Cognitive operating system for AI agents — 490 tools across 28 Gana meta-tools, 5D holographic memory, ethical governance, and 7-language polyglot acceleration
Project description
WhiteMagic — Agentic AI Platform (v23.0.0)
A polyglot agentic AI platform with Python core, Rust performance bridges, and multi-language support for AI agents, memory systems, and distributed orchestration.
Installation
Lite (MCP + CLI only)
pip install -e ".[dev,mcp,cli]"
Core (standard installation with database + networking)
pip install -e ".[dev,mcp,cli,core]"
Heavy-tier (full ML stack with embeddings + search)
pip install -e ".[dev,mcp,cli,heavy]"
Quick Start
MCP Server (FastMCP)
python -m whitemagic.run_mcp
MCP Server (Lean — stdlib only)
python -m whitemagic.run_mcp_lean
CLI
wm status
wm doctor
Project Structure
whitemagic/
├── core/ # Core systems (memory, intelligence, governance)
├── tools/ # Tool handlers and dispatch
├── security/ # Security, sanitization, tool gating
├── config/ # Configuration and paths
├── cli/ # Command-line interface
├── rust/ # Rust bridge implementations
└── polyglot/ # Multi-language bridges (Koka, Zig, Mojo, etc.)
Development
Run Tests
make test # Full test suite
make test-core # Release-critical contract tests only (fast)
pytest tests/ # Direct pytest invocation
Release Validation
make check-ship # Validate ship surface hygiene
Lint & Typecheck
make lint
make typecheck
Build Rust Extensions
cd whitemagic-rust
maturin develop
Architecture
- Dispatch Pipeline: 9 composable middlewares (sanitizer, circuit breaker, rate limiter, security monitor, tool permissions, maturity gate, governor, observability)
- Memory System: Unified SQLite backend with holographic spatial index, galactic distance tracking, and consolidation
- PRAT Ganas: 28 meta-tools organized into 4 quadrants (Horn, Dipper, Willow, Room)
- Polyglot Bridges: Rust, Koka, Zig, Mojo, Go, Elixir, Julia, Haskell, Erlang, Nim
Documentation
See the workspace root ../README.md for monorepo structure and project overview.
See docs/ for detailed documentation.
License
MIT License — see LICENSE file at repository root.
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 whitemagic-23.0.0.tar.gz.
File metadata
- Download URL: whitemagic-23.0.0.tar.gz
- Upload date:
- Size: 2.0 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2d654bf8691c77c320c55efda8111a53346423730904d6ba595d74c7e73bd869
|
|
| MD5 |
22d581969f693bbffb3409a18c67d206
|
|
| BLAKE2b-256 |
b31fca64cf16235bac9f759fd98af051def66559bdf313ea8c1a7cae3b23bf56
|
File details
Details for the file whitemagic-23.0.0-py3-none-any.whl.
File metadata
- Download URL: whitemagic-23.0.0-py3-none-any.whl
- Upload date:
- Size: 2.4 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1ef2a594bc17a41a52fed917e99af4385e1cf43d5fe4d077dfaaee23e12b0ace
|
|
| MD5 |
9496f0455604ac56eb2bf19c32f1d069
|
|
| BLAKE2b-256 |
bb6336d7a207c2a72955c2329613835bec41845928d52364bea4954f62b8774e
|