Crowe Logic. Universal AI Agent powered by CroweLM on Azure AI Foundry.
Project description
Crowe Logic
Universal AI agent powered by the CroweLM model stack on Azure AI Foundry. The default lineup now fronts gpt-5.4 as CroweLM Titan, gpt-5.4-pro as CroweLM Apex, and claude-opus-4-6 as CroweLM Prime, alongside CroweLM Sovereign, Nexus, Nano, Dense, and the specialist Azure tiers.
Install
pip install crowe-logic
npm i @michaelcrowe11/crowe-logic
Setup
- Deploy the CroweLM-backed Foundry models on Azure AI Foundry
- Configure credentials:
cp .env.example .env
# Fill in the Azure endpoints and API keys for the CroweLM resources
- Authenticate with Azure:
az login
- Verify the model stack:
crowe-logic deploy
- Start chatting:
crowe-logic
Usage
crowe-logic # Interactive chat (default)
crowe-logic chat # Interactive chat session
crowe-logic run "prompt" # Single prompt, get response
crowe-logic deploy # Verify provider health across the CroweLM stack
crowe-logic models sync --account <account> --resource-group <resource-group>
crowe-logic status # Show agent status
crowe-logic tools # List available tools
CroweLM Apex is wired to stream reasoning summaries through both the terminal UI and crowe-logic headless when the Azure Responses API emits them, so hosts that consume the JSON event stream can render reasoning deltas before answer tokens.
Extra Models
The base MODEL_CHAIN can now be extended without editing source. Crowe Logic will load extra model entries from:
CROWE_LOGIC_EXTRA_MODELS_JSONCROWE_LOGIC_EXTRA_MODELS_PATHconfig/models.extra.json~/.config/crowe-logic/models.extra.json~/.crowe-logic/models.extra.json
Start from config/models.extra.example.json and save your generated file as config/models.extra.json, or point CROWE_LOGIC_EXTRA_MODELS_PATH at it.
If you already have Azure deployments and want to turn them into Foundry model entries, generate the file with:
crowe-logic models sync --account <account> --resource-group <resource-group>
By default that writes to ~/.config/crowe-logic/models.extra.json, which the runtime already loads. Use --output config/models.extra.json if you want a project-local registry instead.
You can also sync from a saved Azure CLI payload:
az cognitiveservices account deployment list --name <account> --resource-group <resource-group> --output json > deployments.json
crowe-logic models sync --input deployments.json --output config/models.extra.json
Tools (79)
| Category | Tools | Description |
|---|---|---|
| Filesystem | 4 | Read, write, edit, list files and directories |
| Shell | 1 | Execute commands with timeout and working directory |
| Web & Search | 3 | Web search, grep/ripgrep, URL fetching |
| Git | 5 | Status, diff, log, commit, clone |
| Browser Automation | 5 | Playwright-based navigation, screenshots, interaction |
| macOS / AppleScript | 3 | System automation, app control, notifications |
| iTerm2 | 18 | Windows, tabs, panes, broadcast, badges, colors, variables |
| Quantum Computing | 4 | QubitFlow circuits, Synapse evaluation, Trinity pipeline |
| Music Composition | 11 | Talon engine -- chords, drums, melody, emotion, quantum composition |
| Vision & Image | 2 | Multi-backend photo analysis (OpenRouter, Crowe Vision) |
| Video Generation | 1 | CroweLM Motion text/image-to-video on Azure AI Foundry |
| CroweLM Training | 10 | Dataset management, curation, fine-tuning pipeline |
| CroweLM Pipeline | 4 | Staging, promotion, agent runner, audit logs |
| Crowe Logic Platform | 4 | Chat, vision, grow logs, SOP generation |
| MCP Client | 4 | Search registry, list tools, call tools, stop servers |
MCP Server
The Crowe Logic platform is also available as a standalone MCP server for any MCP client:
uvx crowe-logic-mcp
See crowe-logic-mcp for configuration details.
Specialized Agents
| Agent | Focus |
|---|---|
cultivation |
Mushroom cultivation with Crowe Logic platform integration |
quantum |
Quantum computing with QubitFlow + Synapse + Trinity bridge |
music |
Music composition with Talon engine |
code |
General software development |
research |
Web research and analysis |
Environment Variables
| Variable | Description |
|---|---|
PROJECT_ENDPOINT |
Legacy Azure AI Foundry project endpoint |
MODEL_DEPLOYMENT_NAME |
Legacy Azure Agents deployment name |
AZURE_CORE_ENDPOINT |
Core CroweLM Azure OpenAI endpoint (gpt-5.4-pro, gpt-5.4-nano, Kimi-K2.5) |
AZURE_CORE_API_KEY |
API key for the core CroweLM Azure OpenAI endpoint |
AZURE_8909_ENDPOINT |
Dedicated Azure OpenAI endpoint for CroweLM Titan (gpt-5.4) |
AZURE_8909_API_KEY |
API key for the CroweLM Titan endpoint |
AZURE_4291_ENDPOINT |
Dedicated Azure OpenAI endpoint for CroweLM Oracle (grok-4-20-reasoning) |
AZURE_4291_API_KEY |
API key for the CroweLM Oracle endpoint |
AZURE_7858_ENDPOINT |
Azure OpenAI endpoint for CroweLM Reason, Vector, and Forge |
AZURE_7858_API_KEY |
API key for the CroweLM Reason / Vector / Forge endpoint |
AZURE_9536_ENDPOINT |
Azure OpenAI endpoint for CroweLM Edge and Atlas |
AZURE_9536_API_KEY |
API key for the CroweLM Edge / Atlas endpoint |
AZURE_ANTHROPIC_ENDPOINT |
Azure Anthropic endpoint for CroweLM Prime (claude-opus-4-6) |
AZURE_ANTHROPIC_API_KEY |
API key for the CroweLM Prime endpoint |
AZURE_1960_ANTHROPIC_ENDPOINT |
Azure Anthropic endpoint for CroweLM Sovereign and Classic |
AZURE_1960_API_KEY |
API key for the CroweLM Sovereign / Classic endpoint |
AZURE_GLM_ENDPOINT |
Optional GLM endpoint for CroweLM Dense (FW-GLM-5) |
AZURE_GLM_API_KEY |
API key for the CroweLM Dense endpoint |
AZURE_SORA_ENDPOINT |
Optional dedicated CroweLM Motion endpoint; falls back to AZURE_CORE_ENDPOINT |
AZURE_SORA_API_KEY |
Optional dedicated CroweLM Motion API key; falls back to AZURE_CORE_API_KEY |
AZURE_SORA_DEPLOYMENT_NAME |
CroweLM Motion deployment name, usually sora-2 |
OPENROUTER_API_KEY |
OpenRouter API key (vision fallback) |
CROWE_LOGIC_DEPLOY_TIMEOUT_SECONDS |
Optional timeout for crowe-logic deploy provider checks; defaults to 8 |
CROWE_LOGIC_URL |
Crowe Logic platform URL |
CROWE_LOGIC_KEY |
Crowe Logic API key |
Docker
docker pull michaelcrowe1111/crowe-logic:latest
docker run -it --env-file .env michaelcrowe1111/crowe-logic
GPU variant for fine-tuning:
docker build --target gpu -t crowe-logic:gpu .
Requirements
- Python 3.10+
- Azure AI Foundry account with the CroweLM lineup deployed (
gpt-5.4,gpt-5.4-pro,claude-opus-4-6, plus any optional specialist tiers you want enabled) - Azure CLI (
az login) for authentication
Author
Michael Crowe -- Crowe Logic, Inc.
License
MIT
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
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 crowe_logic-0.2.5.tar.gz.
File metadata
- Download URL: crowe_logic-0.2.5.tar.gz
- Upload date:
- Size: 634.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1ce6e1a6e26f899375d82618fc0b4d0e79e7135de7c7ebb0ae517ee4ea9db8ed
|
|
| MD5 |
66555edb09a7fc6e8de7f6ddd2c3e754
|
|
| BLAKE2b-256 |
6a781ca22cf1fd2b223f97ec0bcb96767d7fa70f067a87857a1b8c5245988301
|
File details
Details for the file crowe_logic-0.2.5-py3-none-any.whl.
File metadata
- Download URL: crowe_logic-0.2.5-py3-none-any.whl
- Upload date:
- Size: 630.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c42827850cb30cc5a89cf4168ac18a66ce1005abd065085774236a795f72721c
|
|
| MD5 |
6686e57298f8dbe58240dc753c65d714
|
|
| BLAKE2b-256 |
a41a7cfb469585c6a621cabd4c0e14a829f3c802109a48cfca22a34fa0255c1e
|