AgentTeams vs ruflo
AI agent coordination projects compared
AgentTeams and ruflo both coordinate multiple AI agents, but take different approaches. AgentTeams manages external runtimes in shared Matrix rooms with human oversight, while ruflo adds orchestration, memory, and workflows to Claude Code and Codex.
AgentTeams: Coordinate Multi-Agent Work in Matrix Rooms
AgentTeams is a collaborative multi-agent runtime platform built around Matrix rooms, where people can observe and intervene as a Manager coordinates Workers. It suits teams that want auditable agent collaboration across multiple runtimes, with local Docker setup or Kubernetes deployment.
ruflo: Coordinate AI Agents and Autonomous Workflows
Ruflo is a TypeScript agent harness for Claude Code and Codex. It adds coordinated agent teams, persistent memory, workflow automation, and MCP integrations for developers building multi-agent systems.
| AgentTeams | ruflo | |
|---|---|---|
| Language | Go | TypeScript |
| License | Apache-2.0 | MIT |
| Stars | 5.9k | 73.8k |
| Forks | 730 | 8.8k |
| Last analyzed | Oct 31, 2026 | Oct 3, 2026 |
Key differences
- AgentTeams runs external Worker runtimes, while ruflo provides an agent harness for Claude Code and Codex.
- AgentTeams centers collaboration on shared Matrix rooms where people can observe and intervene; ruflo emphasizes coding workflows, persistent memory, and reusable automation.
- AgentTeams is written in Go and licensed under Apache-2.0; ruflo is written in TypeScript and licensed under MIT.
- AgentTeams offers local Docker deployment and a Kubernetes control plane; ruflo offers plugin and CLI setup paths.
- AgentTeams routes model traffic through Higress and provides MinIO shared storage; ruflo includes an MCP server, plugins, and provider integrations.
- The projects report different repository scale: AgentTeams has 5.7k stars and 705 forks, while ruflo has 73.8k stars and 8.8k forks. Both are not archived.
Choose AgentTeams if you…
- want people to observe and intervene in agent conversations through Matrix.
- need to coordinate external agent runtimes under centralized credential and traffic management.
- want local Docker deployment or a Kubernetes-based control plane.
Choose ruflo if you…
- use Claude Code or Codex and want agent coordination integrated into those workflows.
- need persistent memory, reusable workflows, or MCP and plugin integrations.
- want to explore agent federation across installations with documented trust and data-handling controls.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.