Skip to main content

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

Project description

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  (e.g. 1.2.3 → 1.2.4)
./scripts/publish.sh --minor      # minor bump  (e.g. 1.2.3 → 1.3.0)
./scripts/publish.sh --major      # major bump  (e.g. 1.2.3 → 2.0.0)
./scripts/publish.sh --message "feat: add new provider"
./scripts/publish.sh --dry-run    # preview without committing

Version History

Version Highlights
v0.1.26 Patch release
v0.1.25 Patch release
v0.1.24 Patch release
v0.1.23 Patch release
v0.1.22 Patch release
v0.1.21 Patch release
v0.1.20 Patch release
v0.1.19 Patch release
v0.1.18 Patch release
v0.1.17 Patch release
v0.1.16 Patch release
v0.1.15 Patch release
v0.1.14 Patch release
v0.1.13 Patch release
v0.1.12 Patch release
v0.1.11 Patch release
v0.1.10 Patch release
v0.1.9 Patch release
v0.1.8 Patch release
v0.1.7 Patch release
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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

matrx_ai-0.1.26.tar.gz (883.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

matrx_ai-0.1.26-py3-none-any.whl (642.3 kB view details)

Uploaded Python 3

File details

Details for the file matrx_ai-0.1.26.tar.gz.

File metadata

  • Download URL: matrx_ai-0.1.26.tar.gz
  • Upload date:
  • Size: 883.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for matrx_ai-0.1.26.tar.gz
Algorithm Hash digest
SHA256 3e492b15d8259471645022113cb39718bae1ec2ca1ce2d2bc6cc86b88ff49742
MD5 a90e6f3999a2694faa893d3559772836
BLAKE2b-256 255a3a2d787c6d16732a1bc44d149b3572e55cd90447931934a3291bbd4429e6

See more details on using hashes here.

Provenance

The following attestation bundles were made for matrx_ai-0.1.26.tar.gz:

Publisher: publish.yml on armanisadeghi/matrx-ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file matrx_ai-0.1.26-py3-none-any.whl.

File metadata

  • Download URL: matrx_ai-0.1.26-py3-none-any.whl
  • Upload date:
  • Size: 642.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for matrx_ai-0.1.26-py3-none-any.whl
Algorithm Hash digest
SHA256 3774a9665fdbd66cd1c913d30ffbe7b067e85191fd2df7fa9a8d649ee6b9f0c2
MD5 fbe0695aed5085f6c7453b771f866720
BLAKE2b-256 24045a65a3a5757699c7a3a50efb7764c790f5e81e6a4748be98b699ec739999

See more details on using hashes here.

Provenance

The following attestation bundles were made for matrx_ai-0.1.26-py3-none-any.whl:

Publisher: publish.yml on armanisadeghi/matrx-ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page