swimmer-agents
AI Agents system using CrewAI to identify former elite swimmers in key tech positions. π Elite Talent Scout: AI-Powered Athlete Career Intelligence $1 $1 $1 π Project Overview This project is an **automated intelligence pipeline** designed to identify high-potential talent for the Tech and VC sectors by tracking the post-retirement careers of over **2,000 elite Israeli swimmers**. Unlike simple web scrapers, this system ingests raw, unstructured data (historical PDF competition results), applies comp
Rank
19
Safety
66
Updated
May 24, 2026
Source
GITHUB REPOS
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. Last updated 5/24/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Mlaitarovskyvendor Β· observed May 24, 2026
- Protocol compatibility
- OpenClawcompatibility Β· observed May 24, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
- Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/crewai-mlaitarovsky-swimmer-agents/snapshot"
Documentation
GITHUB REPOS
Read the full documentation
π Elite Talent Scout: AI-Powered Athlete Career Intelligence
π Project Overview
This project is an automated intelligence pipeline designed to identify high-potential talent for the Tech and VC sectors by tracking the post-retirement careers of over 2,000 elite Israeli swimmers.
Unlike simple web scrapers, this system ingests raw, unstructured data (historical PDF competition results), applies complex text processing algorithms to handle Hebrew language formatting, and deploys a Multi-Agent AI System (CrewAI) to locate and analyze professional profiles.
The Goal: Automatically identify former elite athletes who have transitioned into "Key Positions" (Founders, C-Level, VPs) in the business world.
π Key Features
- Unstructured Data Ingestion: Custom parser using
pdfplumberto extract data from legacy PDF tables (2004-2015). - Hebrew Text Normalization: algorithmic logic to fix visual text reversal common in PDF extraction of RTL (Right-to-Left) languages.
- Resilient Architecture: Implements a "Smart Resume" feature. The system logs progress in real-time and can restart from the exact point of failure (crash-proof).
- Rate Limit Handling: Dynamic error handling for OpenAI
429errors, implementing automatic backoff strategies to process thousands of records without user intervention. - Dual-Agent Verification:
- Researcher Agent: Performs deep web searches using Serper (Google API) to find LinkedIn profiles.
- Analyst Agent: Applies strict logic to filter out students/juniors and identify decision-makers.
π οΈ Tech Stack
- Core: Python 3.11+, Pandas
- AI Orchestration: CrewAI (Multi-Agent Systems)
- LLM: OpenAI GPT-4o-mini (Optimized for cost/performance balance)
- Data Extraction: PDFPlumber, Custom RegEx
- Search Intelligence: Serper API (Google Search Wrapper)
- DevOps: Docker, Python-Dotenv
βοΈ Architecture & Workflow
-
Data Extraction (
extract_hebrew_names.py):- Parses raw PDFs.
- Reverses Hebrew strings (e.g., converts
ΧΧΧ ΧΧΧtoΧΧΧ ΧΧΧ). - Cleans and dedupes data into
all_swimmers_cleaned.csv.
-
Agent Orchestration (
main.py):- Loads the dataset and checks the
processedlog to skip completed records. - Initializes a fresh CrewAI instance for each swimmer to prevent context leakage.
- Agent 1 (Researcher): Searches for "[Name] Israel LinkedIn" and verifies athletic background.
- Agent 2 (Analyst): Analyzes job titles against "Key Position" heuristics (e.g., Is "VP of R&D" a key role? -> Yes).
- Loads the dataset and checks the
-
Output:
- Data is streamed to
swimmers_report_FINAL_RUN.csvin real-time.
- Data is streamed to
π Installation (Local)
-
Clone the repository:
git clone [https://github.com/YourUsername/swimmer-agents.git](https://github.com/YourUsername/swimmer-agents.git) cd swimmer-agents -
Set up the environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate pip install -r requirements.txt -
Configure API Keys: Create a
.envfile in the root directory:OPENAI_API_KEY=sk-your-key-here SERPER_API_KEY=your-serper-key-here -
Run the Pipeline:
python main.py
π³ Docker Support
Run the entire system in an isolated container.
-
Build the image:
docker build -t swimmer-agent . -
Run the container:
docker run --env-file .env -v $(pwd)/data:/app/data swimmer-agent
π License
Distributed under the MIT License. See LICENSE for more information.
@x1pay/langchain
LangChain/LangGraph tools for AI agent x402 payments on X1
@langchain/langgraph-swarm
An implementation of a multi-agent swarm using LangGraph
@langchain/langgraph-supervisor
LangGraph Multi-Agent Supervisor
oceanbus-langchain
LangChain tools for OceanBus β give your LangChain and CrewAI agents a global identity, encrypted messaging, and Yellow Pages service discovery with a single import.
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"label": "Vendor",
"value": "Mlaitarovsky",
"category": "vendor",
"href": "https://github.com/MLaitarovsky/swimmer-agents",
"sourceUrl": "https://github.com/MLaitarovsky/swimmer-agents",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-05-24T06:17:00.409Z",
"isPublic": true,
"metadata": {}
},
{
"factKey": "protocols",
"label": "Protocol compatibility",
"value": "OpenClaw",
"category": "compatibility",
"href": "https://www.xpersona.co/api/v1/agents/crewai-mlaitarovsky-swimmer-agents/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-mlaitarovsky-swimmer-agents/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-05-24T06:17:00.409Z",
"isPublic": true,
"metadata": {}
},
{
"factKey": "handshake_status",
"label": "Handshake status",
"value": "UNKNOWN",
"category": "security",
"href": "https://www.xpersona.co/api/v1/agents/crewai-mlaitarovsky-swimmer-agents/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-mlaitarovsky-swimmer-agents/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true,
"metadata": {}
}
],
"events": []
}Record generated Oct 8, 2026.
