crewai-experiments
Crewai-experiments allows you to run experiments with local models as well as models available through an API, specifically for multi-agent systems in Python
- •When testing different AI models for a multi-agent system
- •When comparing performance of local vs API-based models
- •When integrating AI models with other systems through APIs
python experiments/local_experiment.py --model_path=/path/to/local/model --num_episodes=100
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Works after you add credentials — the setup agent will ask you for them.
mkdir -p ~/.claude/skills/crewai-experiments && curl -fsSL https://workflowstacks.com/api/skills/crewai-experiments/claude-skill -o ~/.claude/skills/crewai-experiments/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Crewai-experiments is a tiny Python project (~450 lines across 3 code files). Setup is light: small project — see the README for how to run it. Last commit 30 months ago, no license file, no tests found.
- 1README.mdStart here — what it does and how to install it
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Works after you add credentials — the setup agent will ask you for them.
mkdir -p ~/.claude/skills/crewai-experiments && curl -fsSL https://workflowstacks.com/api/skills/crewai-experiments/claude-skill -o ~/.claude/skills/crewai-experiments/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? and earn 85% of every sale.
Show it off in your README:
[](https://workflowstacks.com/skills/crewai-experiments?utm_source=github&utm_medium=badge)The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.
Related skills
More multi-agent tools founders pair with this one.