Clean-room multi-agent swarm intelligence system
Project description
SandFish
A Clean-Room Multi-Agent Swarm Intelligence System
Built from scratch with security-first principles, zero foreign dependencies, and native OMPA integration.
Overview
SandFish is a distributed multi-agent simulation engine for prediction, scenario planning, and collective intelligence. Unlike foreign alternatives, SandFish is:
- 100% auditable — All code in English, fully documented
- Zero cloud lock-in — OMPA-native memory (no Zep, no external APIs required)
- Security-first — Production-grade from day one
- ZTB compliant — Zero token burn, minimal operational cost
Architecture
SandFish/
├── core/ # Simulation engine
├── memory/ # OMPA integration
├── agents/ # Swarm agent definitions
├── api/ # FastAPI REST/WebSocket
├── security/ # Audit, sandbox, crypto
└── tests/ # Comprehensive coverage
Quick Start
# Install
pip install sandfish
# Configure
export OMPA_VAULT_PATH="/path/to/vault"
export LLM_API_KEY="your-key"
# Run
sandfish orchestrator --config config.yaml
Security
See SECURITY.md for audit reports and hardening guide.
License
MIT — See LICENSE
Built with 🤖 in the desert.
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 Distributions
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 sandfish-0.1.0-py3-none-any.whl.
File metadata
- Download URL: sandfish-0.1.0-py3-none-any.whl
- Upload date:
- Size: 20.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a3a5b3398c899468746a9d9f538a6724c3dd1512c15d7a50beee03a72c8efaf0
|
|
| MD5 |
7deb02d89b9d09fa585399f157cedc5e
|
|
| BLAKE2b-256 |
2520b51fb7e5e07a27df3b389791e70c34b0c09c7394b1b1adce7de02b4cf107
|