Agent-to-Agent Communication Library - Mia's fork of Coral-Protocol/Anemoi
Project description
mia-anemoi: Agent-to-Agent Communication System
mia-anemoi is Mia's fork of Coral-Protocol/Anemoi โ a semi-centralized multi-agent system (MAS) built on Agent-to-Agent (A2A) communication via MCP.
This fork is adapted for terminal-based agent orchestration and SimExp integration.
๐ Key Features
- Semi-Centralized Architecture: Reduces dependency on a single planner agent
- Direct Agent-to-Agent Collaboration: Real-time monitoring, assessment, and refinement
- Efficient Context Management: Minimizes redundant prompt concatenation
- Benchmark Performance: 52.73% accuracy on GAIA benchmark (+9.09% over OWL)
- SimExp Integration: Terminal-to-AI session continuations with A2A communication
๐ฆ Package Components
| Component | Description | Location |
|---|---|---|
| Python Client | Lightweight A2A communication library | mia_anemoi/ |
| CAMEL Agents | Specialized AI agents (planning, web, coding) | Anemoi/agents/ |
| Kotlin MCP Server | SSE-based thread messaging | src/main/kotlin/ |
๐ง Installation
Python Client (Lightweight)
pip install mia-anemoi
With CAMEL Agents (Full)
pip install mia-anemoi[agents]
From Source
git clone https://github.com/miadisabelle/mia-anemoi.git
cd mia-anemoi
pip install -e .
๐ Quick Start
1. Start MCP Server
# Using Docker
docker run -p 5555:5555 ghcr.io/miadisabelle/mia-anemoi-server:latest
# Or build and run locally
./gradlew build
java -jar build/libs/mia-anemoi-server-1.0-SNAPSHOT.jar
2. Use Python Client
from mia_anemoi import AnemoiClient, AnemoiClientConfig
# Initialize client
config = AnemoiClientConfig(transport="file", base_path="~/.anemoi")
client = AnemoiClient("session-123", config)
# Fork session with context inheritance
child_id = client.fork_session(parent_state)
# Send update to siblings
client.send_update("Task completed", {"files": ["main.py"]})
# Wait for messages
msg = client.wait_for_mentions(timeout=30)
3. Run CAMEL Agents
export CORAL_CONNECTION_URL="http://localhost:5555/devmode/gaia/public/session1/sse"
export OPENAI_API_KEY="sk-..."
python -m Anemoi.agents.planning_agent
๐๏ธ Architecture
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ mia-anemoi Package โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ โ
โ โโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ โ Python Client โ SSE โ Kotlin MCP Server โ โ
โ โ (mia_anemoi/) โโโโโโโโ (src/main/kotlin/coralserver/) โ โ
โ โ โ โ โ โ
โ โ - AnemoiClient โ โ - list_agents โ โ
โ โ - FileTransport โ โ - create_thread โ โ
โ โ - MCPTransport โ โ - send_message โ โ
โ โโโโโโโโโโโโโโโโโโโโโโ โ - wait_for_mentions โ โ
โ โ โ - close_thread โ โ
โ โ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ โผ โ
โ โโโโโโโโโโโโโโโโโโโโโโ โ
โ โ CAMEL Agents โ โ
โ โ (Anemoi/agents/) โ โ
โ โ โ โ
โ โ - planning_agent โ โ
โ โ - web_agent โ โ
โ โ - coding_agent โ โ
โ โ - critique_agent โ โ
โ โโโโโโโโโโโโโโโโโโโโโโ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ Documentation
See the rispecs/ directory for RISE specifications:
- app.spec.md - Package overview and Python client API
- server.spec.md - Kotlin MCP server documentation
- agents.spec.md - CAMEL agent specifications
๐ Original Publication
This is a fork of the original Anemoi project. Please cite the original work:
@article{ren2025anemoi,
title={Anemoi: A Semi-Centralized Multi-agent Systems Based on Agent-to-Agent Communication MCP server from Coral Protocol},
author={Ren, Xinxing and Forder, Caelum and Zang, Qianbo and Tahir, Ahsen and Georgio, Roman J. and Deb, Suman and Carroll, Peter and G\"{u}rcan, \"{O}nder and Guo, Zekun},
journal={arXiv preprint arXiv:2508.17068},
year={2025},
url={https://arxiv.org/abs/2508.17068}
}
๐ Links
- Original Repository: Coral-Protocol/Anemoi
- arXiv Paper: arXiv:2508.17068
- SimExp Integration: miadisabelle/simexp
๐ License
MIT License - See LICENSE for details.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mia_anemoi-0.1.0.tar.gz.
File metadata
- Download URL: mia_anemoi-0.1.0.tar.gz
- Upload date:
- Size: 14.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
022057ac7ea82bc3fc229934f459b31409cd4de46004d28394675fe2133c6635
|
|
| MD5 |
01627062056c803eb784a9ce1ee51eca
|
|
| BLAKE2b-256 |
94d57c254ca7e83d17716ffc4625dea17650ba0e090d58bdaa4a1aa4b9a28c14
|
File details
Details for the file mia_anemoi-0.1.0-py3-none-any.whl.
File metadata
- Download URL: mia_anemoi-0.1.0-py3-none-any.whl
- Upload date:
- Size: 13.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0ccdd589ab1965da87595face761dd676050958c08050ac8045b525d0aab13f0
|
|
| MD5 |
68435803ce3490bf2a428b825a3c4afd
|
|
| BLAKE2b-256 |
4d37fc71151c0a70c3c34dae82b889b8831c5e84d28c7e0a301cff9fa325e52d
|