AgentStr
AgentStr is an extension of Agno AI agents that enables peer-to-peer agent communication using the Nostr protocol.
Overview
AgentStr allows AI agents operated by different organizations to communicate and collaborate. For example:
- Agent A from Company A can coordinate with Agent B from Company B to execute a transaction
- Agents can discover and interact with each other through the decentralized Nostr network
- No central authority or intermediary required
Project Structure
agentstr/
├── src/ # Source code
│ └── agentstr/
│ ├── __init__.py
│ ├── buyer.py
│ ├── buyer.pyi
│ ├── merchant.py
│ ├── merchant.pyi
│ ├── models.py
│ ├── models.pyi
│ ├── nostr.py
│ ├── nostr.pyi
│ └── py.typed
├── tests/ # Test files
├── docs/ # Documentation
├── examples/ # Example implementations
└── ...
Features
Current Features
- Create Merchant agents with Nostr identities:
- Publish and manage merchant products using NIP-15 marketplace protocol
- Create merchant stalls to organize products
- Handle shipping zones and costs
- Secure communication using Nostr keys
- Create Buyer agents:
- Retrieve a list of sellers from the relay using NIP-15 marketplace protocol
- Find an specific seller by name or public key
- Refresh the list of sellers from the relay
Roadmap
- Create marketplace with stalls
- Expand buyer agent to include more features
- Support additional Nostr NIPs
- Add more agent interaction patterns
Installation
# Create a new python environment
python3 -m venv ~/.venvs/aienv
source ~/.venvs/aienv/bin/activate
# Install agentstr
pip install --upgrade pip
pip install agentstr
Examples
You can find example code in the examples directory.
To install the examples clone the repository and navigate to the examples directory:
git clone https://github.com/Synvya/agentstr.git
cd agentstr/examples/
Each example has its own README with instructions on how to run it.
Documentation
For more detailed documentation and examples, see Docs
Development
See CONTRIBUTING.md for:
- Development setup
- Testing instructions
- Contribution guidelines
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Agno - For their AI agent framework
- Rust-Nostr - For their Python Nostr SDK
- Nostr Protocol - For the protocol specification
Metadata
Release files for agentstr 0.1.16
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentstr-0.1.16.tar.gz | 20.7 kB | With provenance | Details for agentstr-0.1.16.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentstr-0.1.16-py3-none-any.whl | Python 3 | none | any | Details for agentstr-0.1.16-py3-none-any.whl |
Total release size: 43.2 kB
Release files / agentstr-0.1.16.tar.gz
| Download URL | agentstr-0.1.16.tar.gz |
|---|---|
| Size | 20.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4f7a0661df5466e93153189816b562788d0aafb08561abf38c4e32d748c4c66a
|
|
BLAKE2b-256 checksum How to use checksums |
3495f4841f1a9f267d2886d0a85fb9e2942aaa65175162938b9862c8856963b6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 1, 2025.
Transparency logRelease files / agentstr-0.1.16-py3-none-any.whl
| Download URL | agentstr-0.1.16-py3-none-any.whl |
|---|---|
| Size | 22.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3720e5f95042c638be318812c56a6484673bac9e1ea89ec32544976451f41dd5
|
|
BLAKE2b-256 checksum How to use checksums |
2c79170728df32193d3dfcf9702884d533fe01f46e9a1e36efdac3bcb8b73412
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 1, 2025.
Transparency logSecurity for agentstr 0.1.16
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for agentstr-0.1.16.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 1, 2025.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.