hevy
Skill1 starsChanged 10 months agoMITView on GitHub
Query workout data from Hevy including workouts, routines, exercises, and history. Use when user asks about their workouts, gym sessions, exercise progress, or fitness routines.
- Reads credentials
- Installs packages
Files
Hevy CLI
CLI for the Hevy workout tracking API. Query workouts, routines, exercises, and track progress.
Installation
npm install -g hevy-cliSetup
Requires Hevy Pro subscription for API access.
- Get API key from https://hevy.com/settings?developer
- Set environment variable:
export HEVY_API_KEY="your-key"
Commands
Status
hevy status # Check configuration and connection
hevy status --jsonWorkouts
hevy workouts # List recent workouts (default 5)
hevy workouts -n 10 # List 10 recent workouts
hevy workouts --all # Fetch all workouts
hevy workouts --kg # Show weights in kg (default is lbs)
hevy workout <id> # Show detailed workout
hevy workouts --json # Output as JSONRoutines
hevy routines # List all routines
hevy routine <id> # Show detailed routine
hevy routines --jsonExercises
hevy exercises # List all exercises
hevy exercises -s "bench press" # Search by name
hevy exercises --muscle chest # Filter by muscle group
hevy exercises --custom # Show only custom exercises
hevy exercises --jsonExercise History
hevy history <exercise-id> # Show history for exercise
hevy history <exercise-id> -n 50 # Limit entries
hevy history <exercise-id> --jsonStats
hevy count # Total workout count
hevy folders # List routine foldersUsage Examples
User: "What did I do at the gym today?"
hevy workouts -n 1User: "Show me my bench press progress"
hevy exercises -s "bench press" --json # Get exercise ID
hevy history <exercise-id> # View historyUser: "What routines do I have?"
hevy routinesUser: "How many workouts have I done?"
hevy countUser: "Find exercises for legs"
hevy exercises --muscle quadriceps
hevy exercises --muscle hamstringsNotes
- Weights default to lbs, use
--kgfor kilograms - Exercise IDs are UUIDs shown in detailed views and JSON output
- API has rate limits; avoid excessive
--allusage
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

