CrewAI Studio

A Streamlit-based graphical interface for building and running CrewAI agents and tasks without writing code, supporting Conda or virtual-environment installs on Windows, Linux, and macOS.

Agent frameworks

Visit website github.com

CrewAI Studio provides a user-friendly interface, written in Streamlit, for interacting with CrewAI so that people who do not want to write code can still configure and run crews of agents. It runs on Windows, Linux, and macOS, installed through Docker/docker-compose or a Conda or Python virtual environment.

Features include a knowledge-source manager for crews, a history of previous results, built-in CrewAI tools for calling APIs, writing files, and web scraping, custom tools, and the ability to export a crew as a single-page Streamlit app. Supported LLM providers include OpenAI, Groq, Anthropic, Ollama, Grok, and LM Studio.

The project is now in low-maintenance mode: the author is not adding new features, but still applies security and critical bug fixes, and welcomes pull requests.

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.
- Agent frameworks
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.
- Agent frameworks
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.
- Coding agents
- Agent frameworks

More in Agent frameworks

Recurse

ProofForge

local-coder

Cookies