Back to directory

CrewAI-GUI

A drag-and-drop, node-based desktop frontend for designing CrewAI multi-agent workflows, which exports the design to JSON and can run it against GPT-4 or a local Ollama model.

Visit website (opens in a new tab)langgraph-gui.github.io
CrewAI-GUI

CrewAI-GUI is a PySide6 desktop application that lets you design CrewAI agent workflows visually, as a directed acyclic graph of nodes, instead of writing the CrewAI Python configuration by hand. Designs can be saved, loaded, and exported as JSON files for modularity and reuse.

A separate backend process converts the exported JSON graph into CrewAI tasks and agents and runs them, supporting either the GPT-4 API or a local Ollama model such as Mistral, and writes output to a log file. Both the frontend and backend can be packaged into standalone executables, with PyInstaller for the Qt frontend and cx_Freeze for the Python backend. The current version supports a limited set of CrewAI node types and slots, with more advanced CrewAI variables and features planned for future releases.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.