Synapse
Kubernetes-like orchestration system for AI agents
Synapse is a powerful framework for orchestrating AI agents with Kubernetes-like semantics. It provides a simple YAML-based workflow definition and a rich CLI for managing agent-based applications.
Features
- 🚀 Kubernetes-inspired agent orchestration
- 📊 Built-in observability with a web dashboard
- ⚡ Fast execution with parallel agent processing
- 🔄 Dependency management between agents
- 📝 YAML-based workflow definitions
- 🔍 Tracing and logging for debugging
- 🎨 Rich CLI with beautiful output
Installation
Install from PyPI:
pip install agent-synapse
Quick Start
- Initialize a new Synapse project:
synapse init
This creates an agents/ directory with demo agents (summarize.py and classify.py) and a workflow.yaml file.
- Run the demo workflow:
synapse run workflow.yaml --prompt "Your text here"
- View the dashboard (optional):
synapse serve
# Open http://localhost:8080 in your browser
- Modify the agents in the
agents/directory to suit your needs!
Documentation
For detailed documentation, please visit the Synapse Documentation.
Key Concepts
- Agents: Independent units of work that process inputs and produce outputs
- Workflows: YAML files that define the agent graph and their dependencies
- Traces: Detailed execution logs stored in
synapse_traces.db - Dashboard: Web UI for monitoring and debugging agent executions
Examples
Check out the examples directory for sample workflows and agent implementations.
Development
- Clone the repository:
git clone https://github.com/YakshithK/synapse.git
cd synapse
- Set up a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -e ".[dev]"
- Run tests:
pytest
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Support
For support, please open an issue on GitHub.
Metadata
Release files for agent-synapse 0.2.1
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 |
|---|---|---|---|---|
| agent_synapse-0.2.1.tar.gz | 21.6 kB | Without provenance | Details for agent_synapse-0.2.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agent_synapse-0.2.1-py3-none-any.whl | Python 3 | none | any | Details for agent_synapse-0.2.1-py3-none-any.whl |
Total release size: 44.2 kB
Release files / agent_synapse-0.2.1.tar.gz
| Download URL | agent_synapse-0.2.1.tar.gz |
|---|---|
| Size | 21.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7a1c1a620e506342de12afd28edc11ae9e721ea9152aba27e04801fd97e50447
|
|
BLAKE2b-256 checksum How to use checksums |
f1f2aa9e04a32e309c20e1cd02b0b7a3ae794fbd92b72bfc8b1dbf4dd1d594b6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Release files / agent_synapse-0.2.1-py3-none-any.whl
| Download URL | agent_synapse-0.2.1-py3-none-any.whl |
|---|---|
| Size | 22.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1ab6e1ad4c9598b93f0c8fb1e099c96f44b47a430f2e3ffa489ce5bbe403a82e
|
|
BLAKE2b-256 checksum How to use checksums |
8c3ef0f2af9c994aaa047c36cc915aa5a0dd017097a5866855052eefce5d3936
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Security for agent-synapse 0.2.1
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A 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.