# Crew AI Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/crew-ai
> Markdown URL: https://aitinkerers.org/technologies/crew-ai.md
> Technology record last updated: 2026-03-05T04:34:41Z
> Generated: 2026-09-21T08:41:06Z

CrewAI is a lean, Python-based, multi-agent orchestration framework: it builds autonomous AI teams ("crews") with defined roles and tools to collaboratively execute complex workflows.

CrewAI, created by João Moura, is the lightning-fast, independent Python framework for multi-agent automation. It empowers developers to orchestrate high-performing AI teams ("crews") where specialized agents collaborate via context sharing and delegation to complete complex tasks. The framework supports any LLM and provides 100s of out-of-the-box tools (e.g., searching, database querying), plus sophisticated features like hierarchical processes and memory management. With over 100,000 certified developers, CrewAI sets the standard for enterprise-ready AI automation.

- Official technology site: https://www.crewai.com
- Public AI Tinkerers demos and talks: 4
- Result page: 1 of 1

## Recent Public Talks and Demos

### [The Zero-Partners VC - AI Native VC running on AI Agents](https://zurich.aitinkerers.org/talks/rsvp_cPNM9rUu4j8)

We are www.ellipsis-venture.com - 2 GPs who are AI Builders (x-Google, x-founders, x-Apple) who run a fund without employees. We built an agentic system that runs everything - sourcing, due diligence, score cards and memos, marketing, Investors Relations, Ops, etc.

- Event context: AI Tinkerers Zurich April 9th — 2026-04-09 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_cPNM9rUu4j8

### [SportAI](https://nurnberg.aitinkerers.org/talks/rsvp_3obGKGXiMrs)

I will be presenting my project, which uses an Agentic AI system to generate predictive insights for NFL, NBA, and MLB sports outcomes. The core of the project is an end-to-end Agentic AI pipeline built using the CrewAI framework, specifically designed to assist bettors by providing intelligent, data-driven predictions. Our Agentic AI system analyzes a wide range of game-related metrics, including: Player performance history Past game results for both teams Betting odds aggregated from multiple sportsbooks Latest team and player news These inputs are processed by a set of specialized agents, each responsible for a specific domain of analysis. Their findings are then passed to higher-level performance and analytical agents, which synthesize the information. Finally, a Decision Agent consolidates all the analyses and produces a comprehensive final prediction report, combining statistical insights, performance trends, and qualitative assessments. All sports data—across teams, players, odds, and news—is sourced directly from SportsData.io, ensuring accuracy and real-time reliability.

- Event context: AI Tinkerers Nürnberg Meetup – Nov 20 — 2025-11-20 — Nürnberg
- Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_3obGKGXiMrs

### [AI Agent Observability](https://seattle.aitinkerers.org/talks/rsvp_pzeKhDkm4VA)

I'll be showcasing how I've used Comet Opik to implement an observability strategy for my AI Agent project. I build an AI Agent to perform data analysis for me with CrewAI, but how do I monitor and evaluate a non-deterministic system like this? I'll talk through my code and show you the observability strategy I used for AI Agents.

- Event context: AI Tinkerers Seattle - April Meetup — 2025-04-25 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_pzeKhDkm4VA

### [Fixpoint - stateful AI workflows and human-in-the-loop](https://nyc.aitinkerers.org/talks/rsvp_lk-th021eeo)

We've been making an open-source project for building stateful, multi-step AI workflows. https://github.com/gofixpoint/fixpoint/ The use-case: you have LLM workflows that have multiple states/steps, and you want to make your workflow recoverable and easier to control. We let devs connect multiple LLM agents (or just prompts) and keep track of agent + workflow state (memory, cache past steps). We just added a human-in-the-loop UI. Fixpoint focuses on giving the programmer tight control over what each AI is doing at each step of the workflow (compared to frameworks like Crew AI, which are a bit more autonomous). You can think of us kind of like someone took SQS or Temporal, and super-charged it with AI-specific features.

- Event context: AI Tinkerers July Meetup — 2024-07-24 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_lk-th021eeo

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Airtable](https://aitinkerers.org/technologies/airtable) ([Markdown](https://aitinkerers.org/technologies/airtable.md)) — 6 public demos
- [Amazon SQS](https://aitinkerers.org/technologies/amazon-sqs) ([Markdown](https://aitinkerers.org/technologies/amazon-sqs.md)) — 1 public demo
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 215 public demos
- [etc](https://aitinkerers.org/technologies/etc) ([Markdown](https://aitinkerers.org/technologies/etc.md)) — 3 public demos
- [evolved to agentic frameworks like Lang-chain](https://aitinkerers.org/technologies/evolved-to-agentic-frameworks-like-lang-chain) ([Markdown](https://aitinkerers.org/technologies/evolved-to-agentic-frameworks-like-lang-chain.md)) — 1 public demo
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [Fixpoint](https://aitinkerers.org/technologies/fixpoint) ([Markdown](https://aitinkerers.org/technologies/fixpoint.md)) — 1 public demo
- [GitHub](https://aitinkerers.org/technologies/github) ([Markdown](https://aitinkerers.org/technologies/github.md)) — 74 public demos
- [Jupyter notebook](https://aitinkerers.org/technologies/jupyter-notebook) ([Markdown](https://aitinkerers.org/technologies/jupyter-notebook.md)) — 13 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos
- [moved to N8N](https://aitinkerers.org/technologies/moved-to-n8n) ([Markdown](https://aitinkerers.org/technologies/moved-to-n8n.md)) — 1 public demo
- [n8n](https://aitinkerers.org/technologies/n8n) ([Markdown](https://aitinkerers.org/technologies/n8n.md)) — 45 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Opik](https://aitinkerers.org/technologies/opik) ([Markdown](https://aitinkerers.org/technologies/opik.md)) — 2 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 105 public demos