matrx-ai 0.1.6

Matrx AI Engine — unified AI orchestration backend with multi-provider LLM support, streaming, tool execution, and conversation persistence.

matrx-ai

Matrx AI Engine — unified AI orchestration backend with multi-provider LLM support, streaming, tool execution, and conversation persistence.

Installation

# Core library only (AI providers, tools, conversation management)
pip install matrx-ai

# With the FastAPI server layer
pip install "matrx-ai[server]"

# Or with uv
uv add matrx-ai
uv add "matrx-ai[server]"

Quick Start (library)

import matrx_ai

# Initialize once at startup (registers the database connection)
matrx_ai.initialize()

# Use the AI engine directly
from matrx_ai.orchestrator import execute_ai_request
from matrx_ai.config.unified_config import UnifiedConfig

Quick Start (server)

uv sync --extra server   # install with server deps
cp .env.example .env     # fill in your API keys
make dev                 # start dev server on :8000

Environment Variables

Copy .env.example to .env and fill in the required keys:

• AI provider keys: OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, etc.
• Supabase: SUPABASE_URL, SUPABASE_ANON_KEY, SUPABASE_SERVICE_ROLE_KEY, SUPABASE_MATRIX_*

Common Commands

make dev        # dev server with reload on :8000
make run        # production mode (matrx-ai-server)
make lint       # ruff check
make fmt        # ruff format
make typecheck  # pyright
make test       # pytest -v

Publishing a New Release

./scripts/publish.sh              # patch bump  0.1.0 → 0.1.1
./scripts/publish.sh --minor      # minor bump  0.1.0 → 0.2.0
./scripts/publish.sh --major      # major bump  0.1.0 → 1.0.0
./scripts/publish.sh --message "feat: add new provider"
./scripts/publish.sh --dry-run    # preview without committing

Version History

Version	Highlights
v0.1.6	Patch release
v0.1.5	Patch release
v0.1.4	Patch release
v0.1.3	Patch release
v0.1.2	Patch release
v0.1.1	Patch release
v0.1.0	Initial release — multi-provider AI orchestration, streaming, tool system, conversation persistence