agentscope
★ 33.7k
vs
murmur
★ 20
agentscope vs murmur
agentscope: AgentScope is a production-ready, easy-to-use agent framework designed for increasingly agentic LLMs. It offers essential abstractions, built-in support for finetuning, and flexible multi-agent orchestration for various deployment environments.; murmur: Murmur is a secure, end-to-end encrypted multi-agent communication bus that enables AI models like Claude and GPT to talk directly to each other. It eliminates the need for human relay, allowing for autonomous collaboration on complex tasks through features like `murmur_request` for send-and-wait messaging.
01
TL;DR
agentscopeMulti-Agent · ★ 33.7k
When to choose:
- You want composable Python 3.11+ building blocks (ReAct loop, toolkit, pipelines, A2A, realtime voice) with bilingual documentation.
- You use Chinese model providers (DashScope, DeepSeek, Volcengine) alongside global APIs under an Apache-2.0 license.
When to skip:
- You rely on v1.x AgentScope code and do not want to migrate to the redesigned v2.0 architecture.
- You need Python 3.10 or .NET support; AgentScope 2.0 requires Python 3.11+.
murmurMulti-Agent · ★ 20
Autonomous Code Reviews: AI agents can collaborate on reviewing pull requests and providing feedback without human intervention.
02
Side-by-Side Comparison
Field
agentscopemurmurCategory
Multi-Agent
Multi-Agent
Stars
★ 33.7k
★ 20
License
Apache-2.0
MIT
Install Command
uv pip install agentscope
git clone https://github.com/alexfrmn/murmur.git && cd murmur && git checkout --detach v2.10.0 && npm ci && npm run build
Updated
1d ago
2d ago
Open Source
Yes
Yes
Tags
Agent Framework, Multi-Agent Systems, Large Language Models
Multi-Agent Communication, E2E Encryption, NATS Messaging
03
Features
agentscope01Easy-to-use with built-in ReAct agents, tools, and human-in-the-loop steering.
02Extensible with broad ecosystem integrations, MCP, and A2A protocol support.
03Production-ready for local, serverless, or Kubernetes deployments with OTel support.
04Voice-enabled agents capable of speech understanding and response.
05Seamless integration with Reinforcement Learning for agent tuning.
murmur01E2E Encryption & Digital Signatures: Uses X25519 + XChaCha20-Poly1305 AEAD for encryption and Ed25519 for message authentication, ensuring secure communication.
02`murmur_request` for Autonomous Workflows: A send-and-wait mechanism that automatically polls for replies, enabling fully autonomous, overnight agent collaboration without human intervention.
03At-Least-Once Delivery with SQLite Outbox: Guarantees message delivery through a persistent SQLite outbox with ACK correlation and includes a dead-letter queue for failed messages.
04MCP Server for AI Client Integration: Exposes a JSON-RPC MCP server with 7 tools, facilitating integration with any MCP-compatible AI client, including native wake for Claude and Codex.
05Scoped Channels & Session Affinity: Ensures that for an addressed conversation, only the owning session of the addressed agent responds, preventing competing threads and guaranteeing exactly one message emit.
04
Use Cases
agentscope↳Developing multi-agent collaborative applications and strategic games.
↳Building agents with advanced tool-use capabilities and multi-step reasoning.
↳Tuning agent performance using Reinforcement Learning for continuous improvement.
murmur↳Autonomous Code Reviews: AI agents can collaborate on reviewing pull requests and providing feedback without human intervention.
↳Collaborative Research Tasks: Multiple AI agents can work together on research, sharing context and findings through encrypted channels.
↳Automated Architectural Decisions: Agents can autonomously discuss and make architectural decisions, leveraging different models' strengths.
↳Inter-Organizational Agent Communication: Facilitates secure, encrypted communication between AI agents across different machines and organizations.
05
Best For
agentscopeMost PopularEssentialTrending
murmur—
FAQ
FAQ
What is the difference between agentscope and murmur?
Both agentscope and murmur are in the Multi-Agent category. agentscope has 33.7k stars, while murmur has 20 stars.
Which is better, agentscope or murmur?
The best choice depends on your use case. Choose agentscope if Developing multi-agent collaborative applications and strategic games., and murmur if Autonomous Code Reviews: AI agents can collaborate on reviewing pull requests and providing feedback without human intervention..
Is agentscope free or open source?
Yes, agentscope is open source on GitHub (Apache-2.0).
Is murmur free or open source?
Yes, murmur is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→