Skip to main content

A powerful multi-agent system for adaptive AI reasoning and automation

Project description

AgenticFleet

A powerful multi-agent system for adaptive AI reasoning and automation. AgenticFleet combines Chainlit's interactive interface with AutoGen's multi-agent capabilities to create a flexible, powerful AI assistant platform.

Pepy Total Downloads

GitHub License GitHub forks GitHub Repo stars

Codacy Badge

chainlitlight

Key Features

  • Multi-Agent System: Coordinated team of specialized AI agents

    • Code generation and analysis
    • Web content processing
    • File system operations
  • Interactive Interface

    • Real-time communication via Chainlit
    • Code syntax highlighting
    • Markdown rendering
    • File upload/download support
  • Advanced Capabilities

    • OAuth authentication integration
    • Configurable agent behaviors
    • Comprehensive error handling
    • Progress tracking
  • Developer-Friendly

    • Easy-to-use CLI
    • Extensive documentation
    • Flexible configuration
    • Active community support

Quick Start

  1. Install AgenticFleet using uv (recommended):
uv pip install agentic-fleet
playwright install --with-deps chromium
  1. Copy and configure environment variables:
# Copy the example environment file
cp .env.example .env

# Open .env and update with your values
# Required: Add your Azure OpenAI credentials
# Recommended: Configure OAuth settings
  1. Start the server:
agenticfleet start

The web interface will be available at http://localhost:8001.

Documentation

Configuration

The .env.example file contains all required and recommended settings. Copy it to .env and update with your values:

# Required: Azure OpenAI Configuration
AZURE_OPENAI_API_KEY=your_api_key
AZURE_OPENAI_ENDPOINT=your_endpoint
AZURE_OPENAI_DEPLOYMENT=your_deployment
AZURE_OPENAI_MODEL=your_model

## Recommended: OAuth Configuration
OAUTH_CLIENT_ID=your_client_id
OAUTH_CLIENT_SECRET=your_client_secret
OAUTH_REDIRECT_URI=http://localhost:8001/oauth/callback

Development

Prerequisites

  • Python 3.10-3.12 (Python 3.13 is not yet supported)
  • uv package manager (recommended)
  • Azure OpenAI API access

Setup

  1. Clone and install:
git clone https://github.com/qredence/agenticfleet.git
cd agenticfleet
pip install uv
uv pip install -e ".[dev]"
  1. Run tests:
pytest tests/

Contributing

We welcome contributions! Please see our Contributing Guide for details.

Security

For security concerns, please review our Security Policy.

License

This project is licensed under the Apache-2.0 License - see the LICENSE file for details.

Support

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

agentic_fleet-0.4.60.tar.gz (35.2 kB view details)

Uploaded Source

Built Distribution

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

agentic_fleet-0.4.60-py3-none-any.whl (8.1 kB view details)

Uploaded Python 3

File details

Details for the file agentic_fleet-0.4.60.tar.gz.

File metadata

  • Download URL: agentic_fleet-0.4.60.tar.gz
  • Upload date:
  • Size: 35.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for agentic_fleet-0.4.60.tar.gz
Algorithm Hash digest
SHA256 a3d657be574d2300c2070b40078d61a6ed452217f49ddf29675ce715b8c82ac7
MD5 2bfbacc167927989337e386ce0986e06
BLAKE2b-256 9124bd8831e0e02d031ccea0b7a54f493f5c65f63da02f6e346c4e0a423e6b1a

See more details on using hashes here.

Provenance

The following attestation bundles were made for agentic_fleet-0.4.60.tar.gz:

Publisher: python-publish.yml on Qredence/AgenticFleet

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

File details

Details for the file agentic_fleet-0.4.60-py3-none-any.whl.

File metadata

  • Download URL: agentic_fleet-0.4.60-py3-none-any.whl
  • Upload date:
  • Size: 8.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for agentic_fleet-0.4.60-py3-none-any.whl
Algorithm Hash digest
SHA256 7b1652a6658ab4628fcb69908f13cb8df1b863b987015534091a72a58c8921f8
MD5 4bf63280410c5d76726a1f7b147ca0aa
BLAKE2b-256 9e2081747fcdb10f91d1ef5fb10b82fa1be982477358cead40a4e0119256adba

See more details on using hashes here.

Provenance

The following attestation bundles were made for agentic_fleet-0.4.60-py3-none-any.whl:

Publisher: python-publish.yml on Qredence/AgenticFleet

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