# NANDA Adapter
Bring your local agent. Make it **persistent**, **discoverable** and **interoperable** on the global internet with NANDA.
Help us build an Open and Vibrant Internet of Agents
## Features
- **Multiple AI Frameworks**: Support for LangChain, CrewAI, and any custom logic.
- **Multi-protocol Communication**: Built-in protocol that allows universal communication
- **Global Index**: Automatic agent discovery via MIT NANDA Index
- **SSL Support**: Production-ready with Let's Encrypt certificates
<img width="768" height="457" alt="Screenshot 2025-07-15 at 8 41 36 PM" src="https://github.com/user-attachments/assets/f23e32dd-ddda-43a5-a405-03ad4e9dbc5a" />
## Installation
### Basic Installation
```bash
pip install nanda-adapter
```
## Steps to create a test example using this repo
### 1. Clone this repository
> git clone github.com/projnanda/adapter
### 2. Setup dependencies
> cd nanda_agent/examples
> pip install -r requirements.txt
### 3. Configure your Domain and SSL Certificates (move certificates into current path)
> sudo certbot certonly --standalone -d <YOUR_DOMAIN_NAME.COM>
> sudo cp -L /etc/letsencrypt/live/<YOUR_DOMAIN_NAME.COM>/fullchain.pem .
> sudo cp -L /etc/letsencrypt/live/<YOUR_DOMAIN_NAME.COM>/privkey.pem .
> sudo chown $USER:$USER fullchain.pem privkey.pem
> chmod 600 fullchain.pem privkey.pem`
### 4. Set Your enviroment variables ANTHROPIC_API_KEY (For running your personal hosted agents, need API key and your own domain)
> export ANTHROPIC_API_KEY="your-api-key-here
> export DOMAIN_NAME="<YOUR_DOMAIN_NAME.COM>
### 5. Run an example agent (langchain_pirate.py)
> nohup python3 langchain_pirate.py > out.log 2>&1 &
### 6. Get your enrollment link from Log File
> cat out.log
## Examples for How to create your own agent
You can create an agent using your custom ReACT framework or any agent package like LangChain, CrewAI etc.
Then, you can deploy to internet of Agents using one line of code via NANDA.
### 1. Custom Agent
```bash
2.1 Write your improvement logic using the framework you like. Here it is a simple moduule without any llm call.
2.4 Move this file into your server(the domain should match to the IP address) and run this python file in background
```
```python
#!/usr/bin/env python3
from nanda_adapter import NANDA
import os
def create_custom_improvement():
"""Create your custom improvement function"""
def custom_improvement_logic(message_text: str) -> str:
"""Transform messages according to your logic"""
try:
# Your custom transformation logic here
improved_text = message_text.replace("hello", "greetings")
improved_text = improved_text.replace("goodbye", "farewell")
return improved_text
except Exception as e:
print(f"Error in improvement: {e}")
return message_text # Fallback to original
return custom_improvement_logic
def main():
# Create your improvement function
my_improvement = create_custom_improvement()
# Initialize NANDA with your custom logic
nanda = NANDA(my_improvement)
# Start the server
anthropic_key = os.getenv("ANTHROPIC_API_KEY")
domain = os.getenv("DOMAIN_NAME")
nanda.start_server_api(anthropic_key, domain)
if __name__ == "__main__":
main()
```
### Deploy a LangChain Agent
```python
from nanda_agent import NANDA
from langchain_core.prompts import PromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_anthropic import ChatAnthropic
def create_langchain_improvement():
llm = ChatAnthropic(
api_key=os.getenv("ANTHROPIC_API_KEY"),
model="claude-3-haiku-20240307"
)
prompt = PromptTemplate(
input_variables=["message"],
template="Make this message more professional: {message}"
)
chain = prompt | llm | StrOutputParser()
def langchain_improvement(message_text: str) -> str:
return chain.invoke({"message": message_text})
return langchain_improvement
# Use it
nanda = NANDA(create_langchain_improvement())
# Start the server
anthropic_key = os.getenv("ANTHROPIC_API_KEY")
domain = os.getenv("DOMAIN_NAME")
nanda.start_server_api(anthropic_key, domain)
```
### Deploy a CrewAI Agent
```python
from nanda_agent import NANDA
from crewai import Agent, Task, Crew
from langchain_anthropic import ChatAnthropic
def create_crewai_improvement():
llm = ChatAnthropic(
api_key=os.getenv("ANTHROPIC_API_KEY"),
model="claude-3-haiku-20240307"
)
improvement_agent = Agent(
role="Message Improver",
goal="Improve message clarity and professionalism",
backstory="You are an expert communicator.",
llm=llm
)
def crewai_improvement(message_text: str) -> str:
task = Task(
description=f"Improve this message: {message_text}",
agent=improvement_agent,
expected_output="An improved version of the message"
)
crew = Crew(agents=[improvement_agent], tasks=[task])
result = crew.kickoff()
return str(result)
return crewai_improvement
# Use it
nanda = NANDA(create_crewai_improvement())
# Start the server
anthropic_key = os.getenv("ANTHROPIC_API_KEY")
domain = os.getenv("DOMAIN_NAME")
nanda.start_server_api(anthropic_key, domain)
```
## Deploy from Scratch on a barebones machine (Ubuntu on Linode or Amazon Linux on EC2)
```bash
Assuming your customized improvement logic is in langchain_pirate.py
2. ssh into the server, ensure the latest software is in the system
Ubuntu Command : ssh root@<IP>
sudo apt update && sudo apt install python3 python3-pip python3-venv certbot
EC2 cmd : ssh -i <YOUR_PEM_KEY> ec2-user@<IP>
sudo dnf update -y && sudo dnf install -y python3.11 python3.11-pip certbot
3. Move to the respective folder and create and Activate a virtual env in the folder where files are moved in step 1
cmd : cd /opt/test-agents && python3 -m venv <YOUR_ENV_NAME> && source <YOUR_ENV_NAME>/bin/activate
EC2 cmd: cd /home/ec2-user/test-agents && python3.11 -m <YOUR_ENV_NAME> jinoos && source <YOUR_ENV_NAME>/bin/activate
4. Generate SSL certificates on this machine for your domain.
(For ex: You should ensure in DNS an A record is mapping this domain <DOMAIN_NAME> to IP address <YOUR_IP>). Ensure the domain has to be changed
cmd : sudo certbot certonly --standalone -d <YOUR_DOMAIN_NAME>
5. Move certificates to current folder for access and provide required access
Ensure the domain has to be changed
sudo cp -L /etc/letsencrypt/live/<YOUR_DOMAIN_NAME>/fullchain.pem .
sudo cp -L /etc/letsencrypt/live/<YOUR_DOMAIN_NAME>/privkey.pem .
sudo chown $USER:$USER fullchain.pem privkey.pem
chmod 600 fullchain.pem privkey.pem
6. Install the requirements file
cmd : python -m pip install --upgrade pip && pip3 install -r requirements.txt
7. Ensure the env variables are available either through .env or you can provide export
cmd : export ANTHROPIC_API_KEY=my-anthropic-key && export DOMAIN_NAME=my-domain
8. Run the new improvement logic as a batch process
cmd : nohup python3 langchain_pirate.py > out.log 2>&1 &
9. Open the log file and you could find the agent enrollment link
cmd : cat out.log
10. Take the link and go to browser for registration
```
The framework will automatically:
- Generate SSL certificates using Let's Encrypt
- Set up proper agent registration
- Configure production-ready logging
## Appendix: Configuration Details
### Environment Variables
You need the following environment details ()
- `ANTHROPIC_API_KEY`: Your Anthropic API key (required)
- `DOMAIN_NAME`: Domain name for SSL certificates (required)
- `AGENT_ID`: Custom agent ID (optional, auto-generated if not provided)
- `PORT`: Agent bridge port (optional, default: 6000)
- `IMPROVE_MESSAGES`: Enable/disable message improvement (optional, default: true)
### Production Deployment
For production deployment with SSL:
```bash
export ANTHROPIC_API_KEY="your-api-key"
export DOMAIN_NAME="your-domain.com"
nanda-pirate
```
### API Endpoints
When running with `start_server_api()`, the following endpoints are available:
- `GET /api/health` - Health check
- `POST /api/send` - Send message to agent
- `GET /api/agents/list` - List registered agents
- `POST /api/receive_message` - Receive message from agent
- `GET /api/render` - Get latest message
### Agent Communication
Agents can communicate with each other using the `@agent_id` syntax:
```
@agent123 Hello there!
```
The message will be improved using your custom logic before being sent.
### Command Line Tools
```bash
# Show help
nanda-adapter --help
# List available examples
nanda-adapter --list-examples
# Run specific examples
nanda-pirate # Simple pirate agent
nanda-pirate-langchain # LangChain pirate agent
nanda-sarcastic # CrewAI sarcastic agent
```
### Architecture
The NANDA framework consists of:
1. **AgentBridge**: Core communication handler
2. **Message Improvement System**: Pluggable improvement logic
3. **Registry System**: Agent discovery and registration
4. **A2A Communication**: Agent-to-agent messaging
5. **Flask API**: External communication interface
### Support
For issues and questions:
- GitHub Issues: https://github.com/nanda-ai/nanda-adapter/issues
## Changelog
### v1.0.0
- Initial release
- Basic NANDA framework
- LangChain integration
- CrewAI integration
- Example agents
- Production deployment support
Raw data
{
"_id": null,
"home_page": "https://github.com/projnanda/adapter.git",
"name": "nanda-adapter",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "nanda ai agent framework",
"author": "NANDA Team",
"author_email": "support@nanda.ai",
"download_url": "https://files.pythonhosted.org/packages/2c/f6/e718222983641ec376d3c64b988266a774391ba0b055b1df57f9802ac591/nanda_adapter-1.0.1.tar.gz",
"platform": null,
"description": "# NANDA Adapter\nBring your local agent. Make it **persistent**, **discoverable** and **interoperable** on the global internet with NANDA.\n\nHelp us build an Open and Vibrant Internet of Agents\n\n## Features\n\n- **Multiple AI Frameworks**: Support for LangChain, CrewAI, and any custom logic.\n- **Multi-protocol Communication**: Built-in protocol that allows universal communication\n- **Global Index**: Automatic agent discovery via MIT NANDA Index\n- **SSL Support**: Production-ready with Let's Encrypt certificates\n\n \n<img width=\"768\" height=\"457\" alt=\"Screenshot 2025-07-15 at 8 41 36\u202fPM\" src=\"https://github.com/user-attachments/assets/f23e32dd-ddda-43a5-a405-03ad4e9dbc5a\" />\n\n## Installation\n\n### Basic Installation\n\n```bash\npip install nanda-adapter\n```\n\n## Steps to create a test example using this repo\n\n### 1. Clone this repository\n\n> git clone github.com/projnanda/adapter\n\n### 2. Setup dependencies\n> cd nanda_agent/examples\n\n> pip install -r requirements.txt\n\n### 3. Configure your Domain and SSL Certificates (move certificates into current path)\n\n> sudo certbot certonly --standalone -d <YOUR_DOMAIN_NAME.COM>\n\n> sudo cp -L /etc/letsencrypt/live/<YOUR_DOMAIN_NAME.COM>/fullchain.pem .\n\n> sudo cp -L /etc/letsencrypt/live/<YOUR_DOMAIN_NAME.COM>/privkey.pem .\n\n> sudo chown $USER:$USER fullchain.pem privkey.pem\n\n> chmod 600 fullchain.pem privkey.pem`\n\n### 4. Set Your enviroment variables ANTHROPIC_API_KEY (For running your personal hosted agents, need API key and your own domain)\n\n> export ANTHROPIC_API_KEY=\"your-api-key-here\n\n> export DOMAIN_NAME=\"<YOUR_DOMAIN_NAME.COM>\n\n### 5. Run an example agent (langchain_pirate.py)\n> nohup python3 langchain_pirate.py > out.log 2>&1 &\n\n### 6. Get your enrollment link from Log File\n> cat out.log\n\n\n## Examples for How to create your own agent\nYou can create an agent using your custom ReACT framework or any agent package like LangChain, CrewAI etc.\n\nThen, you can deploy to internet of Agents using one line of code via NANDA.\n\n### 1. Custom Agent\n\n```bash\n2.1 Write your improvement logic using the framework you like. Here it is a simple moduule without any llm call.\n2.4 Move this file into your server(the domain should match to the IP address) and run this python file in background \n```\n\n```python\n#!/usr/bin/env python3\nfrom nanda_adapter import NANDA\nimport os\n\ndef create_custom_improvement():\n \"\"\"Create your custom improvement function\"\"\"\n \n def custom_improvement_logic(message_text: str) -> str:\n \"\"\"Transform messages according to your logic\"\"\"\n try:\n # Your custom transformation logic here\n improved_text = message_text.replace(\"hello\", \"greetings\")\n improved_text = improved_text.replace(\"goodbye\", \"farewell\")\n \n return improved_text\n except Exception as e:\n print(f\"Error in improvement: {e}\")\n return message_text # Fallback to original\n \n return custom_improvement_logic\n\ndef main():\n # Create your improvement function\n my_improvement = create_custom_improvement()\n \n # Initialize NANDA with your custom logic\n nanda = NANDA(my_improvement)\n \n # Start the server\n anthropic_key = os.getenv(\"ANTHROPIC_API_KEY\")\n domain = os.getenv(\"DOMAIN_NAME\")\n \n nanda.start_server_api(anthropic_key, domain)\n\nif __name__ == \"__main__\":\n main()\n```\n\n### Deploy a LangChain Agent\n\n```python\nfrom nanda_agent import NANDA\nfrom langchain_core.prompts import PromptTemplate\nfrom langchain_core.output_parsers import StrOutputParser\nfrom langchain_anthropic import ChatAnthropic\n\ndef create_langchain_improvement():\n llm = ChatAnthropic(\n api_key=os.getenv(\"ANTHROPIC_API_KEY\"),\n model=\"claude-3-haiku-20240307\"\n )\n \n prompt = PromptTemplate(\n input_variables=[\"message\"],\n template=\"Make this message more professional: {message}\"\n )\n \n chain = prompt | llm | StrOutputParser()\n \n def langchain_improvement(message_text: str) -> str:\n return chain.invoke({\"message\": message_text})\n \n return langchain_improvement\n\n# Use it\nnanda = NANDA(create_langchain_improvement())\n# Start the server\nanthropic_key = os.getenv(\"ANTHROPIC_API_KEY\")\ndomain = os.getenv(\"DOMAIN_NAME\")\n\nnanda.start_server_api(anthropic_key, domain)\n```\n\n### Deploy a CrewAI Agent\n\n```python\nfrom nanda_agent import NANDA\nfrom crewai import Agent, Task, Crew\nfrom langchain_anthropic import ChatAnthropic\n\ndef create_crewai_improvement():\n llm = ChatAnthropic(\n api_key=os.getenv(\"ANTHROPIC_API_KEY\"),\n model=\"claude-3-haiku-20240307\"\n )\n \n improvement_agent = Agent(\n role=\"Message Improver\",\n goal=\"Improve message clarity and professionalism\",\n backstory=\"You are an expert communicator.\",\n llm=llm\n )\n \n def crewai_improvement(message_text: str) -> str:\n task = Task(\n description=f\"Improve this message: {message_text}\",\n agent=improvement_agent,\n expected_output=\"An improved version of the message\"\n )\n \n crew = Crew(agents=[improvement_agent], tasks=[task])\n result = crew.kickoff()\n return str(result)\n \n return crewai_improvement\n\n# Use it\nnanda = NANDA(create_crewai_improvement())\n# Start the server\nanthropic_key = os.getenv(\"ANTHROPIC_API_KEY\")\ndomain = os.getenv(\"DOMAIN_NAME\")\n\nnanda.start_server_api(anthropic_key, domain)\n```\n\n## Deploy from Scratch on a barebones machine (Ubuntu on Linode or Amazon Linux on EC2)\n\n```bash\nAssuming your customized improvement logic is in langchain_pirate.py\n\n2. ssh into the server, ensure the latest software is in the system\nUbuntu Command : ssh root@<IP>\n sudo apt update && sudo apt install python3 python3-pip python3-venv certbot\n\nEC2 cmd : ssh -i <YOUR_PEM_KEY> ec2-user@<IP>\n sudo dnf update -y && sudo dnf install -y python3.11 python3.11-pip certbot\n\n3. Move to the respective folder and create and Activate a virtual env in the folder where files are moved in step 1\ncmd : cd /opt/test-agents && python3 -m venv <YOUR_ENV_NAME> && source <YOUR_ENV_NAME>/bin/activate\n\nEC2 cmd: cd /home/ec2-user/test-agents && python3.11 -m <YOUR_ENV_NAME> jinoos && source <YOUR_ENV_NAME>/bin/activate\n\n4. Generate SSL certificates on this machine for your domain.\n(For ex: You should ensure in DNS an A record is mapping this domain <DOMAIN_NAME> to IP address <YOUR_IP>). Ensure the domain has to be changed\n \ncmd : sudo certbot certonly --standalone -d <YOUR_DOMAIN_NAME> \n\n5. Move certificates to current folder for access and provide required access\nEnsure the domain has to be changed\n\n sudo cp -L /etc/letsencrypt/live/<YOUR_DOMAIN_NAME>/fullchain.pem .\n sudo cp -L /etc/letsencrypt/live/<YOUR_DOMAIN_NAME>/privkey.pem .\n sudo chown $USER:$USER fullchain.pem privkey.pem\n chmod 600 fullchain.pem privkey.pem\n\n6. Install the requirements file \ncmd : python -m pip install --upgrade pip && pip3 install -r requirements.txt \n\n7. Ensure the env variables are available either through .env or you can provide export \ncmd : export ANTHROPIC_API_KEY=my-anthropic-key && export DOMAIN_NAME=my-domain\n\n8. Run the new improvement logic as a batch process \ncmd : nohup python3 langchain_pirate.py > out.log 2>&1 &\n\n9. Open the log file and you could find the agent enrollment link\ncmd : cat out.log\n\n10. Take the link and go to browser for registration\n\n```\n\nThe framework will automatically:\n- Generate SSL certificates using Let's Encrypt\n- Set up proper agent registration\n- Configure production-ready logging\n\n\n## Appendix: Configuration Details\n\n### Environment Variables\nYou need the following environment details ()\n\n- `ANTHROPIC_API_KEY`: Your Anthropic API key (required)\n- `DOMAIN_NAME`: Domain name for SSL certificates (required)\n- `AGENT_ID`: Custom agent ID (optional, auto-generated if not provided)\n- `PORT`: Agent bridge port (optional, default: 6000)\n- `IMPROVE_MESSAGES`: Enable/disable message improvement (optional, default: true)\n\n### Production Deployment\n\nFor production deployment with SSL:\n\n```bash\nexport ANTHROPIC_API_KEY=\"your-api-key\"\nexport DOMAIN_NAME=\"your-domain.com\"\nnanda-pirate\n```\n\n### API Endpoints\n\nWhen running with `start_server_api()`, the following endpoints are available:\n\n- `GET /api/health` - Health check\n- `POST /api/send` - Send message to agent\n- `GET /api/agents/list` - List registered agents\n- `POST /api/receive_message` - Receive message from agent\n- `GET /api/render` - Get latest message\n\n### Agent Communication\n\nAgents can communicate with each other using the `@agent_id` syntax:\n\n```\n@agent123 Hello there!\n```\n\nThe message will be improved using your custom logic before being sent.\n\n### Command Line Tools\n\n```bash\n# Show help\nnanda-adapter --help\n\n# List available examples\nnanda-adapter --list-examples\n\n# Run specific examples\nnanda-pirate # Simple pirate agent\nnanda-pirate-langchain # LangChain pirate agent\nnanda-sarcastic # CrewAI sarcastic agent\n```\n\n### Architecture\n\nThe NANDA framework consists of:\n\n1. **AgentBridge**: Core communication handler\n2. **Message Improvement System**: Pluggable improvement logic\n3. **Registry System**: Agent discovery and registration\n4. **A2A Communication**: Agent-to-agent messaging\n5. **Flask API**: External communication interface\n\n### Support\n\nFor issues and questions:\n- GitHub Issues: https://github.com/nanda-ai/nanda-adapter/issues\n \n## Changelog\n\n### v1.0.0\n- Initial release\n- Basic NANDA framework\n- LangChain integration\n- CrewAI integration\n- Example agents\n- Production deployment support\n",
"bugtrack_url": null,
"license": null,
"summary": "Customizable AI Agent Communication Framework with pluggable message improvement logic",
"version": "1.0.1",
"project_urls": {
"Homepage": "https://github.com/projnanda/adapter.git"
},
"split_keywords": [
"nanda",
"ai",
"agent",
"framework"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "5a91951db3109fa909f242c7c33b3e347ea1b0935bc9fb5a1d63dd293de91e2c",
"md5": "2b757d9cf634d7d18fddb317e0a487ce",
"sha256": "3951fa53bee224b45bc17c1440878e3e5a13ab58715a1cdb59899f8e338e0968"
},
"downloads": -1,
"filename": "nanda_adapter-1.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2b757d9cf634d7d18fddb317e0a487ce",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 29458,
"upload_time": "2025-07-21T16:41:10",
"upload_time_iso_8601": "2025-07-21T16:41:10.159740Z",
"url": "https://files.pythonhosted.org/packages/5a/91/951db3109fa909f242c7c33b3e347ea1b0935bc9fb5a1d63dd293de91e2c/nanda_adapter-1.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "2cf6e718222983641ec376d3c64b988266a774391ba0b055b1df57f9802ac591",
"md5": "b360f78d8378f420d8f681cab5224f31",
"sha256": "d2cc02d163ae5e9cabc2c4726f18b21ffa6d1c6978c238473f34c725dca36358"
},
"downloads": -1,
"filename": "nanda_adapter-1.0.1.tar.gz",
"has_sig": false,
"md5_digest": "b360f78d8378f420d8f681cab5224f31",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 28426,
"upload_time": "2025-07-21T16:41:12",
"upload_time_iso_8601": "2025-07-21T16:41:12.975593Z",
"url": "https://files.pythonhosted.org/packages/2c/f6/e718222983641ec376d3c64b988266a774391ba0b055b1df57f9802ac591/nanda_adapter-1.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-21 16:41:12",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "projnanda",
"github_project": "adapter",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "flask",
"specs": []
},
{
"name": "anthropic",
"specs": []
},
{
"name": "requests",
"specs": []
},
{
"name": "python-a2a",
"specs": [
[
"==",
"0.5.6"
]
]
},
{
"name": "mcp",
"specs": []
},
{
"name": "anthropic",
"specs": []
},
{
"name": "python-dotenv",
"specs": []
},
{
"name": "flask-cors",
"specs": []
},
{
"name": "pymongo",
"specs": []
}
],
"lcname": "nanda-adapter"
}
JSON
