openagents and connectonion

These are competitors offering different architectural approaches to multi-agent coordination—OpenAgents emphasizes decentralized peer-to-peer agent networks while ConnectOnion focuses on centralized orchestration patterns for agent collaboration.

openagents
91
Verified
connectonion
79
Verified
Maintenance 25/25
Adoption 20/25
Maturity 25/25
Community 21/25
Maintenance 25/25
Adoption 18/25
Maturity 16/25
Community 20/25
Stars: 1,752
Forks: 215
Downloads: 7,098
Commits (30d): 806
Language: Python
License: Apache-2.0
Stars: 504
Forks: 72
Downloads: 2,665
Commits (30d): 81
Language: Python
License:
No risk flags
No License

About openagents

openagents-org/openagents

OpenAgents - AI Agent Networks for Open Collaboration

Provides a unified workspace where distributed agents (Claude Code, OpenClaw, Cursor, etc.) collaborate in real-time through shared threads, files, and a live browser—accessible via persistent URL with no account required. Built on an event-native architecture with MCP and A2A protocol support, agents coordinate via @mentions and shared context. Includes a cross-platform Launcher CLI for installing runtimes, managing credentials, and running agents as background daemons, plus a Network SDK for building custom agent systems.

About connectonion

openonion/connectonion

The Best AI Agent Framework for Agent Collaboration.

Provides production-grade agent primitives including function-calling tools, plugins with 12 lifecycle hooks, skill auto-discovery compatible with Claude Code, and approval gates for unsafe operations. Agents expose themselves via HTTP and P2P relay for multi-agent discovery, with a fast rules-based trust system that gates inter-agent calls without LLM overhead. Includes pre-built tools (bash, file system, browser automation, Gmail, calendar, memory), built-in debugging/chat interface, and a ready-to-use frontend at chat.openonion.ai—eliminating typical backend/frontend scaffolding.

Scores updated daily from GitHub, PyPI, and npm data. How scores work