agentscope and oh-my-agent

These are competitors in the multi-agent orchestration space, both offering frameworks to build and coordinate multiple specialized agents, though AgentScope emphasizes interpretability while oh-my-agent emphasizes pre-built agent specialization and observability.

agentscope
90
Verified
oh-my-agent
63
Established
Maintenance 23/25
Adoption 23/25
Maturity 25/25
Community 19/25
Maintenance 13/25
Adoption 18/25
Maturity 12/25
Community 20/25
Stars: 18,063
Forks: 1,606
Downloads: 310,344
Commits (30d): 31
Language: Python
License: Apache-2.0
Stars: 326
Forks: 49
Downloads: 2,249
Commits (30d): 0
Language: TypeScript
License:
No risk flags
No License

About agentscope

agentscope-ai/agentscope

Build and run agents you can see, understand and trust.

Provides built-in support for ReAct agents, multi-agent orchestration via message hub, and ecosystem integrations including MCP (Model Context Protocol), A2A (Agent-to-Agent) protocol, and voice capabilities. Designed for model-centric reasoning rather than prompt-constrained workflows, with production deployment options including serverless, Kubernetes, and local execution with integrated OpenTelemetry observability.

About oh-my-agent

first-fluke/oh-my-agent

oh-my-agent: The Ultimate Multi-Agent Harness. 9 specialized agents, Serena Memory, parallel CLI execution, real-time observability, and zero-config skills.

Built on a layered architecture that routes natural-language requests through orchestration agents (PM and orchestrator) to specialized domain teams (frontend, backend, DB, mobile, infra, design, QA, debug), with two-tier skill design that reduces token usage by ~75%. Integrates with major AI IDEs (Cursor, Claude Code, Gemini CLI, Codex CLI) via portable `.agents/` config directories, and supports multi-vendor LLM selection (Gemini, Claude, Codex, Qwen) per agent type with real-time monitoring dashboards.

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