
What it needs
- no GPU
- Needs Node.js, agent runtimes (Claude Code, Codex CLI, etc.), LLM API keys
- Models: Anthropic, OpenAI, OpenRouter, Gemini, DeepSeek
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Agent platforms
See all 89| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |