OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

AgenticFleet

AgenticFleet is an open-source Python framework for routing tasks among specialized AI agents through analysis, routing, execution, progress and quality phases. It uses DSPy for structured reasoning and Microsoft Agent Framework for execution, with FastAPI, Typer and streamed CLI or web events in its stated stack.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AgenticFleet — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use AgenticFleet when the central requirement is coordinating several specialized agents through an explicit staged pipeline and exposing run activity through CLI or web clients.

Who it is for

  • Developers building multi-agent systems
  • Teams designing domain-specific agent workflows
  • Operators seeking a self-hosted orchestration backend
  • Python teams needing CLI or browser-visible agent-run events

Documented uses

  • Route incoming tasks to specialized agents
  • Coordinate staged multi-agent execution
  • Stream progress and quality events to clients
  • Connect agent workflows with search, browser, code-execution and MCP adapters
  • Run an orchestration backend with local or Azure-oriented storage options
Before you choose

Requirements & limits

The repository is public and displays an MIT license badge. The documented setup requires an OpenAI API key; Tavily is optional for web search, while Azure credentials apply to optional Azure integrations.

  • The core implementation is Python and specifies Python 3.12 or 3.13.
  • DSPy and Microsoft Agent Framework divide reasoning and execution roles in the stated design.
  • FastAPI and Typer support web-backend and CLI usage.
  • The frontend stack includes React, TypeScript, Vite and real-time SSE/WebSocket streaming.
  • SQLite/local persistence and Azure Cosmos DB are both described as storage options.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up AgenticFleet for local development

Prepare the documented Python and frontend development environment.

Before you start

  • Python 3.12 or 3.13
  • uv
  • Node.js 18 or later for the frontend
  • An OpenAI API key
  • The public AgenticFleet repository

Steps

  1. Clone https://github.com/Qredence/agentic-fleet and change into the repository directory.

  2. Run make dev-setup to install the documented Python, frontend and pre-commit dependencies.

  3. Copy .env.example to .env.

  4. Set OPENAI_API_KEY and other required environment variables in .env.

Expected outcome

The repository is configured according to its documented development setup path.

Guide limitations

  • The setup instructions do not establish that a particular deployment or workflow will run successfully.
  • Tavily, Azure, tracing and other integrations require their respective optional configuration.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
AgenticFleetRoute incoming tasks to specialized agentsCLI, Cloud, Self-hosted, ServerThe repository is public and displays an MIT license badge. The documented setup requires an OpenAI API key; Tavily is optional for web search, while Azure credentials apply to optional Azure integrations.
MassgenRun multiple AI agents against the same user task.CLIThe repository documents installation through pip or uv and requires Python 3.11 or later. Setup can configure API keys for OpenAI, Anthropic, Google and xAI; credentials are needed for the selected model backends.
Langchain Multi Agents BoilerplateRoute incoming football questions to model and agent workflows according to task complexity.WebThe repository is public and specifies an MIT license. Running the application requires OpenAI and Groq API keys and a Redis server.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
Qredence/agentic-fleet · Official homepage title · retained in its source language
How we review sourcesSuggest a correction